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_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 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 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);
