def script_createHistDifferenceHTML():
out_dir_meta='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d';
train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs=[dir[:-7] for dir in os.listdir('/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations') if dir.endswith('_pascal')];
layers=['pool5','fc6','fc7'];
degrees=[0,45,90,135,180];
delta=5;
caption_text=['Trained','Not Trained'];
replace=[out_dir_meta+'/',''];
degree=90;
for layer in layers:
out_file_html=os.path.join(out_dir_meta,layer+'_all_azimuths'+'.html')
img_paths=[];
caption_paths=[];
for dir in dirs:
img_paths_row=[];
caption_paths_row=[];
for idx,file_pre in enumerate([train_pre,non_train_pre]):
curr_dir=os.path.join(file_pre+'_'+layer+'_all_azimuths');
im_file=os.path.join(curr_dir,dir+'_'+str(degree)+'_'+str(delta)+'_compress.png');
img_paths_row.append(im_file.replace(replace[0],replace[1]));
caption_paths_row.append(caption_text[idx]+' '+layer+' '+dir);
img_paths.append(img_paths_row);
caption_paths.append(caption_paths_row);
visualize.writeHTML(out_file_html,img_paths,caption_paths,height=400,width=400);
print out_file_html
def script_visualizeScoreResults(test_output_file,gt_output_file,gt_data_output_file,out_file_html,rel_path,means,out_dir): data=np.load(gt_data_output_file); gt_label=np.load(gt_output_file); pred_label=np.load(test_output_file); print data.shape,gt_label.shape,pred_label.shape # print data.shape; im_paths=[];captions=[]; correct=0; for im_no in range(data.shape[0]): data_path=os.path.join(out_dir,str(im_no)+'_data.png'); # gt_path=os.path.join(out_dir,str(im_no)+'_gt.png'); # pred_path=os.path.join(out_dir,str(im_no)+'_pred.png'); # scipy.misc.imsave(data_path,reshapeMat(data[im_no],means)); visualize.saveMatAsImage(reshapeMat(data[im_no],means)/255,data_path); pred_label_curr=pred_label[im_no,0]; gt_label_curr=gt_label[im_no,0]; # visualize.saveMatAsImage(reshapeMat(gt[im_no],means),gt_path); # visualize.saveMatAsImage(reshapeMat(out[im_no],means),pred_path); im_paths.append([data_path.replace(rel_path[0],rel_path[1])]); if (pred_label_curr*gt_label_curr)>=0: correct=correct+1; captions.append(['Pred '+str(pred_label_curr)+' GT '+str(gt_label_curr)]); # if im_no==10: # break; print correct visualize.writeHTML(out_file_html,im_paths,captions,height=224,width=224);
def script_visualizeHashBinDensity(params):
hash_tables = params.hash_tables
in_files = params.in_files
out_files = params.out_files
out_file_html = params.out_file_html
rel_path = params.rel_path
bins = params.bins
height_width = params.height_width
min_maxs = []
for file_idx, in_file in enumerate(in_files):
densities = pickle.load(open(in_file, 'rb'))
densities = densities.values()
min_maxs.append((min(densities), max(densities)))
visualize.hist(densities,
out_files[file_idx],
bins=bins,
normed=True,
xlabel='Bin Density',
ylabel='Frequency',
title="Hash Bins' Density")
img_files_html = [[out_file.replace(rel_path[0], rel_path[1])]
for out_file in out_files]
captions_html = []
for idx_hash_table, hash_table in enumerate(hash_tables):
caption_curr = str(hash_table) + ' ' + str(min_maxs[idx_hash_table])
captions_html.append([caption_curr])
visualize.writeHTML(out_file_html, img_files_html, captions_html,
height_width[0], height_width[1])
def script_visualizeNNComparisonWithHash(params):
in_file = params.in_file
in_file_hash = params.in_file_hash
out_file_html = params.out_file_html
rel_path = params.rel_path
topn = params.topn
img_size = params.img_size
[
_, _, labels_test, labels_train, img_paths_test, img_paths_train,
indices, _
] = pickle.load(open(in_file, 'rb'))
[indices_hash, _, _] = pickle.load(open(in_file_hash, 'rb'))
img_paths_nn, captions_nn = getImgPathsAndCaptionsNN(
indices, img_paths_test, img_paths_train, labels_test, labels_train,
rel_path)
img_paths_hash, captions_hash = getImgPathsAndCaptionsNN(
indices_hash, img_paths_test, img_paths_train, labels_test,
labels_train, rel_path)
img_paths_all = []
captions_all = []
for idx in range(len(img_paths_nn)):
img_paths_all.append(img_paths_nn[idx][:topn])
img_paths_all.append(img_paths_hash[idx][:topn])
captions_all.append([x + ' nn' for x in captions_nn[idx][:topn]])
captions_all.append([x + ' hash' for x in captions_hash[idx][:topn]])
visualize.writeHTML(out_file_html, img_paths_all, captions_all,
img_size[0], img_size[1])
def visualizeRankedPatchesPerClass(class_score_info, num_to_display,
out_file_html, rel_path, height_width):
img_paths_all = []
captions_all = []
for selected_class, class_label, out_file in class_score_info:
[list_scores, list_files] = pickle.load(open(out_file, 'rb'))
num_patches = len(list_files)
img_paths, scores_picked, idx_display = getNRankedPatches(
list_scores, list_files, num_to_display)
img_paths = [
img_path.replace(rel_path[0], rel_path[1])
for img_path in img_paths
]
captions = []
for idx_idx_curr, idx_curr in enumerate(idx_display):
score_curr = round(scores_picked[idx_idx_curr], 5)
caption_curr = str(idx_idx_curr) + ' Rank ' + str(
idx_curr +
1) + ' of ' + str(num_patches) + ' Score: ' + str(score_curr)
caption_curr = class_label + ' ' + caption_curr
captions.append(caption_curr)
# captions=[[list_scores[sort_idx[idx_curr]],5))] for idx_idx_curr,idx_curr in enumerate(idx_display)]
# print captions
img_paths_all.append(img_paths)
captions_all.append(captions)
img_paths_all = np.array(img_paths_all).T
captions_all = np.array(captions_all).T
visualize.writeHTML(out_file_html, img_paths_all, captions_all,
height_width[0], height_width[0])
print out_file_html
def script_compareHashWithToyExperiment(params):
in_file = params.in_file;
num_hash_tables_all = params.num_hash_tables_all;
key_type = params.key_type;
out_file_indices = params.out_file_indices;
out_file_pres = params.out_file_pres;
out_file_html = params.out_file_html;
rel_path = params.rel_path;
[features_test,features_train,labels_test,labels_train,_,_,indices,_]=pickle.load(open(in_file,'rb'));
visualize.saveMatAsImage(indices,out_file_indices);
hammings=[];
for out_file_pre,num_hash_tables in zip(out_file_pres,num_hash_tables_all):
indices_hash = getIndicesHash(features_test,features_train,num_hash_tables,key_type);
visualize.saveMatAsImage(indices_hash,out_file_pre+'.png');
hamming=util.getHammingDistance(indices,indices_hash);
pickle.dump([indices_hash,indices,hamming],open(out_file_pre+'.p','wb'));
hammings.append(np.mean(hamming));
sizes = scipy.misc.imread(out_file_indices);
sizes = sizes.shape
im_files_html=[];
captions_html=[];
for idx,out_file_pre in enumerate(out_file_pres):
out_file_curr=out_file_pre+'.png'
key_str=str(key_type);
key_str=key_str.replace('<type ','').replace('>','');
caption_curr='NN Hash. Num Hash Tables: '+str(num_hash_tables_all[idx])+' '+'Hamming Distance: '+str(hammings[idx]);
im_files_html.append([out_file_indices.replace(rel_path[0],rel_path[1]),out_file_curr.replace(rel_path[0],rel_path[1])])
captions_html.append(['NN cosine',caption_curr]);
visualize.writeHTML(out_file_html,im_files_html,captions_html,sizes[0]/2,sizes[1]/2);
def script_visualizePatchesByAngleDifference(params):
out_file=params.out_file
rel_path=params.rel_path
output=getNNRankComparisonInfo(params)
img_paths_test = output['img_paths_test']
img_paths_train = output['img_paths_nn_train']
img_paths_no_train = output['img_paths_nn_no_train']
nn_rank_train = output['nn_rank_train']
nn_rank_no_train = output['nn_rank_no_train']
html_img_paths=[];
captions=[];
for idx,org_img_path in enumerate(img_paths_test):
for nn_rank_row,img_path_row in [(nn_rank_train[idx],img_paths_train[idx]),(nn_rank_no_train[idx],img_paths_no_train[idx])]:
html_row=[];
caption_row=[];
html_row.append(org_img_path.replace(rel_path[0],rel_path[1]));
caption_row.append('Test Image ')
for idx_im,im in enumerate(img_path_row):
html_row.append(im.replace(rel_path[0],rel_path[1]));
caption_row.append(str(nn_rank_row[idx_im])+' '+str(idx))
html_img_paths.append(html_row);
captions.append(caption_row);
visualize.writeHTML(out_file,html_img_paths,captions);
def script_visualizeHashBinDensity(params):
hash_tables = params.hash_tables
in_files = params.in_files
out_files = params.out_files
out_file_html = params.out_file_html
rel_path = params.rel_path
bins = params.bins
height_width = params.height_width
min_maxs=[];
for file_idx,in_file in enumerate(in_files):
densities=pickle.load(open(in_file,'rb'));
densities=densities.values();
min_maxs.append((min(densities),max(densities)))
visualize.hist(densities,out_files[file_idx],bins=bins,normed=True,xlabel='Bin Density',
ylabel='Frequency',title="Hash Bins' Density")
img_files_html=[[out_file.replace(rel_path[0],rel_path[1])] for out_file in out_files];
captions_html=[]
for idx_hash_table,hash_table in enumerate(hash_tables):
caption_curr=str(hash_table)+' '+str(min_maxs[idx_hash_table]);
captions_html.append([caption_curr]);
visualize.writeHTML(out_file_html,img_files_html,captions_html,height_width[0],height_width[1]);
def script_visualizePatchesByAngleDifference(params):
out_file = params.out_file
rel_path = params.rel_path
output = getNNRankComparisonInfo(params)
img_paths_test = output['img_paths_test']
img_paths_train = output['img_paths_nn_train']
img_paths_no_train = output['img_paths_nn_no_train']
nn_rank_train = output['nn_rank_train']
nn_rank_no_train = output['nn_rank_no_train']
html_img_paths = []
captions = []
for idx, org_img_path in enumerate(img_paths_test):
for nn_rank_row, img_path_row in [
(nn_rank_train[idx], img_paths_train[idx]),
(nn_rank_no_train[idx], img_paths_no_train[idx])
]:
html_row = []
caption_row = []
html_row.append(org_img_path.replace(rel_path[0], rel_path[1]))
caption_row.append('Test Image ')
for idx_im, im in enumerate(img_path_row):
html_row.append(im.replace(rel_path[0], rel_path[1]))
caption_row.append(str(nn_rank_row[idx_im]) + ' ' + str(idx))
html_img_paths.append(html_row)
captions.append(caption_row)
visualize.writeHTML(out_file, html_img_paths, captions)
def script_createHistsWithSpecificAngleHtml():
out_dir_meta='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d';
train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs=[dir[:-7] for dir in os.listdir('/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations') if dir.endswith('_pascal')];
layers=['pool5','fc6','fc7'];
deg_to_see=0;
degree=90;
delta=5;
out_file_html=os.path.join('/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d','hist_angle_restrict_'+str(deg_to_see)+'_'+str(degree)+'_comparison_non_compress.html');
replace=['/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/',''];
img_paths=[];
captions=[];
for dir in dirs:
for layer in layers:
single_row=[];
single_row_caption=[];
for caption_curr,file_pre in [('Trained',train_pre),('Not trained',non_train_pre)]:
curr_dir=file_pre+'_'+layer+'_all_azimuths'
img_path=os.path.join(curr_dir,dir+'_'+str(deg_to_see)+'_'+str(degree)+'_'+str(delta)+'_non_compress.png');
img_path=img_path.replace(replace[0],replace[1]);
single_row.append(img_path);
single_row_caption.append(caption_curr+' '+dir+' '+layer);
img_paths.append(single_row);
captions.append(single_row_caption);
visualize.writeHTML(out_file_html,img_paths,captions,height=300,width=400)
def visualizeBestTubeRank(params):
class_labels_map = params.class_labels_map
rel_path = params.rel_path
out_file_html = params.out_file_html
out_dir = params.out_dir
score_info_file = params.score_info_file
[class_labels,class_idx_map]=zip(*class_labels_map);
class_labels=list(class_labels);
class_idx_map=list(class_idx_map);
[score_files,score_files_info]=pickle.load(open(score_info_file,'rb'));
class_idx=np.unique(score_files_info[:,0]);
tubes=np.unique(score_files_info[:,3])
best_tubes_overall=score_files_info[:,3];
out_file=os.path.join(out_dir,'overall.png');
visualize.hist(best_tubes_overall,out_file,bins=tubes,normed=True,xlabel='Tube_idx',ylabel='Frequency',title='Best Tube Over All',cumulative=False)
img_paths=[];
captions=[];
for class_idx_curr in class_idx:
label=class_labels[class_idx_map.index(class_idx_curr)]
out_file=os.path.join(out_dir,label+'.png');
img_paths.append([out_file.replace(rel_path[0],rel_path[1])]);
captions.append([label]);
rel_tubes=score_files_info[score_files_info[:,0]==class_idx_curr,3];
print class_idx_curr,rel_tubes.shape,min(rel_tubes),max(rel_tubes);
visualize.hist(rel_tubes,out_file,bins=tubes,normed=True,xlabel='Tube Idx',ylabel='Frequency',title='Best Tube '+label,cumulative=False)
# visualize.save
visualize.writeHTML(out_file_html,img_paths,captions,400,400);
def visualizeRankedPatchesPerClass(class_score_info,num_to_display,out_file_html,rel_path,height_width):
img_paths_all=[];
captions_all=[];
for selected_class,class_label,out_file in class_score_info:
[list_scores,list_files] = pickle.load(open(out_file,'rb'));
num_patches=len(list_files);
img_paths,scores_picked,idx_display=getNRankedPatches(list_scores,list_files,num_to_display)
img_paths=[img_path.replace(rel_path[0],rel_path[1]) for img_path in img_paths];
captions=[];
for idx_idx_curr,idx_curr in enumerate(idx_display):
score_curr=round(scores_picked[idx_idx_curr],5)
caption_curr=str(idx_idx_curr)+' Rank '+str(idx_curr+1)+' of '+str(num_patches)+' Score: '+str(score_curr);
caption_curr=class_label+' '+caption_curr;
captions.append(caption_curr);
# captions=[[list_scores[sort_idx[idx_curr]],5))] for idx_idx_curr,idx_curr in enumerate(idx_display)]
# print captions
img_paths_all.append(img_paths);
captions_all.append(captions);
img_paths_all=np.array(img_paths_all).T
captions_all=np.array(captions_all).T
visualize.writeHTML(out_file_html,img_paths_all,captions_all,height_width[0],height_width[0]);
print out_file_html
def script_createComparativeHtmls():
layers = ['pool5', 'fc6', 'fc7']
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations'
file_dir = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB'
dirs = [
dir[:-7] for dir in os.listdir(path_to_anno) if dir.endswith('pascal')
]
file_name = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
file_name_alt = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
replace_paths = ['/disk2', '../../../..']
out_file_pre = 'nn_performance_comparison_trained_notrained'
out_file_pre = os.path.join(
'/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d',
out_file_pre)
for layer in layers:
file_name_l = file_name + '_' + layer
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
idx_sort_binned = script_nearestNeigbourExperiment.sortByPerformance(
indices, gt_labels, 1, perClass=True)
img_paths = [
x.replace(replace_paths[0], replace_paths[1]) for x in img_paths
]
im_paths, captions = visualize.createImageAndCaptionGrid(
img_paths, gt_labels, indices, dirs)
file_name_l = file_name_alt + '_' + layer
[img_paths_alt, gt_labels_alt, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
img_paths_alt = [
x.replace(replace_paths[0], replace_paths[1])
for x in img_paths_alt
]
im_paths_alt, captions_alt = visualize.createImageAndCaptionGrid(
img_paths, gt_labels, indices, dirs)
im_paths_alt = [
im_paths_alt[img_paths_alt.index(curr_img_path)]
for curr_img_path in img_paths
]
captions_alt = [
captions_alt[img_paths_alt.index(curr_img_path)]
for curr_img_path in img_paths
]
im_paths_big = []
captions_big = []
for idx_curr in idx_sort_binned:
im_paths_big.append(im_paths[idx_curr])
im_paths_big.append(im_paths_alt[idx_curr])
captions_big.append(captions[idx_curr])
captions_big.append(captions_alt[idx_curr])
visualize.writeHTML(out_file_pre + '_' + layer + '.html', im_paths_big,
captions_big)
def script_visualizePascalNeighborsFromOtherClass(params):
db_path_out = params.db_path_out
class_id_pascal = params.class_id_pascal
limit = params.limit
layer = params.layer
trainFlag = params.trainFlag
rel_path = params.rel_path
out_file_html = params.out_file_html
top_n = params.top_n
height_width = params.height_width
mani = Imagenet_Manipulator(db_path_out)
mani.openSession()
vals = mani.select(
(Imagenet.idx, Imagenet.img_path, Imagenet.class_label_imagenet, Imagenet.neighbor_index),
(Imagenet.class_id_pascal == class_id_pascal, Imagenet.layer == layer, Imagenet.trainedClass == trainFlag),
distinct=True,
limit=limit,
)
print len(vals)
idx_non_pascal = mani.select(
(Imagenet.idx,),
(Imagenet.class_id_pascal == None, Imagenet.layer == layer, Imagenet.trainedClass == trainFlag),
distinct=True,
)
img_paths_html = []
captions_html = []
for val_curr in vals:
html_row = []
captions_row = []
img_path = val_curr[1]
imagenet_label = val_curr[2]
nearest_neighbor = val_curr[3]
remove_bool = np.in1d(nearest_neighbor, idx_non_pascal, invert=True)
nearest_neighbor = np.delete(nearest_neighbor, np.where(remove_bool))
html_row.append(img_path.replace(rel_path[0], rel_path[1]))
captions_row.append("test image " + imagenet_label)
for idx_curr in range(top_n):
idx_nn = nearest_neighbor[idx_curr]
(img_path_nn, class_id_imagenet, class_label_imagenet) = mani.select(
(Imagenet.img_path, Imagenet.class_id_imagenet, Imagenet.class_label_imagenet),
(Imagenet.idx == idx_nn, Imagenet.layer == layer, Imagenet.trainedClass == trainFlag),
distinct=True,
)[0]
html_row.append(img_path_nn.replace(rel_path[0], rel_path[1]))
captions_row.append(class_id_imagenet + " " + class_label_imagenet)
img_paths_html.append(html_row)
captions_html.append(captions_row)
# raw_input();
mani.closeSession()
visualize.writeHTML(out_file_html, img_paths_html, captions_html, height_width[0], height_width[1])
def main():
out_dir='/disk2/januaryExperiments/jacob_pascal_2007';
img_folder=os.path.join(out_dir,'im_results');
res_folder=os.path.join(out_dir,'results');
out_file_html=os.path.join(out_dir,'jacob_comparison.html');
width_heigh=[400,400];
rel_path=['/disk2','../../../..']
rel_path_res=['/disk2','../../..']
path_to_im='/disk2/pascal_voc_2007/VOCdevkit/VOC2007/JPEGImages/';
im_list=[im_curr for im_curr in os.listdir(img_folder) if im_curr.endswith('.jpg')];
# im_just_name=[im_curr[:im_curr.index('.')] for im_curr in im_list];
# text_files=[os.path.join(res_folder,im_curr+'.txt') for im_curr in im_just_name]
img_corrs=[];
img_arrows=[];
for im_curr in im_list:
im_jn=im_curr[:im_curr.index('.')];
im_txt=os.path.join(res_folder,im_jn+'.txt');
with open(im_txt,'rb') as f:
img_corr=f.readline();
img_corr=img_corr[:img_corr.index(' ')];
img_corrs.append(img_corr);
img_arrows.append(os.path.join(img_folder,im_curr));
# print img_corrs,img_arrow
# raw_input();
img_paths=[];
captions=[];
for img_org,img_arrow in zip(img_corrs,img_arrows):
img_paths.append([img_org.replace(rel_path[0],rel_path[1]),img_arrow.replace(rel_path_res[0],rel_path_res[1])])
captions.append([img_org,img_arrow]);
visualize.writeHTML(out_file_html,img_paths,captions,400,400)
return
path_to_im='/disk2/pascal_voc_2007/VOCdevkit/VOC2007/JPEGImages/';
num_im=1000;
im_list=[os.path.join(path_to_im,im_curr) for im_curr in os.listdir(path_to_im) if im_curr.endswith('.jpg')];
idx=range(len(im_list));
random.shuffle(idx);
idx=idx[:num_im];
im_list=[im_list[idx_curr] for idx_curr in idx];
out_dir='/disk2/januaryExperiments/jacob_pascal_2007';
if not os.path.exists(out_dir):
os.mkdir(out_dir);
jacob_dir='/home/maheenrashid/Downloads/jacob/try_2/optical_flow_prediction/examples/opticalflow';
txt_file=os.path.join(jacob_dir,'test.txt');
res_folder=os.path.join(out_dir,'results');
if not os.path.exists(res_folder):
os.mkdir(res_folder);
with open(txt_file,'wb') as f:
for im in im_list:
f.write(im+' 1\n');
def makeFloHtml(out_file_html,img_files,flo_files,height=200,width=200):
img_paths=[];
captions=[];
for img_file,flo_file in zip(img_files,flo_files):
img_path=[];
img_path.append(util.getRelPath(img_file,'/disk2'));
img_path.append(util.getRelPath(flo_file,'/disk2'));
img_paths.append(img_path);
captions.append(['img','flo']);
visualize.writeHTML(out_file_html,img_paths,captions,height,width);
def script_writeFloVizHTML(out_file_html,out_dir_viz,flo_files,im_files,tif_files,clusters,tifAsPng=False):
img_paths=[];
captions=[];
# idx=0;
for flo_file,im_file,tif_file in zip(flo_files,im_files,tif_files):
# print idx;
# print tif_file
assert os.path.exists(tif_file);
assert os.path.exists(im_file);
# print tif_file
# if not os.path.exists(tif_file) or not os.path.exists(im_file) :
# continue;
file_name=util.getFileNames([flo_file],ext=False)[0];
out_file_pre=os.path.join(out_dir_viz,file_name);
out_file_flo_viz=out_file_pre+'_flo.png';
out_files_tif=[out_file_pre+'_tifim_x.png',out_file_pre+'_tifim_y.png',out_file_pre+'_tifflo.png'];
if not os.path.exists(out_file_flo_viz):
flo=util.readFlowFile(flo_file);
po.saveFloFileViz(flo_file,out_file_flo_viz);
for idx,out_file_tif_viz in enumerate(out_files_tif):
tif=scipy.misc.imread(tif_file)[:,:,:2];
if idx==0 and not os.path.exists(out_file_tif_viz):
tif_flo=replaceClusterIdWithFlow(tif,clusters);
po.saveMatFloViz(tif_flo,out_file_tif_viz);
if not os.path.exists(out_file_tif_viz) and idx==1:
tif_x=np.array(tif[:,:,0]*(255.0/clusters.shape[0]),dtype=int);
tif_x=np.dstack((tif_x,tif_x,tif_x));
scipy.misc.imsave(out_file_tif_viz,tif_x);
if not os.path.exists(out_file_tif_viz) and idx==2:
tif_x=np.array(tif[:,:,1]*(255.0/clusters.shape[0]),dtype=int);
tif_x=np.dstack((tif_x,tif_x,tif_x));
scipy.misc.imsave(out_file_tif_viz,tif_x);
img_paths_curr=[im_file,out_file_flo_viz]+out_files_tif;
im_name=util.getFileNames([im_file],ext=False)[0];
captions_curr=[im_name,'flo_viz']+['tif_flo_viz']*len(out_files_tif)
# if tifAsPng:
# img_paths_curr.append(out_file_tif_viz.replace('_x.png','_y.png'));
# captions_curr.append('tif_flo_viz');
img_paths_curr=[util.getRelPath(file_curr) for file_curr in img_paths_curr];
img_paths.append(img_paths_curr);
captions.append(captions_curr);
# idx=idx+1;
visualize.writeHTML(out_file_html,img_paths,captions)
def makeFloVizHTML(out_file_html,img_paths,dir_flo_viz):
# out_file_html=os.path.join(out_dir,'flo_viz.html');
img_paths_html=[];
captions_html=[];
for img_path,img_file_name in zip(img_paths,util.getFileNames(img_paths,ext=False)):
out_file_flo_viz=os.path.join(dir_flo_viz,img_file_name+'.png');
if img_path.startswith('/disk2'):
img_path='/disk3'+img_path;
img_paths_curr=[util.getRelPath(img_path,'/disk3'),util.getRelPath(out_file_flo_viz,'/disk3')];
img_paths_html.append(img_paths_curr);
captions_html.append([img_file_name,'flo']);
visualize.writeHTML(out_file_html,img_paths_html,captions_html);
def script_testOnYoutube():
val_file='/disk2/mayExperiments/finetuning_youtube_hmdb_llr/val_eq.txt'
out_dir='/disk2/mayExperiments/eval_ucf_finetune';
clusters_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction_test/examples/opticalflow/clusters.mat';
gpu=0;
util.mkdir(out_dir);
# model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction_test/examples/opticalflow/final.caffemodel';
# out_dir_model=os.path.join(out_dir,'original_model');
model_file='/disk2/mayExperiments/ft_youtube_hmdb_ucfClusters/OptFlow_youtube_hmdb__iter_55000.caffemodel';
out_dir_model=os.path.join(out_dir,'ft_ucf_model');
util.mkdir(out_dir_model);
out_dir_flo=os.path.join(out_dir_model,'flo');
out_dir_flo_viz=os.path.join(out_dir_model,'flo_viz');
util.mkdir(out_dir_flo);util.mkdir(out_dir_flo_viz)
num_to_pick=20;
img_paths=util.readLinesFromFile(val_file);
img_paths=[img_path[:img_path.index(' ')] for img_path in img_paths];
class_names=[file_curr[:file_curr.index('_')] for file_curr in util.getFileNames(img_paths)];
classes=list(set(class_names));
class_names=np.array(class_names);
img_paths_test=[];
for class_curr in classes:
idx_rel=np.where(class_names==class_curr)[0];
idx_rel=idx_rel[:num_to_pick];
img_paths_test.extend([img_paths[idx_curr] for idx_curr in idx_rel]);
# po.script_saveFlosAndViz(img_paths_test,out_dir_flo,out_dir_flo_viz,gpu,model_file,clusters_file);
out_file_html=os.path.join(out_dir,'model_comparison.html');
out_dirs_flo_viz=[os.path.join(out_dir,'original_model','flo_viz'),os.path.join(out_dir,'ft_ucf_model','flo_viz')];
out_dirs_flo_viz_captions=['original_model','ft_ucf_model'];
img_paths_html=[];
captions_html=[];
img_names=util.getFileNames(img_paths_test,ext=False);
for img_path_test,img_name in zip(img_paths_test,img_names):
row_curr=[];
row_curr.append(util.getRelPath(img_path_test));
for out_dir_curr in out_dirs_flo_viz:
file_curr=os.path.join(out_dir_curr,img_name+'.png');
row_curr.append(util.getRelPath(file_curr));
captions_curr=[img_name]+out_dirs_flo_viz_captions;
img_paths_html.append(row_curr)
captions_html.append(captions_curr);
visualize.writeHTML(out_file_html,img_paths_html,captions_html);
def script_visualizeRankDifferenceAsHist(params):
out_file_pre = params.out_file_pre;
out_file_html = params.out_file_html;
rel_path = params.rel_path;
class_ids = params.class_id;
layers = params.layer
if not hasattr(class_ids, '__iter__'):
class_ids = [class_ids];
if not hasattr(class_ids, '__iter__'):
layers = [layers];
img_paths_html=[];
captions=[];
for class_id in class_ids:
img_paths_html_row=[];
captions_row=[];
for layer in layers:
params = params._replace(class_id=class_id)
params = params._replace(layer=layer)
output=getNNRankComparisonInfo(params);
indices_difference=experiments_super.getDifferenceInRank(output['img_paths_nn_train'],
output['img_paths_nn_no_train'],
output['nn_rank_train'],
output['nn_rank_no_train']);
xlabel='Difference in Rank (Train - Untrained)';
ylabel='Frequency'
title=class_id+' '+layer
indices_difference=[diff_curr for diffs_curr in indices_difference for diff_curr in diffs_curr]
if len(indices_difference)==0:
continue;
out_file_im=out_file_pre+'_'+str(params.angle)+'_'+str(params.diff)+'_'+str(params.delta)+'_'+class_id+'_'+layer+'.png';
img_paths_html_row.append(out_file_im.replace(rel_path[0],rel_path[1]));
total=len(indices_difference)
sum_less=sum(np.array(indices_difference)<0)/float(total);
sum_less='%0.2f'%(sum_less,)
sum_more=sum(np.array(indices_difference)>=0)/float(total);
sum_more='%0.2f'%(sum_more,)
captions_row.append('Total '+str(total)+', <0: '+sum_less+', >0: '+sum_more);
visualize.hist(indices_difference,out_file=out_file_im,bins=params.bins,normed=params.normed,xlabel=xlabel,ylabel=ylabel,title=title);
img_paths_html.append(img_paths_html_row);
captions.append(captions_row);
visualize.writeHTML(out_file_html,img_paths_html,captions,params.height_width[0],params.height_width[1]);
def comparativeLossViz(img_dirs,
file_post,
loss_post,
range_batches,
range_images,
out_file_html,
dir_server,
img_caption_pre=None):
img_files_all = []
captions_all = []
if img_caption_pre is not None:
assert len(img_caption_pre) == len(img_dirs)
for batch_num in range_batches:
# range(1,num_batches+1):
for im_num in range_images:
for idx_img_dir, img_dir in enumerate(img_dirs):
loss_all = np.load(
os.path.join(img_dir,
str(batch_num) + loss_post))
if im_num > loss_all.shape[0]:
continue
loss_curr = loss_all[im_num - 1, 0]
loss_str = "{:10.4f}".format(loss_curr)
files_curr = [
os.path.join(
img_dir,
str(batch_num) + '_' + str(im_num) + file_post_curr)
for file_post_curr in file_post
]
files_curr = [
util.getRelPath(file_curr, dir_server)
for file_curr in files_curr
]
captions_curr = [
os.path.split(file_curr)[1] + ' ' + loss_str
for file_curr in files_curr
]
if img_caption_pre is not None:
captions_curr = [
img_caption_pre[idx_img_dir] + ' ' + caption_curr
for caption_curr in captions_curr
]
img_files_all.append(files_curr)
captions_all.append(captions_curr)
visualize.writeHTML(out_file_html, img_files_all, captions_all, 224, 224)
def script_createHistComparative():
out_dir_meta='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d';
train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs=[dir[:-7] for dir in os.listdir('/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations') if dir.endswith('_pascal')];
layers=['pool5','fc6','fc7'];
delta=5;
caption_text=['Trained','Not Trained'];
replace=[out_dir_meta+'/',''];
degree=90;
deg_to_see=0;
# train_files=[os.path.join(train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p') for layer in layers for dir in dirs];
# non_train_files=[os.path.join(non_train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p') for layer in layers for dir in dirs];
# for idx in range(len(train_files)):
combos=[(dir,layer) for dir in dirs for layer in layers];
out_file_html=os.path.join(out_dir_meta,'hist_by_degree_'+str(degree)+'_comparisons_compress.html');
img_paths=[];
captions=[];
for dir,layer in combos:
file_train=os.path.join(train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p');
# train_files[idx];
file_non_train=os.path.join(non_train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p');
# non_train_files[idx];
hists_train,bins_train=pickle.load(open(file_train,'rb'));
hists_non_train,bins_non_train=pickle.load(open(file_non_train,'rb'));
mid_points_train=[bins_train[i]+bins_train[i+1]/float(2) for i in range(len(bins_train)-1)];
mid_points_non_train=[bins_non_train[i]+bins_non_train[i+1]/float(2) for i in range(len(bins_non_train)-1)];
# dir=file_train[file_train.rindex('/')+1:];
# dir=dir[:dir.index('_')];
out_file_just_file=layer+'_'+dir+'_'+str(degree)+'_'+str(delta)+'.png'
out_file=os.path.join(out_dir_meta,out_file_just_file)
title=dir+' Comparison';
xlabel='Distance Rank';
ylabel='Frequency';
# print out_file
img_paths.append([out_file_just_file]);
captions.append([dir+' '+layer]);
visualize.plotSimple(zip([mid_points_train,mid_points_non_train],[hists_train,hists_non_train]),out_file,title=title,xlabel=xlabel,ylabel=ylabel,legend_entries=['Trained','Non Trained'],loc=0);
print out_file_html
visualize.writeHTML(out_file_html,img_paths,captions,width=400,height=400);
def script_compareAzimuth():
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations/chair_pascal'
im_dir = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB'
out_file_html = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB/chair_angle_check.html'
anno_files = [
os.path.join(path_to_anno, file_name)
for file_name in os.listdir(path_to_anno) if file_name.endswith('.mat')
]
list_of_chairs = []
for anno_file in anno_files:
just_file = anno_file[anno_file.rindex('/') + 1:]
just_file = just_file[:-4]
curr_dict = scipy.io.loadmat(anno_file,
squeeze_me=True,
struct_as_record=False)
objects = curr_dict['record'].objects
if not hasattr(objects, '__iter__'):
objects = [objects]
for idx, obj in enumerate(objects):
if obj.__dict__['class'] == 'chair':
im_file = os.path.join(
im_dir, just_file + '_chair_' + str(idx) + '.jpg')
list_of_chairs.append((im_file, obj.viewpoint.azimuth_coarse))
angles = list(zip(*list_of_chairs)[1])
images = list(zip(*list_of_chairs)[0])
angles = np.array(angles)
angles_uni = np.unique(angles)
col_im = []
col_caption = []
for angle_uni in angles_uni:
idx_uni = np.where(angles == angle_uni)[0]
row_im_curr = []
row_caption_curr = []
for idx_curr in range(min(5, len(idx_uni))):
idx_im = idx_uni[idx_curr]
image_just_name = images[idx_im]
image_just_name = image_just_name[image_just_name.rindex('/') + 1:]
row_im_curr.append(image_just_name)
row_caption_curr.append(str(angle_uni))
col_im.append(row_im_curr)
col_caption.append(row_caption_curr)
print col_im[:5]
print col_caption[:5]
visualize.writeHTML(out_file_html, col_im, col_caption)
def makeImTifViz(img_paths_all,tif_paths_all,out_file_html,out_dir_tif,num_clusters=40,disk_path='/disk2'): out_files_tif_x=[os.path.join(out_dir_tif,img_name+'_x.png') for img_name in util.getFileNames(tif_paths_all,ext='False')]; out_files_tif_y=[os.path.join(out_dir_tif,img_name+'_y.png') for img_name in util.getFileNames(tif_paths_all,ext='False')]; for tif_path,out_file_x,out_file_y in zip(tif_paths_all,out_files_tif_x,out_files_tif_y): tif=scipy.misc.imread(tif_path); # print np.min(tif[:,:,:2]),np.max(tif[:,:,:2]) assert np.min(tif[:,:,:2])>0 and np.max(tif[:,:,:2])<num_clusters+1; saveTifGray(tif,out_file_x,out_file_y,num_clusters) # out_file_html=out_dir_tif+'.html'; img_paths_html=[[util.getRelPath(img_curr,disk_path) for img_curr in img_list] for img_list in zip(img_paths_all,out_files_tif_x,out_files_tif_y)]; # captions_html=[[util.getFileNames([img_curr],ext=False)[0] for img_curr in img_list] for img_list in zip(img_paths_all,out_files_tif_x,out_files_tif_y)]; captions_html=[['Image','Tif_x','Tif_y']]*len(img_paths_html); visualize.writeHTML(out_file_html,img_paths_html,captions_html);
def saveHTML(out_us, us_test, batch_size=50, num_iter=2):
dir_server = './'
post_us = ['_gt_pts.npy', '_pred_pts.npy']
im_paths, gt_pt_files, pred_pt_files = us_getFilePres(
us_test, out_us, post_us, num_iter, batch_size)
errors_curr = us_getErrorsAll(us_test, out_us, post_us, num_iter,
batch_size)
err = np.array(errors_curr)
bin_keep = err >= 0
err[err < 0] = 0
div = np.sum(bin_keep, 1)
sum_val = np.sum(err, 1).astype(np.float)
avg = sum_val / div
post_ims_us = [
'_org_nokp.jpg',
'_gt.jpg',
'_warp_nokp.jpg',
'_warp.jpg',
'_org.jpg',
]
captions_for_row = [
'Input', 'Ground Truth', 'Warped Image', 'Prediction Warped',
'Prediction'
]
out_file_html = os.path.join(out_us, 'results.html')
idx_sort = np.argsort(avg)
ims = []
captions = []
for idx_idx, idx_curr in enumerate(idx_sort):
file_curr = gt_pt_files[idx_curr]
file_curr = os.path.split(file_curr)[1]
file_curr = file_curr[:file_curr.index('_gt')]
files_us = [
os.path.join(dir_server, file_curr + post_im_curr)
for post_im_curr in post_ims_us
]
captions_us = [
str(idx_idx) + ' ' + caption_curr
for caption_curr in captions_for_row
]
ims.append(files_us)
captions.append(captions_us)
visualize.writeHTML(out_file_html, ims, captions)
print out_file_html
def script_createHistsWithSpecificAngleHtml():
out_dir_meta = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d'
train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs = [
dir[:-7] for dir in os.listdir(
'/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations')
if dir.endswith('_pascal')
]
layers = ['pool5', 'fc6', 'fc7']
deg_to_see = 0
degree = 90
delta = 5
out_file_html = os.path.join(
'/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d',
'hist_angle_restrict_' + str(deg_to_see) + '_' + str(degree) +
'_comparison_non_compress.html')
replace = [
'/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/',
''
]
img_paths = []
captions = []
for dir in dirs:
for layer in layers:
single_row = []
single_row_caption = []
for caption_curr, file_pre in [('Trained', train_pre),
('Not trained', non_train_pre)]:
curr_dir = file_pre + '_' + layer + '_all_azimuths'
img_path = os.path.join(
curr_dir, dir + '_' + str(deg_to_see) + '_' + str(degree) +
'_' + str(delta) + '_non_compress.png')
img_path = img_path.replace(replace[0], replace[1])
single_row.append(img_path)
single_row_caption.append(caption_curr + ' ' + dir + ' ' +
layer)
img_paths.append(single_row)
captions.append(single_row_caption)
visualize.writeHTML(out_file_html,
img_paths,
captions,
height=300,
width=400)
def script_compareHashWithToyExperiment(params):
in_file = params.in_file
num_hash_tables_all = params.num_hash_tables_all
key_type = params.key_type
out_file_indices = params.out_file_indices
out_file_pres = params.out_file_pres
out_file_html = params.out_file_html
rel_path = params.rel_path
[
features_test, features_train, labels_test, labels_train, _, _,
indices, _
] = pickle.load(open(in_file, 'rb'))
visualize.saveMatAsImage(indices, out_file_indices)
hammings = []
for out_file_pre, num_hash_tables in zip(out_file_pres,
num_hash_tables_all):
indices_hash = getIndicesHash(features_test, features_train,
num_hash_tables, key_type)
visualize.saveMatAsImage(indices_hash, out_file_pre + '.png')
hamming = util.getHammingDistance(indices, indices_hash)
pickle.dump([indices_hash, indices, hamming],
open(out_file_pre + '.p', 'wb'))
hammings.append(np.mean(hamming))
sizes = scipy.misc.imread(out_file_indices)
sizes = sizes.shape
im_files_html = []
captions_html = []
for idx, out_file_pre in enumerate(out_file_pres):
out_file_curr = out_file_pre + '.png'
key_str = str(key_type)
key_str = key_str.replace('<type ', '').replace('>', '')
caption_curr = 'NN Hash. Num Hash Tables: ' + str(
num_hash_tables_all[idx]) + ' ' + 'Hamming Distance: ' + str(
hammings[idx])
im_files_html.append([
out_file_indices.replace(rel_path[0], rel_path[1]),
out_file_curr.replace(rel_path[0], rel_path[1])
])
captions_html.append(['NN cosine', caption_curr])
visualize.writeHTML(out_file_html, im_files_html, captions_html,
sizes[0] / 2, sizes[1] / 2)
def visualizeBestTubeRank(params):
class_labels_map = params.class_labels_map
rel_path = params.rel_path
out_file_html = params.out_file_html
out_dir = params.out_dir
score_info_file = params.score_info_file
[class_labels, class_idx_map] = zip(*class_labels_map)
class_labels = list(class_labels)
class_idx_map = list(class_idx_map)
[score_files, score_files_info] = pickle.load(open(score_info_file, 'rb'))
class_idx = np.unique(score_files_info[:, 0])
tubes = np.unique(score_files_info[:, 3])
best_tubes_overall = score_files_info[:, 3]
out_file = os.path.join(out_dir, 'overall.png')
visualize.hist(best_tubes_overall,
out_file,
bins=tubes,
normed=True,
xlabel='Tube_idx',
ylabel='Frequency',
title='Best Tube Over All',
cumulative=False)
img_paths = []
captions = []
for class_idx_curr in class_idx:
label = class_labels[class_idx_map.index(class_idx_curr)]
out_file = os.path.join(out_dir, label + '.png')
img_paths.append([out_file.replace(rel_path[0], rel_path[1])])
captions.append([label])
rel_tubes = score_files_info[score_files_info[:, 0] == class_idx_curr,
3]
print class_idx_curr, rel_tubes.shape, min(rel_tubes), max(rel_tubes)
visualize.hist(rel_tubes,
out_file,
bins=tubes,
normed=True,
xlabel='Tube Idx',
ylabel='Frequency',
title='Best Tube ' + label,
cumulative=False)
# visualize.save
visualize.writeHTML(out_file_html, img_paths, captions, 400, 400)
def script_createHistDifferenceHTML():
out_dir_meta = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d'
train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs = [
dir[:-7] for dir in os.listdir(
'/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations')
if dir.endswith('_pascal')
]
layers = ['pool5', 'fc6', 'fc7']
degrees = [0, 45, 90, 135, 180]
delta = 5
caption_text = ['Trained', 'Not Trained']
replace = [out_dir_meta + '/', '']
degree = 90
for layer in layers:
out_file_html = os.path.join(out_dir_meta,
layer + '_all_azimuths' + '.html')
img_paths = []
caption_paths = []
for dir in dirs:
img_paths_row = []
caption_paths_row = []
for idx, file_pre in enumerate([train_pre, non_train_pre]):
curr_dir = os.path.join(file_pre + '_' + layer +
'_all_azimuths')
im_file = os.path.join(
curr_dir, dir + '_' + str(degree) + '_' + str(delta) +
'_compress.png')
img_paths_row.append(im_file.replace(replace[0], replace[1]))
caption_paths_row.append(caption_text[idx] + ' ' + layer +
' ' + dir)
img_paths.append(img_paths_row)
caption_paths.append(caption_paths_row)
visualize.writeHTML(out_file_html,
img_paths,
caption_paths,
height=400,
width=400)
print out_file_html
def script_writeHTMLStitchedFlos_wDirs(img_paths,out_file_html,viz_dirs):
img_paths_html=[];
captions=[];
for img_path in img_paths:
img_name=img_path[img_path.rindex('/')+1:img_path.rindex('.')];
img_paths_html_curr=[util.getRelPath(img_path)];
captions_curr=['im']
for viz_dir in viz_dirs:
print viz_dir,img_path
# img_path_curr=[os.path.join(viz_dir,file_curr) for file_curr in os.listdir(viz_dir) if file_curr.startswith(img_name)][0];
img_path_curr=os.path.join(viz_dir,img_name+'.png');
img_paths_html_curr.append(util.getRelPath(img_path_curr));
captions_curr.append(viz_dir[viz_dir.rindex('/')+1:]);
img_paths_html.append(img_paths_html_curr);
captions.append(captions_curr)
visualize.writeHTML(out_file_html,img_paths_html,captions);
def script_toyNNExperiment(params):
path_to_db = params.path_to_db;
class_id_pascal = params.class_id_pascal;
video_id = params.video_id;
shot_id = params.shot_id;
tube_id = params.tube_id;
numberofVideos = params.numberofVideos;
numberOfFrames = params.numberOfFrames;
out_file_html = params.out_file_html;
rel_path = params.rel_path;
out_file_hist = params.out_file_hist;
gpuFlag = params.gpuFlag;
dtype = params.dtype;
pascal_ids = params.pascal_ids;
video_info = params.video_info;
out_file_pickle = params.out_file_pickle
info_for_extraction=getInfoForFeatureExtractionForVideo(path_to_db,video_info,numberOfFrames);
video_info={class_id_pascal:[video_id]}
info_for_extraction_query=getInfoForExtractionForTube(path_to_db,class_id_pascal,video_id,shot_id,tube_id)
features_train,labels_train,img_paths_train=setUpFeaturesMat(info_for_extraction,dtype=dtype);
features_test,labels_test,img_paths_test=setUpFeaturesMat(info_for_extraction_query,dtype=dtype);
# features_test,labels_test,img_paths_test=setUpFeaturesMat(info_for_extraction,dtype=dtype);
indices,distances=nearest_neighbor.getNearestNeighbors(features_test,features_train,gpuFlag=gpuFlag);
img_paths_html=[];
captions_html=[];
record_wrong=[]
for r in range(indices.shape[0]):
img_paths_row=[img_paths_test[r].replace(rel_path[0],rel_path[1])];
captions_row=[labels_test[r]];
for c in range(indices.shape[1]):
rank=indices[r,c];
img_paths_row.append(img_paths_train[rank].replace(rel_path[0],rel_path[1]))
captions_row.append(labels_train[rank]);
if labels_train[rank]!=labels_test[r]:
record_wrong.append(c);
img_paths_html.append(img_paths_row);
captions_html.append(captions_row);
visualize.writeHTML(out_file_html,img_paths_html,captions_html);
visualize.hist(record_wrong,out_file_hist,bins=20,normed=True,xlabel='Rank of Incorrect Class',ylabel='Frequency',title='')
pickle.dump([features_test,features_train,labels_test,labels_train,img_paths_test,img_paths_train,indices,distances],open(out_file_pickle,'wb'));
def script_compareAzimuth():
path_to_anno='/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations/chair_pascal';
im_dir='/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB';
out_file_html='/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB/chair_angle_check.html'
anno_files=[os.path.join(path_to_anno,file_name) for file_name in os.listdir(path_to_anno) if file_name.endswith('.mat')];
list_of_chairs=[];
for anno_file in anno_files:
just_file=anno_file[anno_file.rindex('/')+1:];
just_file=just_file[:-4];
curr_dict=scipy.io.loadmat(anno_file,squeeze_me=True, struct_as_record=False);
objects=curr_dict['record'].objects
if not hasattr(objects, '__iter__'):
objects=[objects]
for idx,obj in enumerate(objects):
if obj.__dict__['class']=='chair':
im_file=os.path.join(im_dir,just_file+'_chair_'+str(idx)+'.jpg');
list_of_chairs.append((im_file,obj.viewpoint.azimuth_coarse));
angles=list(zip(*list_of_chairs)[1]);
images=list(zip(*list_of_chairs)[0]);
angles=np.array(angles)
angles_uni=np.unique(angles);
col_im=[];
col_caption=[];
for angle_uni in angles_uni:
idx_uni=np.where(angles==angle_uni)[0];
row_im_curr=[];
row_caption_curr=[];
for idx_curr in range(min(5,len(idx_uni))):
idx_im=idx_uni[idx_curr]
image_just_name=images[idx_im]
image_just_name=image_just_name[image_just_name.rindex('/')+1:];
row_im_curr.append(image_just_name);
row_caption_curr.append(str(angle_uni));
col_im.append(row_im_curr);
col_caption.append(row_caption_curr);
print col_im[:5];
print col_caption[:5];
visualize.writeHTML(out_file_html,col_im,col_caption)
def script_writeHTMLStitchedFlos(out_file_html,out_file,out_dir,grid_sizes=[1,2,4,8],grid_dir_pre='grid_flo_viz_'):
img_paths=util.readLinesFromFile(out_file);
viz_dirs=[os.path.join(out_dir,grid_dir_pre+str(num)) for num in grid_sizes];
img_paths_html=[];
captions=[];
for img_path in img_paths:
img_name=img_path[img_path.rindex('/')+1:img_path.rindex('.')];
img_paths_html_curr=[util.getRelPath(img_path)];
captions_curr=['im']
for viz_dir in viz_dirs:
print viz_dir,img_path
img_path_curr=[os.path.join(viz_dir,file_curr) for file_curr in os.listdir(viz_dir) if file_curr.startswith(img_name)][0];
img_paths_html_curr.append(util.getRelPath(img_path_curr));
captions_curr.append(viz_dir[viz_dir.rindex('/')+1:]);
img_paths_html.append(img_paths_html_curr);
captions.append(captions_curr)
visualize.writeHTML(out_file_html,img_paths_html,captions);
def script_doEverything(path_to_npy,path_to_im,ext,lim,out_file,out_dir_scratch,window,step_size,thresh,scale_info,scale_all, scale_images,lim_cases,gpu,model_file,clusters_file,train_val_file=None,overwrite=False):
for scale in scale_all:
# script_saveImCrops(path_to_npy,path_to_im,ext,lim,out_file,out_dir_scratch,window,step_size,thresh,scale_info,scale,scale_images,lim_cases)
for scale_image in scale_images:
dir_scale=os.path.join(out_dir_scratch,scale+'_'+str(scale_image));
scale_info=pickle.load(open(out_file,'rb'));
img_dirs=[os.path.join(dir_scale,im_curr_info[0]) for im_curr_info in scale_info[scale][:lim_cases]]
for img_dir in img_dirs:
img_paths=util.getFilesInFolder(img_dir,ext='.png');
if len(img_paths)==0:
'CONTINUING'
continue;
img_paths=[img_path for img_path in img_paths if not img_path.endswith('onImg.png')];
out_dir_flo=img_dir+'_pred_flo';
out_dir_flo_viz=img_dir+'_pred_flo_viz';
util.mkdir(out_dir_flo);
util.mkdir(out_dir_flo_viz);
po.script_saveFlosAndViz(img_paths,out_dir_flo,out_dir_flo_viz,gpu,model_file,clusters_file,train_val_file=train_val_file,overwrite=overwrite)
img_names=util.getFileNames(img_paths,ext=False);
out_dir_flo=img_dir+'_pred_flo';
out_dir_flo_viz=img_dir+'_pred_flo_viz';
out_file_html=img_dir+'.html';
img_paths_html=[];
captions_all=[];
for img_name in img_names:
row_curr=[];
row_curr.append(util.getRelPath(os.path.join(img_dir,img_name+'_onImg.png')));
row_curr.append(util.getRelPath(os.path.join(img_dir,img_name+'.png')));
row_curr.append(util.getRelPath(os.path.join(out_dir_flo_viz,img_name+'.png')));
captions=['','','']
img_paths_html.append(row_curr);
captions_all.append(captions);
visualize.writeHTML(out_file_html,img_paths_html,captions_all);
def makeClusterHTML(out_file_html, labels, num_cols, size_im, dir_server):
ims = []
captions = []
start_idx = 0
while start_idx < len(labels):
row_curr = []
caption_curr = []
if start_idx + num_cols > len(labels):
num_cols_real = len(labels) - start_idx
else:
num_cols_real = num_cols
for col_no in range(num_cols_real):
idx_curr = start_idx + col_no
label_curr = labels[idx_curr]
row_curr.append(util.getRelPath(label_curr, dir_server))
caption_curr.append('')
ims.append(row_curr)
captions.append(caption_curr)
start_idx = start_idx + num_cols_real
visualize.writeHTML(out_file_html, ims, captions, size_im, size_im)
print out_file_html.replace(dir_server,
'http://vision1.idav.ucdavis.edu:1000')
def script_createComparativeHtmls():
layers=['pool5','fc6','fc7'];
path_to_anno='/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations';
file_dir='/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB';
dirs=[dir[:-7] for dir in os.listdir(path_to_anno) if dir.endswith('pascal')];
file_name='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
file_name_alt='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
replace_paths=['/disk2','../../../..']
out_file_pre='nn_performance_comparison_trained_notrained'
out_file_pre=os.path.join('/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d',out_file_pre);
for layer in layers:
file_name_l=file_name+'_'+layer;
[img_paths,gt_labels,indices,_]=pickle.load(open(file_name_l+'.p','rb'));
idx_sort_binned=script_nearestNeigbourExperiment.sortByPerformance(indices,gt_labels,1,perClass=True);
img_paths=[x.replace(replace_paths[0],replace_paths[1]) for x in img_paths];
im_paths,captions=visualize.createImageAndCaptionGrid(img_paths,gt_labels,indices,dirs)
file_name_l=file_name_alt+'_'+layer;
[img_paths_alt,gt_labels_alt,indices,_]=pickle.load(open(file_name_l+'.p','rb'));
img_paths_alt=[x.replace(replace_paths[0],replace_paths[1]) for x in img_paths_alt];
im_paths_alt,captions_alt=visualize.createImageAndCaptionGrid(img_paths,gt_labels,indices,dirs)
im_paths_alt=[im_paths_alt[img_paths_alt.index(curr_img_path)] for curr_img_path in img_paths];
captions_alt=[captions_alt[img_paths_alt.index(curr_img_path)] for curr_img_path in img_paths];
im_paths_big=[];
captions_big=[];
for idx_curr in idx_sort_binned:
im_paths_big.append(im_paths[idx_curr]);
im_paths_big.append(im_paths_alt[idx_curr]);
captions_big.append(captions[idx_curr]);
captions_big.append(captions_alt[idx_curr]);
visualize.writeHTML(out_file_pre+'_'+layer+'.html',im_paths_big,captions_big)
def script_visualizeSegResults(pred_file,gt_output_file,gt_data_output_file,out_file_html,rel_path,means,out_dir): data=np.load(gt_data_output_file); gt= np.load(gt_output_file); out = np.load(pred_file); print data.shape; im_paths=[];captions=[]; for im_no in range(data.shape[0]): print im_no; data_path=os.path.join(out_dir,str(im_no)+'_data.png'); gt_path=os.path.join(out_dir,str(im_no)+'_gt.png'); pred_path=os.path.join(out_dir,str(im_no)+'_pred.png'); # scipy.misc.imsave(data_path,reshapeMat(data[im_no],means)); visualize.saveMatAsImage(reshapeMat(data[im_no],means)/255,data_path); visualize.saveMatAsImage(reshapeMat(gt[im_no],means),gt_path); visualize.saveMatAsImage(reshapeMat(out[im_no],means),pred_path); im_paths.append([data_path.replace(rel_path[0],rel_path[1]),gt_path.replace(rel_path[0],rel_path[1]),pred_path.replace(rel_path[0],rel_path[1])]); captions.append(['im','mask_gt','mask_pred']); # if im_no==10: # break; visualize.writeHTML(out_file_html,im_paths,captions,height=224,width=224);
def compareMagInfoLayerTime(dirs,out_dirs,model_num,num_iters,file_pre_grad,file_pre_weight,out_file_html):
img_paths=[];
captions=[];
for dir_curr,out_dir_curr in zip(dirs,out_dirs):
dict_for_plotting={'grads_mag':OrderedDict(),'weights_mag':OrderedDict(),'ratios':OrderedDict()};
dict_for_plotting=OrderedDict(dict_for_plotting.items());
for model_num_curr in model_num:
print model_num_curr;
file_pairs=[(os.path.join(dir_curr,model_num_curr,file_pre_grad+str(iter_curr)+'.npy'),
os.path.join(dir_curr,model_num_curr,file_pre_weight+str(iter_curr)+'.npy')) for iter_curr in num_iters];
means,_=getMagInfo(file_pairs,alt=True);
dict_for_plotting['grads_mag'][model_num_curr]=means[0];
dict_for_plotting['weights_mag'][model_num_curr]=means[1];
dict_for_plotting['ratios'][model_num_curr]=means[2];
img_paths_curr=[];
captions_curr=[];
for key_curr in dict_for_plotting.keys():
out_file_curr=os.path.join(out_dir_curr,key_curr+'.png');
data=dict_for_plotting[key_curr];
xAndYs=data.values();
legend_entries=data.keys();
xAndYs=[(range(len(x_curr)),x_curr) for x_curr in xAndYs];
visualize.plotSimple(xAndYs,out_file_curr,title=key_curr,xlabel='layer',ylabel='magnitude',legend_entries=legend_entries,outside=True);
print out_file_curr.replace('/disk3','vision3.cs.ucdavis.edu:1001');
img_paths_curr.append(util.getRelPath(out_file_curr,'/disk3'));
# print dir_curr.split('/');
captions_curr.append(dir_curr.split('/')[-2]+' '+dir_curr.split('/')[-1]+' '+key_curr);
img_paths.append(img_paths_curr);
captions.append(captions_curr);
visualize.writeHTML(out_file_html,img_paths,captions,height=500,width=500);
print out_file_html.replace('/disk3','vision3.cs.ucdavis.edu:1001');
def script_visualizeTifAsIm(tif_dir,im_dir,inc,out_tif,out_file_html,rel_path):
tif_files=[file_curr for file_curr in os.listdir(tif_dir) if file_curr.endswith('.tif')];
num_files=[int(file_curr[file_curr.rindex('_')+1:file_curr.rindex('.')]) for file_curr in tif_files];
tif_files_sorted=[];
num_files_sorted=num_files[:];
num_files_sorted.sort();
for idx in range(len(num_files)):
num_curr=num_files_sorted[idx];
file_curr=tif_files[num_files.index(num_curr)];
tif_files_sorted.append(file_curr);
rows_all=[];
captions_all=[];
for tif_file in tif_files_sorted:
row_curr=[];
tif_file_full=os.path.join(tif_dir,tif_file);
file_name_only=tif_file[:tif_file.rindex('.')];
file_pre=file_name_only[:file_name_only.rindex('_')+1];
num_file=int(file_name_only[file_name_only.rindex('_')+1:]);
num_match=num_file+inc;
im_1=os.path.join(im_dir,file_name_only+'.jpg');
im_2=os.path.join(im_dir,file_pre+str(num_match)+'.jpg');
row_curr.append(im_1);
row_curr.append(im_2);
tif=scipy.misc.imread(tif_file_full);
out_x=os.path.join(out_tif,file_name_only+'_x.png');
out_y=os.path.join(out_tif,file_name_only+'_y.png');
visualize.visualizeFlo(tif,out_x,out_y);
row_curr.append(out_x);
row_curr.append(out_y);
row_curr=[path.replace(rel_path[0],rel_path[1]) for path in row_curr];
rows_all.append(row_curr);
captions_all.append([str(num_file),str(num_match),'x','y']);
visualize.writeHTML(out_file_html,rows_all,captions_all);
def script_visualizeLossesFromExperiment():
# out_dir='/disk3/maheen_data/ft_youtube_40_noFix_alexnet';
out_dir='/disk3/maheen_data/debug_networks/noFixCopyByLayerAlexNet';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/models/bvlc_alexnet/bvlc_alexnet.caffemodel';
layers=['conv1','conv2','conv3','conv4','conv5','fc6'];
# ,'fc7'];
layers_str=[];
for idx in range(len(layers)):
# if idx==0:
# fix_layers=layers[0];
# layer_str=str(fix_layers);
# else:
fix_layers=layers[:idx+1];
layer_str='_'.join(fix_layers);
layers_str.append(layer_str);
log_files=[os.path.join(out_dir,'log_'+layer_str+'.log') for layer_str in layers_str];
str_match=' solver.cpp:209] Iteration ';
xAndYs=[svl.getIterationsAndLosses(log_file,str_match) for log_file in log_files];
out_files=[];
for layer_str,log_file in zip(layers_str,log_files):
xAndY=svl.getIterationsAndLosses(log_file,str_match);
print xAndY
out_file=os.path.join(out_dir,'loss_'+layer_str+'.png');
visualize.plotSimple([xAndY],out_file,title=layer_str);
out_files.append(out_file);
out_file_html=os.path.join(out_dir,'losses_all.html');
img_paths=[[util.getRelPath(out_file,'/disk3')] for out_file in out_files];
captions=[['']]*len(out_files);
print img_paths
print captions
visualize.writeHTML(out_file_html,img_paths,captions,height=300,width=300);
def script_visualizeFlos(params):
out_file_html = params.out_file_html
out_dir_flo_im = params.out_dir_flo_im
flo_dir = params.flo_dir
im_file_1 = params.im_file_1
im_file_2 = params.im_file_2
height = params.height
width = params.width
rel_path = params.rel_path
list_1=util.readLinesFromFile(im_file_1);
list_2=util.readLinesFromFile(im_file_2);
flo_files=[os.path.join(flo_dir,file_curr) for file_curr in os.listdir(flo_dir) if file_curr.endswith('.flo')];
flo_nums=[int(file_curr[file_curr.rindex('(')+1:file_curr.rindex(')')]) for file_curr in flo_files];
print len(list_1),len(list_2),len(flo_files);
flo_files_sorted=[];
for idx_flo in range(len(flo_nums)):
idx_curr=flo_nums.index(idx_flo);
flo_files_sorted.append(flo_files[idx_curr]);
im_list=[];
caption_list=[];
# for idx_flo,flo_file_curr in enumerate(flo_files_sorted):
for idx_flo in range(len(list_1)):
flo_file_curr=flo_files_sorted[idx_flo];
out_flo_x=os.path.join(out_dir_flo_im,str(idx_flo)+'_x.png');
out_flo_y=os.path.join(out_dir_flo_im,str(idx_flo)+'_y.png');
flo=util.readFlowFile(flo_file_curr);
visualize.visualizeFlo(flo,out_flo_x,out_flo_y);
im_file_rel_1=list_1[idx_flo].replace(rel_path[0],rel_path[1]);
im_file_rel_2=list_2[idx_flo].replace(rel_path[0],rel_path[1]);
flo_file_rel_1=out_flo_x.replace(rel_path[0],rel_path[1]);
flo_file_rel_2=out_flo_y.replace(rel_path[0],rel_path[1]);
im_list.append([im_file_rel_1,im_file_rel_2,flo_file_rel_1,flo_file_rel_2]);
caption_list.append(['Image 1','Image 2','Flow x','Flow y']);
visualize.writeHTML(out_file_html,im_list,caption_list,height=height,width=width)
def script_visualizeNNComparisonWithHash(params):
in_file = params.in_file
in_file_hash = params.in_file_hash
out_file_html = params.out_file_html
rel_path = params.rel_path
topn = params.topn
img_size = params.img_size
[_,_,labels_test,labels_train,img_paths_test,img_paths_train,indices,_]=pickle.load(open(in_file,'rb'));
[indices_hash,_,_]=pickle.load(open(in_file_hash,'rb'));
img_paths_nn,captions_nn=getImgPathsAndCaptionsNN(indices,img_paths_test,img_paths_train,labels_test,labels_train,rel_path)
img_paths_hash,captions_hash=getImgPathsAndCaptionsNN(indices_hash,img_paths_test,img_paths_train,labels_test,labels_train,rel_path)
img_paths_all=[];
captions_all=[];
for idx in range(len(img_paths_nn)):
img_paths_all.append(img_paths_nn[idx][:topn]);
img_paths_all.append(img_paths_hash[idx][:topn]);
captions_all.append([x+' nn' for x in captions_nn[idx][:topn]]);
captions_all.append([x+' hash' for x in captions_hash[idx][:topn]]);
visualize.writeHTML(out_file_html,img_paths_all,captions_all,img_size[0],img_size[1]);
def main():
# data='/home/SSD3/maheen-data/horse_project/data_resize/horse/matches_5_train_allKP.txt'
# # /home/SSD3/maheen-data/horse_project/data_resize/horse/matches_5_train_allKP.txt
# to_search=\
# ['/home/SSD3/maheen-data/horse_project/data_check/horse/im/horses_pascal_selected/2009_004662.jpg /home/SSD3/maheen-data/horse_project/data_check/horse/npy/horses_pascal_selected/2009_004662.npy',
# '/home/SSD3/maheen-data/horse_project/data_check/horse/im/imagenet_n02374451/n02374451_11539.jpg /home/SSD3/maheen-data/horse_project/data_check/horse/npy/imagenet_n02374451/n02374451_11539.npy',
# '/home/SSD3/maheen-data/horse_project/data_check/horse/im/imagenet_n02374451/n02374451_16786.jpg /home/SSD3/maheen-data/horse_project/data_check/horse/npy/imagenet_n02374451/n02374451_16786.npy',
# '/home/SSD3/maheen-data/horse_project/data_check/horse/im/imagenet_n02374451/n02374451_4338.jpg /home/SSD3/maheen-data/horse_project/data_check/horse/npy/imagenet_n02374451/n02374451_4338.npy']
# data=util.readLinesFromFile(data);
# print data[0];
# to_search=[file_curr.replace('data_check','data_resize') for file_curr in to_search];
# idx_lines=[data.index(line_curr) for line_curr in to_search if line_curr in data];
# print idx_lines;
# for idx_line_curr in idx_lines:
# print 'batch_no',(idx_line_curr)/64
# # npy_files=[file_curr[file_curr.index(' ')+1:] for file_curr in data];
# # print npy_files[0];
# # print len(npy_files);
# # p=multiprocessing.Pool(multiprocessing.cpu_count());
# # problem_files=p.map(findProblemNPYMP,npy_files);
# # problem_files=[file_curr for file_curr in problem_files if file_curr is not None];
# # print (len(problem_files));
# return
# data='/home/laoreja/new-deep-landmark/train/vanilla/aflw_224/aflw_vanilla_val_224.txt';
# data='/home/laoreja/new-deep-landmark/train/vanilla/aflw_224/aflw_vanilla_train_224_weight.txt';
# data=util.readLinesFromFile(data);
# print data;
# total=0;
# for h5_file_curr in data:
# with h5py.File(h5_file_curr,'r') as hf:
# print('List of arrays in this file: ', hf.keys())
# data = hf.get('confidence')
# np_data = np.array(data)
# total=total+np_data.shape[0];
# print('Shape of the array dataset_1: ', np_data.shape)
# print total;
# return
# horse_path='/home/SSD3/maheen-data/horse_project/data_resize/horse/matches_5_train_allKP.txt'
# human_path_noIm='/home/SSD3/maheen-data/horse_project/data_resize/aflw/matches_5_train_allKP_noIm.txt'
# human_path='/home/SSD3/maheen-data/horse_project/data_resize/aflw/matches_5_train_allKP.txt'
# paths=[horse_path,human_path_noIm,human_path];
# out_files=[file_curr[:file_curr.rindex('.')]+'_dummy.txt' for file_curr in paths];
# for file_curr,out_file_curr in zip(paths,out_files):
# data_curr=util.readLinesFromFile(file_curr);
# data_curr=data_curr[0:50:5];
# # print data_curr;
# print len(data_curr);
# util.writeFile(out_file_curr,data_curr);
# print out_file_curr;
# return
# im_path= "/home/SSD3/maheen-data/horse_project/data_resize/horse/im/_04_Aug16_png/horse+head12.jpg"
# # 2 : "/home/SSD3/maheen-data/horse_project/data_resize/horse/npy/_04_Aug16_png/horse+head12.npy"
# # "/home/SSD3/maheen-data/horse_project/data_resize/aflw/im/0/image67102_20650.jpg"
# np_path="/home/SSD3/maheen-data/horse_project/data_resize/horse/npy/_04_Aug16_png/horse+head12.npy"
# # "/home/SSD3/maheen-data/horse_project/data_resize/aflw/npy/0/image67102_20650.npy"
# # im=scipy.misc.read(im_path);
# im=cv2.imread(im_path);
# labels=np.load(np_path);
# print labels
# for i in xrange(labels.shape[0]):
# cv2.circle(im, (labels[i][0], labels[i][1]), 2, (0,0,255), -1)
# cv2.imwrite('/home/SSD3/maheen-data/temp/check.png', im)
# return
# path_to_th='/home/maheenrashid/Downloads/horses/torch/test_tps_cl.th';
# iterations=10;
# out_dir_models='/home/SSD3/maheen-data/horse_human_fiveKP_tps_adam'
# model_pre=os.path.join(out_dir_models,'intermediate','model_all_');
# model_post='.dat';
# range_models=range(450,4500+1,450);
# out_dir_meta=os.path.join(out_dir_models,'test_overtime');
# batch_size=60;
# # commands=generateTPSTestCommands(path_to_th,batch_size,iterations,model_pre,model_post,range_models,out_dir_meta)
# # print len(commands);
# # print commands[0];
# # out_file_commands=os.path.join(out_dir_meta+'.sh');
# # util.writeFile(out_file_commands,commands);
# dir_server='/home/SSD3/maheen-data';
# range_batches=range(1,10);
# # batch_size=60;
# range_images=range(1,61,5);
# img_dir_meta='/home/SSD3/maheen-data/horse_human_fiveKP_tps_adam/test_overtime'
# img_dir=[os.path.join(img_dir_meta,'model_all_'+str(range_model_curr)) for range_model_curr in range_models]
# out_file_html='/home/SSD3/maheen-data/horse_human_fiveKP_tps_adam/test_viz.html'
# file_post=['_horse.jpg','_human.jpg','_gtwarp.jpg','_predwarp.jpg']
# loss_post='_loss.npy';
# out_file_html=img_dir_meta+'.html';
# img_caption_pre=[str(model_num) for model_num in range_models];
# comparativeLossViz(img_dir,file_post,loss_post,range_batches,range_images,out_file_html,dir_server,img_caption_pre)
# return
dir_server = '/home/SSD3/maheen-data'
range_batches = range(1, 9)
# batch_size=60;
range_images = range(1, 129, 5)
img_dir = ['/home/SSD3/maheen-data/horse_human_fiveKP_tps_adam/test_viz/']
# out_file_html='/home/SSD3/maheen-data/horse_human_fiveKP_tps_adam/test_viz.html'
img_dir = [
'/home/SSD3/maheen-data/horse_project/tps_train_allKP_adam/test_viz'
]
out_file_html = '/home/SSD3/maheen-data/horse_project/tps_train_allKP_adam/test_viz.html'
file_post = ['_horse.jpg', '_human.jpg', '_gtwarp.jpg', '_predwarp.jpg']
loss_post = '_loss.npy'
comparativeLossViz(img_dir, file_post, loss_post, range_batches,
range_images, out_file_html, dir_server)
return
img_files = []
caption_files = []
out_dir = '/home/SSD3/maheen-data/training_kp_withWarp_test_debug_tps_adam'
out_dir = '/home/SSD3/maheen-data/testing_5_kp_withWarp_fixed_adam_debug'
out_dir = '/home/SSD3/maheen-data/training_5_kp_withWarp_fixed_adam__1e-05/test'
dir_server = '/home/SSD3/maheen-data'
out_file_html = os.path.join(out_dir, 'viz.html')
for i in range(1, 94):
im_file = os.path.join(out_dir,
str(i) + '_org.jpg')
warp_file = os.path.join(out_dir,
str(i) + '_warp.jpg')
im_file_small = os.path.join(out_dir,
str(i) + '_small_org.jpg')
warp_file_small = os.path.join(out_dir,
str(i) + '_small_warp.jpg')
im_file = util.getRelPath(im_file, dir_server)
warp_file = util.getRelPath(warp_file, dir_server)
im_file_small = util.getRelPath(im_file_small, dir_server)
warp_file_small = util.getRelPath(warp_file_small, dir_server)
img_files.append([im_file, warp_file])
# ,im_file_small,warp_file_small]);
caption_files.append([str(i) + ' org',
str(i) + ' warp'])
# ,'small_org','small_warp']);
visualize.writeHTML(out_file_html, img_files, caption_files, 224, 224)
return
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
num_neighbors = 5
out_file_human = os.path.join(
out_dir_meta_face, 'matches_' + str(num_neighbors) + '_val_fiveKP.txt')
out_file_human_new = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_val_fiveKP_noIm.txt')
modifyHumanFile(out_file_human, out_file_human_new)
# out_dir_meta_face='/home/SSD3/maheen-data/horse_project/aflw';
out_file_human = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_train_fiveKP.txt')
out_file_human_new = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_train_fiveKP_noIm.txt')
modifyHumanFile(out_file_human, out_file_human_new)
return
# matches_file='/home/maheenrashid/Downloads/knn_5_points_train_list_clean.txt'
# face_data_file='/home/laoreja/new-deep-landmark/dataset/train/aflw_trainImageList.txt';
# # face_data_file_old='/home/laoreja/deep-landmark-master/dataset/train/trainImageList.txt';
# face_data_list_file='/home/SSD3/maheen-data/aflw_data/npy/data_list.txt';
# out_dir_meta_horse='/home/SSD3/maheen-data/horse_project/horse';
# out_dir_meta_horse_list=[os.path.join(out_dir_meta_horse,'im'),os.path.join(out_dir_meta_horse,'npy')];
# out_dir_meta_face='/home/SSD3/maheen-data/horse_project/aflw';
# out_dir_meta_face_list=[os.path.join(out_dir_meta_face,'im'),os.path.join(out_dir_meta_face,'npy')];
# out_dir_meta_face_old='/home/SSD3/maheen-data/horse_project/face';
# out_dir_meta_face_old_list=[os.path.join(out_dir_meta_face_old,'im'),os.path.join(out_dir_meta_face_old,'npy')];
# num_neighbors=5;
# out_file_face=os.path.join(out_dir_meta_face,'matches_'+str(num_neighbors)+'_train_fiveKP.txt');
# out_file_horse=os.path.join(out_dir_meta_horse,'matches_'+str(num_neighbors)+'_train_fiveKP.txt');
# missing_files=makeMatchFile(num_neighbors,matches_file,face_data_file,out_dir_meta_horse_list,out_dir_meta_face_list,out_file_horse,out_file_face,out_dir_meta_face_old_list)
# return
# out_dir_meta_face='/home/SSD3/maheen-data/horse_project/aflw';
# num_neighbors=5;
# out_file_human=os.path.join(out_dir_meta_face,'matches_'+str(num_neighbors)+'_val_fiveKP.txt');
# out_file_human_new=os.path.join(out_dir_meta_face,'matches_'+str(num_neighbors)+'_val_fiveKP_noIm.txt');
# # modifyHumanFile(out_file_human,out_file_human_new)
# # out_dir_meta_face='/home/SSD3/maheen-data/horse_project/aflw';
# out_file_human=os.path.join(out_dir_meta_face,'matches_'+str(num_neighbors)+'_train_fiveKP.txt');
# out_file_human_new=os.path.join(out_dir_meta_face,'matches_'+str(num_neighbors)+'_train_fiveKP_noIm.txt');
# # modifyHumanFile(out_file_human,out_file_human_new)
# print out_file_human_new;
# return
# img_files=[];
# caption_files=[];
# out_dir='/home/SSD3/maheen-data/training_kp_withWarp_test_final'
# dir_server='/home/SSD3/maheen-data';
# out_file_html=os.path.join(out_dir,'viz.html');
# for i in range(1,94):
# im_file=os.path.join(out_dir,str(i)+'.jpg');
# warp_file=os.path.join(out_dir,str(i)+'_warp.jpg');
# im_file=util.getRelPath(im_file,dir_server);
# warp_file=util.getRelPath(warp_file,dir_server);
# img_files.append([im_file,warp_file]);
# caption_files.append(['org','warp']);
# visualize.writeHTML(out_file_html,img_files,caption_files,224,224);
# return
file_horse = '/home/SSD3/maheen-data/horse_project/horse/matches_5_train_fiveKP.txt'
out_file_horse = '/home/SSD3/maheen-data/horse_project/horse_resize/matches_5_train_fiveKP.txt'
lines = util.readLinesFromFile(file_horse)
print len(lines)
lines = list(set(lines))
print len(lines)
lines = [line_curr.split(' ') for line_curr in lines]
im_files = [line_curr[0] for line_curr in lines]
npy_files = [line_curr[1] for line_curr in lines]
out_dir_meta_old = '/home/SSD3/maheen-data/horse_project/horse/'
out_dir_meta_new = '/home/SSD3/maheen-data/horse_project/horse_resize/'
replace_paths = [out_dir_meta_old, out_dir_meta_new]
args = []
for idx in range(len(im_files)):
im_file = im_files[idx]
npy_file = npy_files[idx]
out_im_file = im_file.replace(replace_paths[0], replace_paths[1])
out_npy_file = npy_file.replace(replace_paths[0], replace_paths[1])
args.append((idx, im_file, npy_file, out_im_file, out_npy_file))
p = multiprocessing.Pool(multiprocessing.cpu_count())
p.map(resizeImAndNpy224, args)
out_dir_meta_old = '/home/SSD3/maheen-data/horse_project/horse/'
out_dir_meta_new = '/home/SSD3/maheen-data/horse_project/horse_resize/'
replace_paths = [out_dir_meta_old, out_dir_meta_new]
lines = util.readLinesFromFile(file_horse)
lines_new = [
line.replace(replace_paths[0], replace_paths[1]) for line in lines
]
util.writeFile(out_file_horse, lines_new)
lines = util.readLinesFromFile(out_file_horse)
print(len(lines))
im_file = lines[90].split(' ')[0]
im = cv2.imread(im_file, 1)
labels = np.load(lines[90].split(' ')[1])
for i in xrange(labels.shape[0]):
cv2.circle(im, (labels[i][0], labels[i][1]), 2, (0, 0, 255), -1)
cv2.imwrite('/home/SSD3/maheen-data/temp/check.png', im)
return
dir_out = '/home/SSD3/maheen-data/temp/horse_human/viz_transform_aflw_val'
visualize.writeHTMLForFolder(dir_out)
return
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
num_neighbors = 5
out_file_human = os.path.join(
out_dir_meta_face, 'matches_' + str(num_neighbors) + '_val_fiveKP.txt')
out_file_human_new = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_val_fiveKP_noIm.txt')
modifyHumanFile(out_file_human, out_file_human_new)
# out_dir_meta_face='/home/SSD3/maheen-data/horse_project/aflw';
out_file_human = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_train_fiveKP.txt')
out_file_human_new = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_train_fiveKP_noIm.txt')
modifyHumanFile(out_file_human, out_file_human_new)
return
matches_file = '/home/laoreja/data/knn_res_new/knn_5_points_val_list.txt'
face_data_file = '/home/laoreja/new-deep-landmark/dataset/train/aflw_trainImageList.txt'
# face_data_file_old='/home/laoreja/deep-landmark-master/dataset/train/trainImageList.txt';
face_data_list_file = '/home/SSD3/maheen-data/aflw_data/npy/data_list.txt'
out_dir_meta_horse = '/home/SSD3/maheen-data/horse_project/horse'
out_dir_meta_horse_list = [
os.path.join(out_dir_meta_horse, 'im'),
os.path.join(out_dir_meta_horse, 'npy')
]
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
out_dir_meta_face_list = [
os.path.join(out_dir_meta_face, 'im'),
os.path.join(out_dir_meta_face, 'npy')
]
out_dir_meta_face_old = '/home/SSD3/maheen-data/horse_project/face'
out_dir_meta_face_old_list = [
os.path.join(out_dir_meta_face_old, 'im'),
os.path.join(out_dir_meta_face_old, 'npy')
]
num_neighbors = 5
out_file_face = os.path.join(
out_dir_meta_face, 'matches_' + str(num_neighbors) + '_val_fiveKP.txt')
out_file_horse = os.path.join(
out_dir_meta_horse,
'matches_' + str(num_neighbors) + '_val_fiveKP.txt')
missing_files = makeMatchFile(num_neighbors, matches_file, face_data_file,
out_dir_meta_horse_list,
out_dir_meta_face_list, out_file_horse,
out_file_face, out_dir_meta_face_old_list)
return
matches_file = '/home/laoreja/data/knn_res_new/knn_5_points_train_list.txt'
matches_file = '/home/maheenrashid/Downloads/knn_5_points_train_list_clean.txt'
face_data_file = '/home/laoreja/new-deep-landmark/dataset/train/aflw_trainImageList.txt'
# face_data_file_old='/home/laoreja/deep-landmark-master/dataset/train/trainImageList.txt';
face_data_list_file = '/home/SSD3/maheen-data/aflw_data/npy/data_list.txt'
out_dir_meta_horse = '/home/SSD3/maheen-data/horse_project/horse'
out_dir_meta_horse_list = [
os.path.join(out_dir_meta_horse, 'im'),
os.path.join(out_dir_meta_horse, 'npy')
]
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
out_dir_meta_face_list = [
os.path.join(out_dir_meta_face, 'im'),
os.path.join(out_dir_meta_face, 'npy')
]
out_dir_meta_face_old = '/home/SSD3/maheen-data/horse_project/face'
out_dir_meta_face_old_list = [
os.path.join(out_dir_meta_face_old, 'im'),
os.path.join(out_dir_meta_face_old, 'npy')
]
num_neighbors = 5
out_file_face = os.path.join(
out_dir_meta_face,
'matches_' + str(num_neighbors) + '_train_fiveKP.txt')
out_file_horse = os.path.join(
out_dir_meta_horse,
'matches_' + str(num_neighbors) + '_train_fiveKP.txt')
missing_files = makeMatchFile(num_neighbors, matches_file, face_data_file,
out_dir_meta_horse_list,
out_dir_meta_face_list, out_file_horse,
out_file_face, out_dir_meta_face_old_list)
return
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
num_neighbors = 5
out_file_face = os.path.join(out_dir_meta_face,
'matches_' + str(num_neighbors) + '.txt')
out_file_face_new = os.path.join(
out_dir_meta_face, 'matches_noIm_' + str(num_neighbors) + '.txt')
# modifyHumanFile(out_file_face,out_file_face_new);
# old_data=util.readLinesFromFile(out_file_face);
# old_data=[line_curr.split(' ')[1] for line_curr in old_data];
# new_data=util.readLinesFromFile(out_file_face_new);
# new_data=[line_curr.split(' ')[0] for line_curr in new_data];
# assert len(old_data)==len(new_data);
# for i,old_line in enumerate(old_data):
# print i;
# assert old_line==new_data[i];
return
matches_file = '/home/laoreja/data/knn_res_new/5_points_list.txt'
matches_file = '/home/laoreja/data/knn_res_new/knn_train_list.txt'
face_data_file = '/home/laoreja/new-deep-landmark/dataset/train/aflw_trainImageList.txt'
face_data_list_file = '/home/SSD3/maheen-data/aflw_data/npy/data_list.txt'
out_dir_meta_horse = '/home/SSD3/maheen-data/horse_project/horse'
out_dir_meta_horse_list = [
os.path.join(out_dir_meta_horse, 'im'),
os.path.join(out_dir_meta_horse, 'npy')
]
out_dir_meta_face = '/home/SSD3/maheen-data/horse_project/aflw'
out_dir_meta_face_list = [
os.path.join(out_dir_meta_face, 'im'),
os.path.join(out_dir_meta_face, 'npy')
]
num_neighbors = 5
out_file_face = os.path.join(out_dir_meta_face,
'matches_' + str(num_neighbors) + '.txt')
out_file_horse = os.path.join(out_dir_meta_horse,
'matches_' + str(num_neighbors) + '.txt')
makeMatchFile(num_neighbors, matches_file, face_data_file,
out_dir_meta_horse_list, out_dir_meta_face_list,
out_file_horse, out_file_face)
return
# script_saveTrainTxt()
# dir_viz='/home/SSD3/maheen-data/temp/horse_human/viz_transform_aflw';
# visualize.writeHTMLForFolder(dir_viz,'.jpg');
return
out_dir_meta = '/home/SSD3/maheen-data'
face_dir = 'aflw_data'
horse_dir = 'horse_data'
num_neighbors = 5
path_replace_horse = [
'/home/laoreja/data/horse-images/annotation',
os.path.join(out_dir_meta, horse_dir, 'im')
]
path_replace_face = ['/npy/', '/im/']
new_match_file = os.path.join(out_dir_meta, face_dir,
'match_' + str(num_neighbors) + '.txt')
out_face_train_file = os.path.join(
out_dir_meta, face_dir, 'match_' + str(num_neighbors) + '_train.txt')
out_horse_train_file = os.path.join(
out_dir_meta, horse_dir, 'match_' + str(num_neighbors) + '_train.txt')
horse_txt_file = os.path.join(out_dir_meta, horse_dir, 'train.txt')
face_txt_file = os.path.join(out_dir_meta, face_dir, 'train.txt')
horse_train = util.readLinesFromFile(horse_txt_file)
horse_train_just_beginning = [
horse_curr.split(' ')[0] for horse_curr in horse_train
]
horse_train_just_beginning = [
horse_curr[:horse_curr.rindex('.')]
for horse_curr in horse_train_just_beginning
]
print horse_train_just_beginning[0]
face_train = util.readLinesFromFile(face_txt_file)
face_train_just_beginning = [
face_curr.split(' ')[0] for face_curr in face_train
]
face_train_just_beginning = [
face_curr[:face_curr.rindex('.')]
for face_curr in face_train_just_beginning
]
print len(horse_train)
print horse_train[0]
print len(face_train)
print face_train[0]
# return
matches = util.readLinesFromFile(new_match_file)
print(len(matches))
matches = [match_curr.split(' ') for match_curr in matches]
horse_matches = []
face_matches = []
for match_curr in matches:
assert len(match_curr) == num_neighbors + 1
horse_curr = match_curr[0]
horse_curr_path, horse_name = os.path.split(horse_curr)
if horse_curr_path[-3:] == 'gxy':
horse_curr_path = horse_curr_path[:-3]
horse_curr_path = horse_curr_path.replace(path_replace_horse[0],
path_replace_horse[1])
horse_curr = os.path.join(horse_curr_path,
horse_name[:horse_name.rindex('.')])
if horse_curr in horse_train_just_beginning:
horse_match = horse_train[horse_train_just_beginning.index(
horse_curr)]
else:
# print horse_curr
# print match_curr[0];
# raw_input();
continue
for face_curr in match_curr[1:]:
face_curr = face_curr[:face_curr.rindex('.')]
face_curr = face_curr.replace(path_replace_face[0],
path_replace_face[1])
face_match = face_train[face_train_just_beginning.index(face_curr)]
horse_matches.append(horse_match)
face_matches.append(face_match)
# print match_curr;
# print match_curr[0];
# for idx,i in enumerate(match_curr[1:]):
# print idx,face_matches[idx],i,horse_matches[idx]
assert len(face_matches) == len(horse_matches)
print len(face_matches)
util.writeFile(out_face_train_file, face_matches)
util.writeFile(out_horse_train_file, horse_matches)
return
# face_dir='/home/SSD3/maheen-data/face_data';
# train_txt=os.path.join(face_dir,'train.txt');
# files=util.readLinesFromFile(train_txt);
# files=[file_curr.split(' ') for file_curr in files];
# [im_files,npy_files]=zip(*files);
# for idx,npy_file in enumerate(npy_files):
# print idx,len(npy_files);
# assert os.path.exists(npy_file);
# assert np.load(npy_file).shape[1]==3;
# print len(im_files);
# print (im_files[0]);
# print len(npy_files);
# print (npy_files[0]);
dir_viz = '/home/SSD3/maheen-data/temp/horse_human/viz_transform'
visualize.writeHTMLForFolder(dir_viz, '.jpg')
return
horse_data = '/home/SSD3/maheen-data/horse_data'
new_face_data = '/home/SSD3/maheen-data/face_data'
old_txt = 'train.txt'
num_to_keep = 10
new_txt = 'train_' + str(num_to_keep) + '.txt'
for data_type in [horse_data, new_face_data]:
lines_new = util.readLinesFromFile(os.path.join(data_type, old_txt))
random.shuffle(lines_new)
lines_new = lines_new[:num_to_keep]
file_new = os.path.join(data_type, new_txt)
util.writeFile(file_new, lines_new)
print len(lines_new), file_new
return
def main():
out_file_html = '/disk2/aprilExperiments/horses/frames_with_detections/visualize.html'
out_dir_meta = '/disk2/aprilExperiments/horses/frames_with_detections'
img_paths = []
captions = []
rel_path = ['/disk2', '../../../..']
for dir_curr in os.listdir(out_dir_meta):
dir_curr = os.path.join(out_dir_meta, dir_curr)
if os.path.isdir(dir_curr):
print dir_curr
jpegs = [
os.path.join(dir_curr, file_curr)
for file_curr in os.listdir(dir_curr)
if file_curr.endswith('.png')
]
jpegs = [
file_curr.replace(rel_path[0], rel_path[1])
for file_curr in jpegs
]
# print jpegs[:10];
jpegs.sort()
# print jpegs[:10];
captions_curr = [''] * len(jpegs)
print captions_curr
img_paths.append(jpegs)
captions.append(captions_curr)
# raw_input();
visualize.writeHTML(out_file_html,
img_paths,
captions,
height=100,
width=100)
return
dirs_meta = [
'/disk2/aprilExperiments/horses/mediaFromPPT_frames',
'/disk2/aprilExperiments/horses/ResearchSpring2016_frames'
]
out_file = '/disk2/aprilExperiments/horses/list_of_frames.txt'
im_list = []
for dir_curr in dirs_meta:
list_curr = [
os.path.join(dir_curr, im_curr) for im_curr in os.listdir(dir_curr)
if im_curr.endswith('.jpg')
]
im_list = im_list + list_curr
util.writeFile(out_file, im_list)
return
in_file = '/disk2/aprilExperiments/horses/list_of_frames.txt'
out_dir_meta = '/disk2/aprilExperiments/horses/frames_with_detections/'
util.mkdir(out_dir_meta)
with open(in_file, 'rb') as f:
im_names = f.readlines()
im_names = [line.strip('\n') for line in im_names]
for im_name in im_names:
vid_name = im_name[im_name.rindex('/') + 1:im_name.rindex('_')]
out_dir_curr = os.path.join(out_dir_meta, vid_name)
if not os.path.exists(out_dir_curr):
os.mkdir(out_dir_curr)
return
out_dir = '/disk2/temp/horses'
arr_file = os.path.join(out_dir, 'Outside4_00011_horse_detections.npy')
im_file = '/disk2/aprilExperiments/horses/ResearchSpring2016_frames/Outside4_00011.jpg'
arr = np.load(arr_file)
out_file = arr_file[:-4] + '.png'
saveDets(im_file, 'horse', arr, out_file, 0.8)
# plt.imshow(im);
# plt.savefig();
print 'done'
def script_visualizeRankDifferenceAsHist(params):
out_file_pre = params.out_file_pre
out_file_html = params.out_file_html
rel_path = params.rel_path
class_ids = params.class_id
layers = params.layer
if not hasattr(class_ids, '__iter__'):
class_ids = [class_ids]
if not hasattr(class_ids, '__iter__'):
layers = [layers]
img_paths_html = []
captions = []
for class_id in class_ids:
img_paths_html_row = []
captions_row = []
for layer in layers:
params = params._replace(class_id=class_id)
params = params._replace(layer=layer)
output = getNNRankComparisonInfo(params)
indices_difference = experiments_super.getDifferenceInRank(
output['img_paths_nn_train'], output['img_paths_nn_no_train'],
output['nn_rank_train'], output['nn_rank_no_train'])
xlabel = 'Difference in Rank (Train - Untrained)'
ylabel = 'Frequency'
title = class_id + ' ' + layer
indices_difference = [
diff_curr for diffs_curr in indices_difference
for diff_curr in diffs_curr
]
if len(indices_difference) == 0:
continue
out_file_im = out_file_pre + '_' + str(params.angle) + '_' + str(
params.diff) + '_' + str(
params.delta) + '_' + class_id + '_' + layer + '.png'
img_paths_html_row.append(
out_file_im.replace(rel_path[0], rel_path[1]))
total = len(indices_difference)
sum_less = sum(np.array(indices_difference) < 0) / float(total)
sum_less = '%0.2f' % (sum_less, )
sum_more = sum(np.array(indices_difference) >= 0) / float(total)
sum_more = '%0.2f' % (sum_more, )
captions_row.append('Total ' + str(total) + ', <0: ' + sum_less +
', >0: ' + sum_more)
visualize.hist(indices_difference,
out_file=out_file_im,
bins=params.bins,
normed=params.normed,
xlabel=xlabel,
ylabel=ylabel,
title=title)
img_paths_html.append(img_paths_html_row)
captions.append(captions_row)
visualize.writeHTML(out_file_html, img_paths_html, captions,
params.height_width[0], params.height_width[1])
def script_writeCommandsForSavingHashValsNpz():
out_dir = '/disk2/decemberExperiments/hash_tables'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
path_to_db = 'sqlite://///disk2/novemberExperiments/experiments_youtube/patches_nn_hash.db'
out_file = os.path.join(out_dir, 'commands_list.txt')
file_script = '/home/maheenrashid/Downloads/caffe/caffe-rc2/python/maheen_code/script_saveHashValsNpz.py'
commands = []
for hash_table in range(32):
for hash_val in range(256):
command = []
command.append('python')
command.append(file_script)
command.append(path_to_db)
command.append(out_dir)
command.append(str(hash_table))
command.append(str(hash_val))
command = ' '.join(command)
commands.append(command)
with open(out_file, 'wb') as f:
for command in commands:
f.write(command + '\n')
# def script_scoreRandomFrames(params):
path_to_db = params.path_to_db
class_labels_map = params.class_labels_map
npz_path = params.npz_path
numberOfFrames = params.numberOfFrames
max_idx = params.max_idx
n_jobs = params.n_jobs
table_idx_all = params.table_idx_all
out_file_html = params.out_file_html
rel_path = params.rel_path
width_height = params.width_height
out_file_frames = params.out_file_frames
[class_labels, class_idx] = zip(*class_labels_map)
if not os.path.exists(out_file_frames):
frames_all = []
for table_idx in table_idx_all:
scores, class_idx_curr, frame_path = getScoreForIdx(
table_idx,
path_to_db,
class_idx_pascal=class_idx,
npz_path=npz_path,
n_jobs=n_jobs)
frames_all.append([frame_path, class_idx_curr, scores])
pickle.dump(frames_all, open(out_file_frames, 'wb'))
frames_all = pickle.load(open(out_file_frames, 'rb'))
img_paths = []
captions = []
for frame_path, class_idx_curr, scores in frames_all:
scores = np.array(scores)
avg_scores = np.mean(scores, axis=0)
gt_idx = class_idx.index(class_idx_curr)
gt_score = avg_scores[gt_idx]
sort_idx = np.argsort(avg_scores)[::-1]
max_idx = sort_idx[0]
max_score = avg_scores[max_idx]
max_class_idx = class_idx[max_idx]
gt_rank = np.where(sort_idx == gt_idx)[0][0]
caption_curr = []
caption_curr.append('GT')
caption_curr.append(class_labels[class_idx.index(class_idx_curr)])
caption_curr.append(str(round(gt_score, 4)))
caption_curr.append(str(gt_rank + 1))
caption_curr.append('Best')
caption_curr.append(class_labels[max_idx])
caption_curr.append(str(round(max_score, 4)))
caption_curr = ' '.join(caption_curr)
img_paths.append([frame_path.replace(rel_path[0], rel_path[1])])
captions.append([caption_curr])
visualize.writeHTML(out_file_html, img_paths, captions, width_height[0],
width_height[1])
def saveHTML(out_us, us_test, batch_size=50, num_iter=2, justHTML=False):
dir_server = './'
post_us = ['_gt_pts.npy', '_pred_pts.npy']
im_paths, gt_pt_files, pred_pt_files = us_getFilePres(
us_test, out_us, post_us, num_iter, batch_size)
if justHTML:
post_ims_us = [
'_org_nokp.jpg',
'_gt.jpg',
'_warp_nokp.jpg',
'_warp.jpg',
'_org.jpg',
]
captions_for_row = [
'Input', 'Ground Truth', 'Warped Image', 'Prediction Warped',
'Prediction'
]
out_file_html = os.path.join(out_us, 'results.html')
idx_sort = range(len(gt_pt_files))
ims = []
captions = []
for idx_idx, idx_curr in enumerate(idx_sort):
file_curr = gt_pt_files[idx_curr]
file_curr = os.path.split(file_curr)[1]
file_curr = file_curr[:file_curr.index('_gt')]
files_us = [
os.path.join(dir_server, file_curr + post_im_curr)
for post_im_curr in post_ims_us
]
captions_us = [
str(idx_idx) + ' ' + caption_curr
for caption_curr in captions_for_row
]
ims.append(files_us)
captions.append(captions_us)
visualize.writeHTML(out_file_html, ims, captions)
print out_file_html
else:
errors_curr = us_getErrorsAll(us_test, out_us, post_us, num_iter,
batch_size)
err = np.array(errors_curr)
bin_keep = err >= 0
err[err < 0] = 0
div = np.sum(bin_keep, 1)
sum_val = np.sum(err, 1).astype(np.float)
avg = sum_val / div
post_ims_us = [
'_org_nokp.jpg',
'_gt.jpg',
'_warp_nokp.jpg',
'_warp.jpg',
'_org.jpg',
]
captions_for_row = [
'Input', 'Ground Truth', 'Warped Image', 'Prediction Warped',
'Prediction'
]
out_file_html = os.path.join(out_us, 'results.html')
idx_sort = np.argsort(avg)
ims = []
captions = []
for idx_idx, idx_curr in enumerate(idx_sort):
file_curr = gt_pt_files[idx_curr]
file_curr = os.path.split(file_curr)[1]
file_curr = file_curr[:file_curr.index('_gt')]
files_us = [
os.path.join(dir_server, file_curr + post_im_curr)
for post_im_curr in post_ims_us
]
captions_us = [
str(idx_idx) + ' ' + caption_curr
for caption_curr in captions_for_row
]
ims.append(files_us)
captions.append(captions_us)
visualize.writeHTML(out_file_html, ims, captions)
print out_file_html
labels = ['Ours']
# ,'thems'];
ticks = ['LE', 'RE', 'N', 'LM', 'RM', 'ALL']
colors = ['b']
# ,'g'];
ylim = None
errors_all = []
errors_curr = us_getErrorsAll(us_test, out_us, post_us, num_iter,
batch_size)
failures, failures_kp = getErrRates(errors_curr, 0.1)
errors_all.append(errors_curr)
# errors_all.append(errors_curr[:])
out_file_kp_err = os.path.join(out_us, 'bar.pdf')
err_rates_all = plotComparisonKpError(errors_all,
out_file_kp_err,
ticks,
labels,
colors=colors,
ylim=ylim)
out_file_stats = os.path.join(out_us, 'stats.txt')
# print err_rates_all;
string = [
str(ticks[idx_num_curr]) + ' ' + str(num_curr)
for idx_num_curr, num_curr in enumerate(err_rates_all[0])
]
print string
# print failures,failures_kp
# print errors_all
# string=' '.join(string);
util.writeFile(out_file_stats, string)
def script_createHistComparative():
out_dir_meta = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d'
train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_pre = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
dirs = [
dir[:-7] for dir in os.listdir(
'/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations')
if dir.endswith('_pascal')
]
layers = ['pool5', 'fc6', 'fc7']
delta = 5
caption_text = ['Trained', 'Not Trained']
replace = [out_dir_meta + '/', '']
degree = 90
deg_to_see = 0
# train_files=[os.path.join(train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p') for layer in layers for dir in dirs];
# non_train_files=[os.path.join(non_train_pre+'_'+layer+'_all_azimuths',dir+'_'+str(degree)+'_'+str(delta)+'_compress_data.p') for layer in layers for dir in dirs];
# for idx in range(len(train_files)):
combos = [(dir, layer) for dir in dirs for layer in layers]
out_file_html = os.path.join(
out_dir_meta,
'hist_by_degree_' + str(degree) + '_comparisons_compress.html')
img_paths = []
captions = []
for dir, layer in combos:
file_train = os.path.join(
train_pre + '_' + layer + '_all_azimuths',
dir + '_' + str(degree) + '_' + str(delta) + '_compress_data.p')
# train_files[idx];
file_non_train = os.path.join(
non_train_pre + '_' + layer + '_all_azimuths',
dir + '_' + str(degree) + '_' + str(delta) + '_compress_data.p')
# non_train_files[idx];
hists_train, bins_train = pickle.load(open(file_train, 'rb'))
hists_non_train, bins_non_train = pickle.load(
open(file_non_train, 'rb'))
mid_points_train = [
bins_train[i] + bins_train[i + 1] / float(2)
for i in range(len(bins_train) - 1)
]
mid_points_non_train = [
bins_non_train[i] + bins_non_train[i + 1] / float(2)
for i in range(len(bins_non_train) - 1)
]
# dir=file_train[file_train.rindex('/')+1:];
# dir=dir[:dir.index('_')];
out_file_just_file = layer + '_' + dir + '_' + str(degree) + '_' + str(
delta) + '.png'
out_file = os.path.join(out_dir_meta, out_file_just_file)
title = dir + ' Comparison'
xlabel = 'Distance Rank'
ylabel = 'Frequency'
# print out_file
img_paths.append([out_file_just_file])
captions.append([dir + ' ' + layer])
visualize.plotSimple(zip([mid_points_train, mid_points_non_train],
[hists_train, hists_non_train]),
out_file,
title=title,
xlabel=xlabel,
ylabel=ylabel,
legend_entries=['Trained', 'Non Trained'],
loc=0)
print out_file_html
visualize.writeHTML(out_file_html,
img_paths,
captions,
width=400,
height=400)
def main():
out_file_crude = '/disk2/januaryExperiments/tube_scoring/iou_crude_info.p'
out_file_bestOfBoth = '/disk2/januaryExperiments/tube_scoring/iou_bestOfBoth.p'
out_file_bestOfBoth_perShot = '/disk2/januaryExperiments/tube_scoring/iou_bestOfBoth_perShot.p'
out_file_file = '/disk2/januaryExperiments/tube_scoring/iou_crude_info.p'
class_labels_map = [('boat', 2), ('train', 9), ('dog', 6), ('cow', 5),
('aeroplane', 0), ('motorbike', 8), ('horse', 7),
('bird', 1), ('car', 3), ('cat', 4)]
avg_iou_pred, avg_iou_best = getAverageIOUPerClassBOB(
out_file_bestOfBoth, class_labels_map)
avg_iou_pred_perShot, _ = getAverageIOUPerClassBOB(
out_file_bestOfBoth_perShot, class_labels_map)
avg_iou_fanyi = getAverageIOUBestFanyi(out_file_crude, class_labels_map)
dict_vals = {}
label_keys = ['Fanyi', 'Shot', 'Frame', 'Best']
avg_ious = [
avg_iou_fanyi, avg_iou_pred_perShot, avg_iou_pred, avg_iou_best
]
xtick_labels = avg_iou_pred.keys()
print xtick_labels
for k in avg_iou_pred:
for idx in range(len(label_keys)):
if label_keys[idx] in dict_vals:
dict_vals[label_keys[idx]].append(avg_ious[idx][k])
else:
dict_vals[label_keys[idx]] = [avg_ious[idx][k]]
# dict_vals['Shot']=avg_iou_fanyi[k]
# dict_vals['Frame']=avg_iou_fanyi[k]
# dict_vals['Best']=avg_iou_fanyi[k]
print k, avg_iou_fanyi[k], avg_iou_pred_perShot[k], avg_iou_pred[
k], avg_iou_best[k]
out_file = '/disk2/januaryExperiments/tube_scoring/avg_iou_comparison.png'
colors = ['r', 'g', 'b', 'y']
visualize.plotGroupBar(out_file,
dict_vals,
xtick_labels,
label_keys,
colors,
ylabel='Average IOU',
title='Average IOU Comparison',
width=0.25,
ylim=[0.2, 0.9])
return
# path_to_txt='/disk2/youtube/categories/gt_list.txt';
params_dict = {}
params_dict['class_labels_map'] = [('boat', 2), ('train', 9), ('dog', 6),
('cow', 5), ('aeroplane', 0),
('motorbike', 8), ('horse', 7),
('bird', 1), ('car', 3), ('cat', 4)]
params_dict[
'out_file'] = '/disk2/januaryExperiments/tube_scoring/gt_data.p'
params_dict[
'path_to_tube_ranks'] = '/disk2/januaryExperiments/tube_scoring/scores_perShot'
params_dict['path_to_mats'] = '/disk2/res11'
params_dict[
'out_file_crude_info'] = '/disk2/januaryExperiments/tube_scoring/iou_crude_info_perShot.p'
params_dict[
'out_file_bestOfBoth'] = '/disk2/januaryExperiments/tube_scoring/iou_bestOfBoth_perShot.p'
params = createParams('saveIOUInfo')
params = params(**params_dict)
script_saveIOUInfo(params)
return
# path_to_data = '/disk2/youtube/categories'
# saveGTData(path_to_txt,class_labels_map,out_file)
# return
[class_labels, class_idx_all] = zip(*class_labels_map)
[meta_info, coords] = pickle.load(open(out_file, 'rb'))
meta_curr = meta_info[0]
gt_box = coords[0]
meta_curr_str = [str(curr) for curr in meta_curr]
class_label = class_labels[class_idx_all.index(meta_curr[0])]
tube_file = os.path.join(path_to_tube_ranks,
'_'.join(meta_curr_str[:3]) + '.p')
mat_file = os.path.join(
path_to_mats, '_'.join([class_label] + meta_curr_str[1:3]) + '.mat')
res = scipy.io.loadmat(mat_file, squeeze_me=True,
struct_as_record=False)['res']
tube_coords = getTubeCoordsForFrame(res, meta_curr[-1])
ious, tubes_gt = getTubeGTOverlap(gt_box, tube_coords)
tubes_ranked, tubes_scores = pickle.load(open(tube_file, 'rb'))
tubes_ranked = list(tubes_ranked)
gt_idx_best_rank, iou_best_rank, rank_idx_best_gt, iou_best_gt = getBestOfBothRank(
ious, tubes_gt, tubes_ranked)
print gt_idx_best_rank, iou_best_rank, rank_idx_best_gt, iou_best_gt
print tubes_ranked
return
frame_path = youtube.getFramePath(path_to_data, class_label, meta_curr[1],
meta_curr[2], meta_curr[3])
im = Image.open(frame_path)
draw = ImageDraw.Draw(im)
for idx_tube, tube in enumerate(tubes_ranked):
draw.line(getLineCoords(tube_coords[tube]),
width=2,
fill=(255, 255, 0))
draw.line(getLineCoords(tube_coords[tubes_ranked[0]]),
width=2,
fill=(255, 0, 0))
# for gt_box in gt_coords:
# print gt_box
draw.line(getLineCoords(gt_box), width=2, fill=(0, 255, 0))
out_file = '/disk2/temp/temp.png'
misc.imsave(out_file, np.array(im))
# gt_boxes=coords[0];
# break
# video_id=;
# shot_id=;
# frame_id=;
#
# print res['coor']
# break
# print sticks[0];
# videos=[vid for vid in os.listdir(path) if os.path.isdir(os.path.join(path,vid))];
# for vid in videos:
# path_vid = os.path.join(path,vid);
# shots=[shot for shot in os.listdir(path_vid) if os.path.isdir(os.path.join(path_vid,shot))];
# for shot in shots:
# path_shot = os.path.join(path_vid,shot);
return
meta_dir = '/disk2/januaryExperiments/tube_scoring'
out_file_html_pre = '/disk2/januaryExperiments/tube_scoring/best_tubes_comparison'
rel_path = ['/disk2', '../../..']
paths_to_im = [
os.path.join(meta_dir, 'images'),
os.path.join(meta_dir, 'images_perShot')
]
height_width = [500, 800]
columns = ['Frame Level', 'Shot Level']
for class_idx in range(10):
out_file_html = out_file_html_pre + '_' + str(class_idx) + '.html'
files = [
file_curr for file_curr in os.listdir(paths_to_im[0])
if file_curr.endswith('.png')
and file_curr.startswith(str(class_idx) + '_')
]
img_paths = []
captions = []
for file_curr in files:
img_paths_row = []
captions_row = []
for idx_path_to_im, path_to_im in enumerate(paths_to_im):
im_curr = os.path.join(path_to_im, file_curr).replace(
rel_path[0], rel_path[1])
img_paths_row.append(im_curr)
captions_row.append(columns[idx_path_to_im] + ' ' + file_curr)
img_paths.append(img_paths_row)
captions.append(captions_row)
visualize.writeHTML(out_file_html, img_paths, captions,
height_width[0], height_width[1])
return
params_dict = {}
params_dict['path_to_data'] = '/disk2/youtube/categories'
params_dict[
'score_dir'] = '/disk2/januaryExperiments/tube_scoring/scores_perShot'
params_dict['mat_dir'] = '/disk2/res11'
params_dict[
'out_dir'] = '/disk2/januaryExperiments/tube_scoring/images_perShot'
if not os.path.exists(params_dict['out_dir']):
os.mkdir(params_dict['out_dir'])
params_dict['to_exclude'] = [
'/disk2/res11/horse_7_16.mat', '/disk2/res11/horse_7_14.mat',
'/disk2/res11/horse_4_49.mat'
]
params_dict['class_labels_map'] = [('boat', 2), ('train', 9), ('dog', 6),
('cow', 5), ('aeroplane', 0),
('motorbike', 8), ('horse', 7),
('bird', 1), ('car', 3), ('cat', 4)]
params_dict['n_jobs'] = 12
params = createParams('drawTubeBB')
params = params(**params_dict)
script_drawTubeBB(params)
return
shot_dir = '/disk2/januaryExperiments/shot_score_normalized_perShot'
out_dir = '/disk2/januaryExperiments/tube_scoring/scores_perShot'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
class_labels_map = [('boat', 2), ('train', 9), ('dog', 6), ('cow', 5),
('aeroplane', 0), ('motorbike', 8), ('horse', 7),
('bird', 1), ('car', 3), ('cat', 4)]
n_jobs = 12
[class_labels, class_idx_all] = zip(*class_labels_map)
check_list = [str(class_idx) for class_idx in class_idx_all]
# print check_list
file_list = [
file_curr for file_curr in os.listdir(shot_dir)
if file_curr.endswith('.p') and file_curr[0] in check_list
]
args = [(os.path.join(shot_dir,
file_curr), os.path.join(out_dir, file_curr), idx)
for idx, file_curr in enumerate(file_list)]
print len(args)
p = multiprocessing.Pool(n_jobs)
p.map(saveBestTubeAvgScore, args)
# for class_idx in class_idx_all:
# rel_files=[file_curr for file_curr in file_list if file_curr.startswith(str(class_idx)+'_') and file_curr.endswith('.p')];
# for rel_file in rel_files:
# score_file=os.path.join(shot_dir,rel_file);
# out_file=os.path.join(out_dir,rel_file);
# best_tube_rank,tubes_ranked,scores_ranked = getBestTubeAvgScore(score_file)
# pickle.dump([best_tube_rank,tubes_ranked,scores_ranked],open(out_file,'wb'));
# out_files=[os.path.join(shot_dir,file_curr) for file_curr in file_list if file_curr.startswith(str(class_idx)+'_') and file_curr.endswith('.p')];
# score_file=os.path.join(shot_dir,str(class_idx)+'_'+str(video_id)+'_'+str(shot_id)+'.p');
# best_tube_rank,tubes_ranked,scores_ranked = getBestTubeAvgScore(os.path.join(shot_dir,score_file))
return
path_to_data = '/disk2/youtube/categories'
to_exclude = [
'/disk2/res11/horse_7_16.mat', '/disk2/res11/horse_7_14.mat',
'/disk2/res11/horse_4_49.mat'
]
meta_dir = '/disk2/res11'
mat_files = pickle.load(open('/disk2/temp/horse_problem.p', 'rb'))
mat_files = [
os.path.join(meta_dir, file_curr[file_curr.rindex('/') + 1:] + '.mat')
for file_curr in mat_files
]
# for mat_file in mat_files:
mat_file = '/disk2/res11/horse_7_11.mat'
out_file = '/disk2/temp.png'
drawTubeBB(mat_file, path_to_data, out_file)
return
path_to_data = '/disk2/youtube/categories'
out_dir_patches = '/disk2/res11/tubePatches'
path_to_mat = '/disk2/res11'
if not os.path.exists(out_dir_patches):
os.mkdir(out_dir_patches)
mat_files = [
os.path.join(path_to_mat, file_curr)
for file_curr in os.listdir(path_to_mat) if file_curr.endswith('.mat')
]
mat_file = mat_files[0]
print mat_file
drawTubeBB(mat_file)
# script_saveTubePatches(mat_files,path_to_data,out_dir_patches,numThreads=8)
return
shot_dir = '/disk2/januaryExperiments/shot_score_normalized'
class_idx = 0
video_id = 1
shot_id = 1
score_file = os.path.join(
shot_dir,
str(class_idx) + '_' + str(video_id) + '_' + str(shot_id) + '.p')
best_tube_rank, tubes_ranked, scores_ranked = getBestTubeAvgScore(
os.path.join(shot_dir, score_file))
print best_tube_rank, tubes_ranked, scores_ranked
def main():
train_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
layers = ['pool5', 'fc6', 'fc7']
out_dir = '/disk2/octoberExperiments/nn_pascal3d'
db_file = os.path.join(out_dir, 'nn_pascal3d_new.db')
if not os.path.exists(out_dir):
os.mkdir(out_dir)
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations'
class_ids = [
dir[:-7] for dir in os.listdir(path_to_anno) if dir.endswith('pascal')
]
file_pre = train_file
trainFlag = True
caffe_model = '/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'
# exceptions=script_populateDB(db_file,file_pre,trainFlag,layers,class_ids,caffe_model)
# for ex in exceptions:
# print len(ex)
# pickle.dump([exceptions],open(file_pre+'_db_exceptions.p','wb'));
file_pre = non_train_file
trainFlag = False
caffe_model = '/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel'
script_populateDB(db_file, file_pre, trainFlag, layers, class_ids,
caffe_model)
return
script_saveIndicesAll(train_file, layers)
script_saveIndicesAll(non_train_file, layers)
# script_testingDoNN();
return
script_createHistComparative()
# script_createHistsWithSpecificAngle()
return
script_createHistComparative()
# script_createHistDifferenceHTML()
# script_savePerClassPerDegreeHistograms()
return
script_visualizePerClassAzimuthPerformance()
return
train_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/trained/20151027204114'
non_train_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547'
layers = ['pool5', 'fc6', 'fc7']
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations'
for file_name in [train_file, non_train_file]:
[img_paths, gt_labels,
azimuths] = pickle.load(open(file_name + '_azimuths.p', 'rb'))
for layer in layers:
print layer
file_name_l = file_name + '_' + layer + '_all'
out_file = file_name_l + '_azimuths.p'
t = time.time()
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
t = time.time() - t
print t
# raw_input();
diffs_all, dists_all = getAzimuthInfo(img_paths, gt_labels,
indices, azimuths)
pickle.dump([img_paths, gt_labels, azimuths, diffs_all, dists_all],
open(out_file, 'wb'))
return
text_labels = [
dir[:-7] for dir in os.listdir(path_to_anno) if dir.endswith('pascal')
]
for file_name in [train_file, non_train_file]:
[img_paths, gt_labels,
azimuths] = pickle.load(open(file_name + '_azimuths.p', 'rb'))
for layer in layers:
print layer
file_name_l = file_name + '_' + layer + '_all'
out_dir = file_name_l + '_azimuths'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
t = time.time()
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
t = time.time() - t
print t
# raw_input();
createAzimuthGraphs(img_paths, gt_labels, indices, azimuths,
out_dir, text_labels)
for layer in layers:
print layer
out_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/azimuths_' + layer + '_all' + '_comparison.html'
rel_train = 'trained/20151027204114_' + layer + '_all' + '_azimuths'
rel_notrain = 'no_trained/20151027203547_' + layer + '_all' + '_azimuths'
out_dir = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203547_' + layer + '_all' + '_azimuths'
im_paths = [[
os.path.join(rel_train, file_curr),
os.path.join(rel_notrain, file_curr)
] for file_curr in os.listdir(out_dir) if file_curr.endswith('.jpg')]
captions = [['train', 'no_train']] * len(im_paths)
visualize.writeHTML(out_file,
im_paths,
captions,
height=500,
width=500)
# script_saveAzimuthInfo(train_file,path_to_anno);
# script_saveAzimuthInfo(non_train_file,path_to_anno);
# script_saveIndicesAll(train_file,layers)
# script_saveIndicesAll(non_train_file,layers)
return
out_dir = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
# out_dir=os.path.join(out_dir,'no_trained');
out_dir = os.path.join(out_dir, 'trained')
if not os.path.exists(out_dir):
os.mkdir(out_dir)
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations'
file_dir = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB'
dirs = [
dir[:-7] for dir in os.listdir(path_to_anno) if dir.endswith('pascal')
]
test_set = []
for dir_idx, dir in enumerate(dirs):
ims = [
filename for filename in glob.glob(file_dir + '/*' + dir + '*.jpg')
]
test_set.extend(zip(ims, [dir_idx] * len(ims)))
print len(test_set)
layers = ['pool5', 'fc6', 'fc7']
gpu_no = 1
path_to_classify = '..'
numberOfN = 5
relativePaths = ['/disk2', '../../../../..']
deployFile = '/disk2/octoberExperiments/nn_performance_without_pascal/deploy.prototxt'
meanFile = '/disk2/octoberExperiments/nn_performance_without_pascal/mean.npy'
modelFile = '/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel'
# file_name=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers,deployFile=deployFile,meanFile=meanFile,modelFile=modelFile,ext='jpg')
# file_name=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers,ext='jpg')
file_name = os.path.join(out_dir, '20151027204114')
test_set, _ = pickle.load(open(file_name + '.p', 'rb'))
vals = np.load(file_name + '.npz')
test_set = sorted(test_set, key=lambda x: x[0])
test_set = zip(*test_set)
img_paths = list(test_set[0])
gt_labels = list(test_set[1])
numberOfN = 5
# file_name_alt='/disk2/octoberExperiments/nn_performance_without_pascal/pascal_3d/no_trained/20151027203004'
for layer in layers:
print layer
file_name_l = file_name + '_' + layer
# indices,conf_matrix=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,vals[layer],numberOfN=numberOfN,distance='cosine',algo='brute')
# pickle.dump([img_paths,gt_labels,indices,conf_matrix],open(file_name_l+'.p','wb'));
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
idx_sort_binned = script_nearestNeigbourExperiment.sortByPerformance(
indices, gt_labels, 0, perClass=True)
img_paths = [x.replace('/disk2', '../../../../..') for x in img_paths]
im_paths, captions = visualize.createImageAndCaptionGrid(
img_paths, gt_labels, indices, dirs)
im_paths = [im_paths[idx] for idx in idx_sort_binned]
captions = [captions[idx] for idx in idx_sort_binned]
visualize.writeHTML(file_name_l + '_sorted.html', im_paths, captions)
return
path_to_anno = '/disk2/pascal_3d/PASCAL3D+_release1.0/Annotations'
path_to_im = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images'
dirs = [dir for dir in os.listdir(path_to_anno) if dir.endswith('pascal')]
out_dir = '/disk2/pascal_3d/PASCAL3D+_release1.0/Images_BB'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
for dir in dirs:
file_names = [
os.path.join(dir, file_name)[:-4]
for file_name in os.listdir(os.path.join(path_to_im, dir))
if file_name.endswith('.jpg')
]
saveBBImages(path_to_im, path_to_anno, file_names, out_dir)
def script_scoreRandomFrames(params):
path_to_db = params.path_to_db
class_labels_map = params.class_labels_map
npz_path = params.npz_path
numberOfFrames = params.numberOfFrames
max_idx = params.max_idx
n_jobs = params.n_jobs
table_idx_all = params.table_idx_all
out_file_html = params.out_file_html
rel_path = params.rel_path
width_height = params.width_height
out_file_frames = params.out_file_frames
frameCountNorm = params.frameCountNorm
[class_labels, class_idx] = zip(*class_labels_map)
if not os.path.exists(out_file_frames):
if frameCountNorm:
total_counts = getTotalCountsPerClass(path_to_db, list(class_idx))
else:
total_counts = None
frames_all = []
for table_idx in table_idx_all:
scores, class_idx_curr, frame_path = getScoreForIdx(
table_idx,
path_to_db,
class_idx_pascal=class_idx,
npz_path=npz_path,
n_jobs=n_jobs,
total_counts=total_counts)
frames_all.append([frame_path, class_idx_curr, scores])
pickle.dump(frames_all, open(out_file_frames, 'wb'))
frames_all = pickle.load(open(out_file_frames, 'rb'))
img_paths = []
captions = []
for frame_path, class_idx_curr, scores in frames_all:
scores = np.array(scores)
avg_scores = np.mean(scores, axis=0)
gt_idx = class_idx.index(class_idx_curr)
gt_score = avg_scores[gt_idx]
sort_idx = np.argsort(avg_scores)[::-1]
max_idx = sort_idx[0]
max_score = avg_scores[max_idx]
max_class_idx = class_idx[max_idx]
gt_rank = np.where(sort_idx == gt_idx)[0][0]
caption_curr = []
caption_curr.append('GT')
caption_curr.append(class_labels[class_idx.index(class_idx_curr)])
caption_curr.append(str(round(gt_score, 4)))
caption_curr.append(str(gt_rank + 1))
caption_curr.append('Best')
caption_curr.append(class_labels[max_idx])
caption_curr.append(str(round(max_score, 4)))
caption_curr = ' '.join(caption_curr)
img_paths.append([frame_path.replace(rel_path[0], rel_path[1])])
captions.append([caption_curr])
visualize.writeHTML(out_file_html, img_paths, captions, width_height[0],
width_height[1])
def main():
# out_dir='/disk3/maheen_data/ft_youtube_40_noFix_diffLR_sZclusters';
# model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
# util.mkdir(out_dir);
# train_file=os.path.join(out_dir,'train.txt');
# template_deploy_file='trainval_noFix_withRandom_diffForConv.prototxt';
# template_solver_file='solver_debug.prototxt';
# base_lr=0.000001;
# snapshot=1000;
# layers=[None,'conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8'];
# gpu=1;
# commands=[];
# idx=len(layers)-4;
# fix_layers=layers[1:idx+1];
# layer_str='_'.join(fix_layers);
# print layer_str;
# # return
# model_file_curr=model_file
# snapshot_prefix=os.path.join(out_dir,'opt_noFix_'+layer_str+'_');
# out_deploy_file=os.path.join(out_dir,'deploy_'+layer_str+'.prototxt');
# out_solver_file=os.path.join(out_dir,'solver_'+layer_str+'.prototxt');
# log_file=os.path.join(out_dir,'log_'+layer_str+'.log');
# replaceSolverFile(out_solver_file,template_solver_file,out_deploy_file,base_lr,snapshot,snapshot_prefix,gpu=gpu);
# replaceDeployFile(out_deploy_file,template_deploy_file,train_file,fix_layers);
# command=printTrainingCommand(out_solver_file,log_file,model_file_curr);
# util.writeFile(os.path.join(out_dir,'train.sh'),[command]);
# return
model_file='/disk3/maheen_data/ft_youtube_40_images_cluster_suppress_yjConfig/opt_noFix_conv1_conv2_conv3_conv4_conv5_llr__iter_50000.caffemodel'
# model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
solver_file='/disk3/maheen_data/ft_youtube_40_images_cluster_suppress_yjConfig/solver_conv1_conv2_conv3_conv4_conv5.prototxt';
deploy_file='/disk3/maheen_data/ft_youtube_40_images_cluster_suppress_yjConfig/deploy_conv1_conv2_conv3_conv4_conv5.prototxt';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
solver_file='/disk3/maheen_data/ft_youtube_40_noFix_diffLR_sZclusters/solver_conv1_conv2_conv3_conv4_conv5.prototxt'
deploy_file='/disk3/maheen_data/ft_youtube_40_noFix_diffLR_sZclusters/deploy_conv1_conv2_conv3_conv4_conv5.prototxt';
justCheckGradients(solver_file,deploy_file,model_file);
return
out_dir='/disk3/maheen_data/debug_networks/sanityCheckDebug';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
util.mkdir(out_dir);
train_file=os.path.join(out_dir,'train.txt');
template_deploy_file='deploy_withRandom.prototxt';
template_solver_file='solver_debug.prototxt';
base_lr=0.000001;
snapshot=1000;
layers=[None,'conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8'];
gpu=1;
commands=[];
idx=len(layers)-1;
fix_layers=layers[1:idx+1];
layer_str='_'.join(fix_layers);
print layer_str;
model_file_curr=model_file
snapshot_prefix=os.path.join(out_dir,'opt_noFix_'+layer_str+'_');
out_deploy_file=os.path.join(out_dir,'deploy_'+layer_str+'.prototxt');
out_solver_file=os.path.join(out_dir,'solver_'+layer_str+'.prototxt');
log_file=os.path.join(out_dir,'log_'+layer_str+'.log');
replaceSolverFile(out_solver_file,template_solver_file,out_deploy_file,base_lr,snapshot,snapshot_prefix,gpu=gpu);
replaceDeployFile(out_deploy_file,template_deploy_file,train_file,fix_layers);
command=printTrainingCommand(out_solver_file,log_file,model_file_curr);
util.writeFile(os.path.join(out_dir,'train.sh'),[command]);
return
out_dir='/disk3/maheen_data/ft_youtube_40_images_cluster_suppress_yjConfig/';
out_dir='/disk3/maheen_data/ft_youtube_40_images_cluster_suppress_yjConfig_llr_diff/';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
util.mkdir(out_dir);
train_file=os.path.join(out_dir,'train.txt');
template_deploy_file='deploy_withRandom_yjConfig.prototxt';
template_solver_file='solver_debug.prototxt';
base_lr=0.00001;
snapshot=500;
layers=[None,'conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8'];
gpu=1;
commands=[];
idx=len(layers)-4;
fix_layers=layers[1:idx+1];
layer_str='_'.join(fix_layers);
print layer_str;
# return
model_file_curr=model_file
snapshot_prefix=os.path.join(out_dir,'opt_noFix_'+layer_str+'_');
out_deploy_file=os.path.join(out_dir,'deploy_'+layer_str+'.prototxt');
out_solver_file=os.path.join(out_dir,'solver_'+layer_str+'.prototxt');
log_file=os.path.join(out_dir,'log_'+layer_str+'.log');
replaceSolverFile(out_solver_file,template_solver_file,out_deploy_file,base_lr,snapshot,snapshot_prefix,gpu=gpu);
replaceDeployFile(out_deploy_file,template_deploy_file,train_file,fix_layers);
command=printTrainingCommand(out_solver_file,log_file,model_file_curr);
util.writeFile(os.path.join(out_dir,'train.sh'),[command]);
return
out_dir='/disk3/maheen_data/ft_youtube_40_noFix_noCopyFC8_FC7';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
# out_dir='/disk3/maheen_data/ft_youtube_40_noFix_alexnet';
# model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/models/bvlc_alexnet/bvlc_alexnet.caffemodel';
util.mkdir(out_dir);
train_txt_orig_path='/disk3/maheen_data/ft_youtube_40/train.txt';
template_deploy_file='deploy_withRandom.prototxt';
template_solver_file='solver_debug.prototxt';
train_file=os.path.join(out_dir,'train.txt');
data=util.readLinesFromFile(train_txt_orig_path);
random.shuffle(data);
# data[:100];
util.writeFile(train_file,data);
# shutil.copyfile(train_txt_orig_path,train_file);
# out_dir='/disk3/maheen_data/ft_youtube_40_ucf_permute';
# train_file=os.path.join(out_dir,'train_permute.txt');
base_lr=0.0001;
snapshot=2000;
layers=[None,'conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8'];
gpu=0;
# command_file=os.path.join(out_dir,'debug_0.sh');
commands=[];
# for idx in range(4,len(layers)):
# if idx==0:
# fix_layers=layers[0];
# layer_str=str(fix_layers);
# model_file_curr=None;
# else:
idx=len(layers)-3;
fix_layers=layers[1:idx+1];
layer_str='_'.join(fix_layers);
print layer_str;
return
model_file_curr=model_file
# print fix_layers
snapshot_prefix=os.path.join(out_dir,'opt_noFix_'+layer_str+'_');
out_deploy_file=os.path.join(out_dir,'deploy_'+layer_str+'.prototxt');
out_solver_file=os.path.join(out_dir,'solver_'+layer_str+'.prototxt');
log_file=os.path.join(out_dir,'log_'+layer_str+'.log');
replaceSolverFile(out_solver_file,template_solver_file,out_deploy_file,base_lr,snapshot,snapshot_prefix,gpu=gpu);
replaceDeployFile(out_deploy_file,template_deploy_file,train_file,fix_layers);
command=printTrainingCommand(out_solver_file,log_file,model_file_curr);
util.writeFile(os.path.join(out_dir,'train.sh'),[command]);
# commands.append(command);
# util.writeFile(command_file,commands);
return
# out_dir='/disk3/maheen_data/debug_networks/noFix';
# model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
# '/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/train.txt'
# data=util.readLinesFromFile(train_txt_orig_path);
# random.shuffle(data);
# # data[:100];
# util.writeFile(train_file,data[:100]);
# out_dir='/disk3/maheen_data/debug_networks/noFixNoCopy';
# model_file=None;
out_dir='/disk3/maheen_data/debug_networks/noFixCopyByLayer';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
util.mkdir(out_dir);
train_txt_orig_path='/disk3/maheen_data/debug_networks/noFix/train.txt';
deploy_file='/disk3/maheen_data/debug_networks/noFix/deploy.prototxt';
solver_file='/disk3/maheen_data/debug_networks/noFix/solver.prototxt';
# template_deploy_file='deploy_debug_noFix.prototxt';
template_deploy_file='deploy_fc8NoCopy.prototxt';
template_solver_file='solver_debug.prototxt';
train_file=os.path.join(out_dir,'train.txt');
# shutil.copyfile(train_txt_orig_path,train_file);
base_lr=0.0001;
snapshot=100;
layers=[None,'conv1','conv2','conv3','conv4','conv5','fc6','fc7','fc8'];
return
out_dir='/disk3/maheen_data/ft_youtube_40_noFix_alexnet';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/models/bvlc_alexnet/bvlc_alexnet.caffemodel';
layers=['conv1','conv2','conv3','conv4','conv5','fc6','fc7'];
layers_str=[];
for idx in range(len(layers)):
if idx==0:
fix_layers=layers[0];
layer_str=str(fix_layers);
else:
fix_layers=layers[1:idx+1];
layer_str='_'.join(fix_layers);
layers_str.append(layer_str);
log_files=[os.path.join(out_dir,'log_'+layer_str+'.log') for layer_str in layers_str];
str_match=' solver.cpp:209] Iteration ';
xAndYs=[svl.getIterationsAndLosses(log_file,str_match) for log_file in log_files];
out_files=[];
for layer_str,log_file in zip(layers_str,log_files):
xAndY=svl.getIterationsAndLosses(log_file,str_match);
print xAndY
out_file=os.path.join(out_dir,'loss_'+layer_str+'.png');
visualize.plotSimple([xAndY],out_file,title=layer_str);
out_files.append(out_file);
out_file_html=os.path.join(out_dir,'losses_all.html');
img_paths=[[util.getRelPath(out_file,'/disk3')] for out_file in out_files];
captions=[['']]*len(out_files);
print img_paths
print captions
visualize.writeHTML(out_file_html,img_paths,captions,height=300,width=300);
# out_file=os.path.join(out_dir,'losses_all.png');
# print len(xAndYs);
# print xAndYs[-2][1]
# visualize.plotSimple(xAndYs,out_file,legend_entries=layers_str,loc=0,outside=True)
return
# mean_standard_proto_file='/home/maheenrashid/Downloads/debugging_jacob/opticalflow/standard.binaryproto';
model_file='/home/maheenrashid/Downloads/debugging_jacob/optical_flow_prediction/examples/opticalflow/final.caffemodel';
layers_to_copy=['conv1','conv2','conv3','conv4','conv5']
# model_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/OptFlow_youtube_hmdb__iter_5000.caffemodel';
# layers_to_copy=['conv1','conv2','conv3','conv4','conv5','fc6_fix','fc7_fix','fc8_fix']
# model_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic_llr/OptFlow_youtube_hmdb__iter_65000.caffemodel';
# layers_to_copy=['conv1','conv2','conv3','conv4','conv5','fc6_fix','fc7_fix','fc8_fix']
# deploy_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/opt_train_coarse_xavier.prototxt';
# solver_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/train.prototxt';
deploy_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/deploy_debug.prototxt';
solver_file='/disk2/mayExperiments/ft_youtube_hmdb_newClusters_layerMagic/solver_debug.prototxt';
# layers_to_copy=['conv1','conv2','conv3','conv4','conv5','fc6_fix','fc7_fix','fc8_fix']
# layers_to_explore=['conv1','conv2','conv3','conv4','conv5','fc6_fix','fc7_fix','fc8_fix']
# ,'fc6','fc7','fc8']
layers_to_explore=['conv1','conv2','conv3','conv4','conv5','fc6_fix','fc7_fix','fc8_fix']
blobs_lr=[(0,0),(0,0),(0,0),
# (10,20),(10,20),
(0.1,0.2),(0.1,0.2),
(1,2),(1,2),(1,2)]
iterations=400;
momentum=0.9;
lr=0.000001;
caffe.set_device(1)
caffe.set_mode_gpu()
solver=caffe.SGDSolver(solver_file);
net_org=caffe.Net(deploy_file,model_file);
# copy weights
for layer_name in layers_to_copy:
solver.net.params[layer_name][0].data[...]=net_org.params[layer_name][0].data;
solver.net.params[layer_name][1].data[...]=net_org.params[layer_name][1].data;
layer_names=list(solver.net._layer_names);
ratios={};
for key in layers_to_explore:
ratios[key]=[];
dict_layers={};
for idx_curr,layer_name in enumerate(layer_names):
print idx_curr,layer_name,
if layer_name in solver.net.params.keys():
print len(solver.net.params[layer_name])
update_prev=[np.zeros(solver.net.layers[idx_curr].blobs[0].diff.shape),
np.zeros(solver.net.layers[idx_curr].blobs[1].diff.shape)];
blob_lr=list(blobs_lr[layers_to_explore.index(layer_name)]);
dict_layers[idx_curr]=[layer_name,update_prev,blob_lr];
else:
print 0;
for idx_curr in dict_layers.keys():
print idx_curr,len(dict_layers[idx_curr]),dict_layers[idx_curr][0],dict_layers[idx_curr][1][0].shape,dict_layers[idx_curr][1][1].shape,dict_layers[idx_curr][2]
for iteration in range(iterations):
print iteration
solver.net.forward();
solver.net.backward();
for idx_curr in dict_layers.keys():
rel_row=dict_layers[idx_curr]
layer_name=rel_row[0];
update_prev=rel_row[1][0];
print rel_row[2][0]
lr_curr=rel_row[2][0]*lr;
diffs_curr=solver.net.params[layer_name][0].diff;
weights_curr=solver.net.params[layer_name][0].data;
param_scale = np.linalg.norm(weights_curr.ravel())
update = update_prev*momentum-lr_curr*diffs_curr;
update_scale = np.linalg.norm(update.ravel())
ratio= update_scale / param_scale # want ~1e-3
print layer_name,ratio,update_scale,param_scale
ratios[layer_name].append(ratio);
for idx_curr,layer in enumerate(solver.net.layers):
for idx_blob,blob in enumerate(layer.blobs):
rel_row=dict_layers[idx_curr]
layer_name=rel_row[0];
update_prev=rel_row[1][idx_blob];
lr_curr=rel_row[2][idx_blob]*lr;
diffs_curr=blob.diff;
update_curr=momentum*update_prev-(lr_curr*diffs_curr);
blob.data[...] -= update_curr
blob.diff[...] = np.zeros(blob.diff.shape);
dict_layers[idx_curr][1][idx_blob]=update_curr;
def main():
old_file = '/home/laoreja/data/knn_res_new/knn_5_points_train_list.txt'
new_file = '/home/maheenrashid/Downloads/knn_5_points_train_list_clean.txt'
match_str = 'n02374451_4338.JPEG'
lines = util.readLinesFromFile(old_file)
lines_to_keep = []
for line in lines:
if match_str not in line:
lines_to_keep.append(line)
assert len(lines_to_keep) == len(lines) - 1
util.writeFile(new_file, lines_to_keep)
return
file_curr = '/home/laoreja/finetune-deep-landmark/dataset/train/trainImageList_2.txt'
out_file = '/home/maheenrashid/Downloads/trainImageList_2_clean.txt'
lines = util.readLinesFromFile(file_curr)
lines_to_keep = []
for line in lines:
if line == '/home/laoreja/data/horse-images/annotation/imagenet_n02374451/gxy/n02374451_4338.JPEG 156 169 79 99 161 88 1 43 46 1 167 95 1 164 95 1 43 56 1':
print 'found!'
else:
lines_to_keep.append(line)
print len(lines_to_keep), len(lines)
assert len(lines_to_keep) + 1 == len(lines)
util.writeFile(out_file, lines_to_keep)
return
horse_file = '/home/SSD3/maheen-data/horse_project/horse/matches_5_val_fiveKP.txt'
human_file = '/home/SSD3/maheen-data/horse_project/aflw/matches_5_val_fiveKP_noIm.txt'
horse_data = util.readLinesFromFile(horse_file)
human_data = util.readLinesFromFile(human_file)
# horse_data=[horse_data[41]];
# human_data=[human_data[41]];
# print horse_data[0];
horse_im = [line_curr.split(' ')[0] for line_curr in horse_data]
human_im = [
line_curr.split(' ')[0].replace('/npy/',
'/im/').replace('.npy', '.jpg')
for line_curr in human_data
]
horse_npy = [line_curr.split(' ')[1] for line_curr in horse_data]
human_npy = [line_curr.split(' ')[0] for line_curr in human_data]
problem_cases = []
for horse_npy_curr in horse_npy:
labels = np.load(horse_npy_curr)
if np.any(labels < 0):
problem_cases.append(horse_npy_curr)
print len(problem_cases), len(set(problem_cases))
return
dir_server = '/home/SSD3/maheen-data'
out_dir_debug = os.path.join(dir_server, 'temp',
'debug_problem_batch/rerun')
im_file = '/home/laoreja/data/horse-images/annotation/imagenet_n02374451/gxy/n02374451_4338.JPEG'
npy_file = '/home/SSD3/maheen-data/temp/debug_problem_batch/rerun/npy/imagenet_n02374451/n02374451_4338.npy'
out_file = os.path.join(out_dir_debug, 'check.png')
saveImWithAnno((1, im_file, npy_file, out_file))
# arg=([156, 169, 79, 99], [[161, 88, 1], [43, 46, 1], [167, 95, 1], [164, 95, 1], [43, 56, 1]], '/home/SSD3/maheen-data/temp/debug_problem_batch/rerun/npy/imagenet_n02374451/n02374451_4338.npy', 0);
# # print np.load(arg[2]);
# saveBBoxNpy(arg);
# # print np.load(arg[2]);
return
dir_server = '/home/SSD3/maheen-data'
out_dir_debug = os.path.join(dir_server, 'temp',
'debug_problem_batch/rerun')
util.mkdir(out_dir_debug)
params_dict = {}
params_dict[
'path_txt'] = '/home/SSD3/maheen-data/temp/debug_problem_batch/train_dummy.txt'
# '/home/laoreja/finetune-deep-landmark/dataset/train/trainImageList_2.txt';
params_dict['path_pre'] = None
params_dict['type_data'] = 'horse'
params_dict['out_dir_meta'] = out_dir_debug
util.mkdir(params_dict['out_dir_meta'])
params_dict['out_dir_im'] = os.path.join(params_dict['out_dir_meta'], 'im')
params_dict['out_dir_npy'] = os.path.join(params_dict['out_dir_meta'],
'npy')
params_dict['out_file_list_npy'] = os.path.join(params_dict['out_dir_npy'],
'data_list.txt')
params_dict['out_file_list_im'] = os.path.join(params_dict['out_dir_im'],
'data_list.txt')
params_dict['out_file_pairs'] = os.path.join(params_dict['out_dir_meta'],
'pairs.txt')
params_dict['overwrite'] = True
local_script_makeBboxPairFiles(params_dict)
return
npy_file = '/home/SSD3/maheen-data/horse_project/horse/npy/imagenet_n02374451/n02374451_4338.npy'
labels = np.load(npy_file)
print labels
return
dir_server = '/home/SSD3/maheen-data'
out_dir_debug = os.path.join(dir_server, 'temp', 'debug_problem_batch')
util.mkdir(out_dir_debug)
out_horse_im_dir = os.path.join(out_dir_debug, 'horse_im')
out_human_im_dir = os.path.join(out_dir_debug, 'human_im')
util.mkdir(out_horse_im_dir)
util.mkdir(out_human_im_dir)
horse_file = '/home/SSD3/maheen-data/horse_project/horse_resize/matches_5_train_fiveKP_debug.txt'
human_file = '/home/SSD3/maheen-data/horse_project/aflw/matches_5_train_fiveKP_noIm_debug.txt'
horse_data = util.readLinesFromFile(horse_file)
human_data = util.readLinesFromFile(human_file)
horse_data = [horse_data[41]]
human_data = [human_data[41]]
print horse_data[0]
horse_im = [line_curr.split(' ')[0] for line_curr in horse_data]
human_im = [
line_curr.split(' ')[0].replace('/npy/',
'/im/').replace('.npy', '.jpg')
for line_curr in human_data
]
horse_npy = [line_curr.split(' ')[1] for line_curr in horse_data]
human_npy = [line_curr.split(' ')[0] for line_curr in human_data]
args = []
for idx, horse_im_curr in enumerate(horse_im):
args.append((idx, horse_im_curr, horse_npy[idx],
os.path.join(out_horse_im_dir,
str(idx) + '.jpg')))
for idx, horse_im_curr in enumerate(human_im):
args.append((idx, horse_im_curr, human_npy[idx],
os.path.join(out_human_im_dir,
str(idx) + '.jpg')))
# saveImWithAnno(args[-1]);
p = multiprocessing.Pool(multiprocessing.cpu_count())
p.map(saveImWithAnno, args)
out_file_html = os.path.join(out_dir_debug, 'viz_matches.html')
img_paths = []
captions = []
for idx in range(len(horse_im)):
horse_im_curr = os.path.join(out_horse_im_dir,
str(idx) + '.jpg')
horse_im_curr = util.getRelPath(horse_im_curr, dir_server)
human_im_curr = os.path.join(out_human_im_dir,
str(idx) + '.jpg')
human_im_curr = util.getRelPath(human_im_curr, dir_server)
img_paths.append([horse_im_curr, human_im_curr])
captions.append(['horse ' + str(idx), 'human'])
# for idx,horse_im_curr in enumerate(horse_im):
# human_im_curr=util.getRelPath(human_im[idx],dir_server);
# horse_im_curr=util.getRelPath(horse_im_curr,dir_server);
# img_paths.append([horse_im_curr,human_im_curr]);
# captions.append(['horse','human']);
visualize.writeHTML(out_file_html, img_paths, captions, 224, 224)
