def testSubsetFiles(meta_val_file,meta_synset_words_file,sub_val_file,sub_synset_words_file,excluded_ids_all_file,removePath):
meta_list_files_val,meta_idx_val=zip(*imagenet.readLabelsFile(meta_val_file));
meta_val_idx_mapped=[int(idx_curr) for idx_curr in meta_idx_val];
meta_val_idx_mapped=np.array(meta_val_idx_mapped);
t=time.time();
meta_ids,meta_labels=zip(*imagenet.readLabelsFile(meta_synset_words_file));
meta_ids=np.array(meta_ids);
meta_val_ids_mapped=np.empty((len(meta_list_files_val),),dtype='object');
for idx_curr in np.unique(meta_val_idx_mapped):
idx_rel=meta_val_idx_mapped==idx_curr;
meta_val_ids_mapped[idx_rel]=meta_ids[idx_curr];
meta_val_ids_mapped=list(meta_val_ids_mapped);
print time.time()-t
sub_list_files_val,sub_idx_val=zip(*imagenet.readLabelsFile(sub_val_file));
sub_val_idx_mapped=[int(idx_curr) for idx_curr in sub_idx_val];
excluded_ids_all=imagenet.readSynsetsFile(excluded_ids_all_file);
#all excluded files are excluded
check_exclude=testFilesExcludedProperly(sub_list_files_val,meta_list_files_val,meta_val_ids_mapped,excluded_ids_all)
#all included files are included
check_include=testFilesIncludedProperly(sub_list_files_val,meta_list_files_val,meta_val_ids_mapped,excluded_ids_all)
#all indices labeling is consistent
check_labeling=testFilesLabeledProperly(sub_val_idx_mapped,sub_list_files_val,meta_val_idx_mapped,meta_list_files_val)
return check_exclude,check_include,check_labeling;
def script_pascalClasses_get():
path_to_file = "../../data/ilsvrc12/synset_words.txt"
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = "/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt"
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
pascal_labels = list(zip(*pascal_ids)[1])
pascal_labels = [id_curr.strip(" ") for id_curr in pascal_labels]
pascal_labels[pascal_labels.index("dining_table")] = "diningtable"
pascal_labels[pascal_labels.index("tv/monitor")] = "tvmonitor"
pascal3d_ids = [
"boat",
"train",
"bicycle",
"chair",
"motorbike",
"aeroplane",
"sofa",
"diningtable",
"bottle",
"tvmonitor",
"bus",
"car",
]
idx_mapping = []
for id_curr in pascal3d_ids:
idx_mapping.append(pascal_labels.index(id_curr))
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids, pascal_just_ids, False)
return to_exclude
def script_writeHTMLS():
path_to_file = '../../data/ilsvrc12/synset_words.txt'
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
val_gt_file = '../../data/ilsvrc12/val.txt'
list_of_ids_im = [id for id_list in to_exclude for id in id_list]
mapping_file = '../../data/ilsvrc12/synsets.txt'
list_of_ids = imagenet.getImagenetIdToTrainingIdMapping(
mapping_file, list_of_ids_im)
print len(list_of_ids)
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids,
pascal_just_ids,
keepMapping=True)
list_of_ids_pascal = []
for id_no in range(len(to_exclude)):
list_of_ids_pascal = list_of_ids_pascal + [id_no] * len(
to_exclude[id_no])
file_text_labels = '../../data/ilsvrc12/synset_words.txt'
text_labels = np.loadtxt(file_text_labels, str, delimiter='\t')
trained_file = '/disk2/octoberExperiments/nn_performance_without_pascal/trained/20151023153522'
notrained_file = '/disk2/octoberExperiments/nn_performance_without_pascal/notrained/20151026132705'
file_pres = [trained_file, notrained_file]
layers = ['pool5', 'fc6', 'fc7']
file_names = [
file_pre + '_' + layer for file_pre in file_pres for layer in layers
]
for file_name in file_names:
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name + '.p', 'rb'))
gt_labels_pascal = [
list_of_ids_pascal[list_of_ids.index(gt_label)]
for gt_label in gt_labels
]
file_name_l = file_name + '_' + layer + '_pascal'
def preprocessImagesFromImagenet(imagenet_ids_to_test,
synset_words,
val_gt_file,
path_to_images_imagenet='',
all_files_info=None,
start_idx=1):
# class_ids=[];
ids, labels = zip(*imagenet.readLabelsFile(synset_words))
list_of_idx = [ids.index(id_curr) for id_curr in imagenet_ids_to_test]
test_set = imagenet.selectTestSetByID(val_gt_file,
list_of_idx,
path_to_val=path_to_images_imagenet)
if all_files_info is None:
all_files_info = []
for img_path, imagenet_idx in test_set:
dict_curr = {}
dict_curr['img_path'] = img_path
id_curr = ids[imagenet_idx]
dict_curr['class_idx'] = imagenet_ids_to_test.index(
id_curr) + start_idx
dict_curr['class_id'] = id_curr
dict_curr['azimuth'] = None
all_files_info.append(dict_curr)
return all_files_info
def main(): synset_words='/disk2/octoberExperiments/nn_performance_without_pascal/synset_words.txt' pascal_classes=['person','bird','cat','cow','dog','horse','sheep','aeroplane','bicycle','boat','bus','car','motorbike','train','bottle','chair','dining_table','potted_plant','sofa','tv/monitor','none'] out_dir='/disk2/novemberExperiments/network_no_pascal' out_file_to_exclude_text=os.path.join(out_dir,'to_exclude.txt'); print len(pascal_classes); ids_labels=imagenet.readLabelsFile(synset_words); print len(ids_labels); out_file=os.path.join(out_dir,'mappingImagenetToPascal.p'); mappingDict=pickle.load(open(out_file,'rb')); writeExcludedIdsFile(mappingDict,out_file_to_exclude_text) # print sum(vals=='none'),len(vals) return out_file=os.path.join(out_dir,'mappingImagenetToPascal_temp.p'); out_file_text=os.path.join(out_dir,'excluded_classes_info_temp.txt'); imagenet_labels=[x[0]+'\n'+x[1] for x in ids_labels]; sample_images=[os.path.join(out_dir,'sample_images/'+x[0]+'.JPEG') for x in ids_labels] imagenet_labels=imagenet_labels[:10]; sample_images=sample_images[:10]; window=Window(pascal_classes,imagenet_labels,sample_images,out_file=out_file); mappingDict=pickle.load(open(out_file,'rb')); writeExcludedClassInfoFile(mappingDict,out_file_text) print out_file_text
def script_setUpPascalExcludedTextFiles():
path_to_file = '../../data/ilsvrc12/synset_words.txt'
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids,
pascal_just_ids)
im_list_file = '../../data/ilsvrc12/val.txt'
mapping_file = '../../data/ilsvrc12/synsets.txt'
ims_to_keep, class_ids_to_keep, classes_to_keep = imagenet.removeImagesFromListByClass(
im_list_file, mapping_file, to_exclude)
new_file_val = '/disk2/octoberExperiments/nn_performance_without_pascal/val.txt'
classes_uni_val = writeNewDataClassFile(new_file_val,
zip(ims_to_keep, classes_to_keep))
im_list_file = '../../data/ilsvrc12/train.txt'
ims_to_keep, class_ids_to_keep, classes_to_keep = imagenet.removeImagesFromListByClass(
im_list_file, mapping_file, to_exclude)
new_file_val = '/disk2/octoberExperiments/nn_performance_without_pascal/train.txt'
classes_uni_train = imagenet.writeNewDataClassFile(
new_file_val, zip(ims_to_keep, classes_to_keep))
assert (str(classes_uni_val) == str(classes_uni_train))
class_file = '/disk2/octoberExperiments/nn_performance_without_pascal/synsets.txt'
with open(class_file, 'wb') as f:
for class_id in classes_uni_train:
f.write(class_id + '\n')
with open(new_file_val, 'rb') as f:
content = f.read()
#sanity check
for id_to_exclude in to_exclude:
if id_to_exclude in content:
print 'FOUND ERROR', id_to_exclude
def testSubsetFiles(meta_val_file, meta_synset_words_file, sub_val_file,
sub_synset_words_file, excluded_ids_all_file, removePath):
meta_list_files_val, meta_idx_val = zip(
*imagenet.readLabelsFile(meta_val_file))
meta_val_idx_mapped = [int(idx_curr) for idx_curr in meta_idx_val]
meta_val_idx_mapped = np.array(meta_val_idx_mapped)
t = time.time()
meta_ids, meta_labels = zip(
*imagenet.readLabelsFile(meta_synset_words_file))
meta_ids = np.array(meta_ids)
meta_val_ids_mapped = np.empty((len(meta_list_files_val), ),
dtype='object')
for idx_curr in np.unique(meta_val_idx_mapped):
idx_rel = meta_val_idx_mapped == idx_curr
meta_val_ids_mapped[idx_rel] = meta_ids[idx_curr]
meta_val_ids_mapped = list(meta_val_ids_mapped)
print time.time() - t
sub_list_files_val, sub_idx_val = zip(
*imagenet.readLabelsFile(sub_val_file))
sub_val_idx_mapped = [int(idx_curr) for idx_curr in sub_idx_val]
excluded_ids_all = imagenet.readSynsetsFile(excluded_ids_all_file)
#all excluded files are excluded
check_exclude = testFilesExcludedProperly(sub_list_files_val,
meta_list_files_val,
meta_val_ids_mapped,
excluded_ids_all)
#all included files are included
check_include = testFilesIncludedProperly(sub_list_files_val,
meta_list_files_val,
meta_val_ids_mapped,
excluded_ids_all)
#all indices labeling is consistent
check_labeling = testFilesLabeledProperly(sub_val_idx_mapped,
sub_list_files_val,
meta_val_idx_mapped,
meta_list_files_val)
return check_exclude, check_include, check_labeling
def script_printExcludedInfoFile():
path_to_file = '../../data/ilsvrc12/synset_words.txt'
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids,
pascal_just_ids,
keepMapping=True)
f_info = '/disk2/octoberExperiments/nn_performance_without_pascal/excluded_classes_info.txt'
with open(f_info, 'wb') as f:
for idx, to_exclude_curr in enumerate(to_exclude):
f.write(str(pascal_ids[idx]) + '\n')
for to_exclude_id in to_exclude_curr:
f.write(to_exclude_id + ' ' +
val_just_labels[val_just_ids.index(to_exclude_id)] +
'\n')
f.write('___' + '\n')
def script_setUpFilesForTrainingOnSubset(params):
parent_synset_words_file = params.parent_synset_words_file
parent_val_file = params.parent_val_file
parent_train_file = params.parent_train_file
parent_synset_file = params.parent_synset_file
new_val_file = params.new_val_file
new_train_file = params.new_train_file
new_synset_file = params.new_synset_file
new_synset_words_file = params.new_synset_words_file
to_exclude_text_file = params.to_exclude_text_file
val_ids = imagenet.readLabelsFile(parent_synset_words_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
with open(to_exclude_text_file, "rb") as f:
to_exclude = f.readlines()
to_exclude = [to_exclude_curr.strip("\n") for to_exclude_curr in to_exclude]
ims_to_keep, class_ids_to_keep, classes_to_keep = imagenet.removeImagesFromListByClass(
parent_val_file, parent_synset_file, to_exclude
)
classes_uni_val = imagenet.writeNewDataClassFile(new_val_file, zip(ims_to_keep, classes_to_keep))
ims_to_keep, class_ids_to_keep, classes_to_keep = imagenet.removeImagesFromListByClass(
parent_train_file, parent_synset_file, to_exclude
)
classes_uni_train = imagenet.writeNewDataClassFile(new_train_file, zip(ims_to_keep, classes_to_keep))
assert str(classes_uni_val) == str(classes_uni_train)
with open(new_synset_file, "wb") as f:
for class_id in classes_uni_train:
f.write(class_id + "\n")
with open(new_synset_words_file, "wb") as f:
for class_id in classes_uni_train:
f.write(class_id + " " + val_just_labels[val_just_ids.index(class_id)] + "\n")
with open(new_synset_file, "rb") as f:
content = f.read()
# sanity check
for id_to_exclude in to_exclude:
if id_to_exclude in content:
print "FOUND ERROR", id_to_exclude
def preprocessImagesFromImagenet(imagenet_ids_to_test,synset_words,val_gt_file,path_to_images_imagenet='',all_files_info=None,start_idx=1):
# class_ids=[];
ids,labels=zip(*imagenet.readLabelsFile(synset_words));
list_of_idx=[ids.index(id_curr) for id_curr in imagenet_ids_to_test];
test_set=imagenet.selectTestSetByID(val_gt_file,list_of_idx,path_to_val=path_to_images_imagenet)
if all_files_info is None:
all_files_info=[];
for img_path,imagenet_idx in test_set:
dict_curr={}
dict_curr['img_path']=img_path;
id_curr=ids[imagenet_idx];
dict_curr['class_idx']=imagenet_ids_to_test.index(id_curr)+start_idx;
dict_curr['class_id']=id_curr;
dict_curr['azimuth']=None;
all_files_info.append(dict_curr);
return all_files_info
def script_runNNOnPascalExcludedInTraining():
path_to_file = '../../data/ilsvrc12/synset_words.txt'
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids,
pascal_just_ids,
keepMapping=True)
val_gt_file = '../../data/ilsvrc12/val.txt'
list_of_ids_im = [id for id_list in to_exclude for id in id_list]
mapping_file = '../../data/ilsvrc12/synsets.txt'
print len(list_of_ids_im)
list_of_ids, _ = imagenet.getImagenetIdToTrainingIdMapping(
mapping_file, list_of_ids_im)
print len(list_of_ids)
# print list_of_ids[0]
list_of_ids_pascal = []
for id_no in range(len(to_exclude)):
list_of_ids_pascal = list_of_ids_pascal + [id_no] * len(
to_exclude[id_no])
path_to_val = '/disk2/imagenet/val'
test_set = imagenet.selectTestSetByID(val_gt_file, list_of_ids,
path_to_val)
# out_dir='/disk2/octoberExperiments/nn_performance_without_pascal/notrained'
out_dir = '/disk2/novemberExperiments/nn_imagenet_top5/trained'
if not os.path.exists(out_dir):
os.mkdir(out_dir)
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'
modelFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'
deployFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/deploy.prototxt'
meanFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/python/caffe/imagenet/ilsvrc_2012_mean.npy'
# modelFile='/disk2/novemberExperiments/network_no_pascal/snapshots/snapshot_iter_450000.caffemodel';
# deployFile='/disk2/novemberExperiments/network_no_pascal/deploy.prototxt';
# meanFile='/disk2/novemberExperiments/network_no_pascal/mean.npy';
# out_file=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers,deployFile=deployFile,meanFile=meanFile,modelFile=modelFile)
# return
# file_name='/disk2/octoberExperiments/nn_performance_without_pascal/notrained/20151026132705'
# file_name='/disk2/novemberExperiments/nn_imagenet_top5/notrained/20151130193757';
file_name = '/disk2/novemberExperiments/nn_imagenet_top5/trained/20151130230243'
file_text_labels = '../../data/ilsvrc12/synset_words.txt'
text_labels = np.loadtxt(file_text_labels, str, delimiter='\t')
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])
gt_labels_pascal = [
list_of_ids_pascal[list_of_ids.index(gt_label)]
for gt_label in gt_labels
]
for layer in layers:
print layer
file_name_l = file_name + '_' + layer
indices = script_nearestNeigbourExperiment.doNN(img_paths,
gt_labels,
vals[layer],
numberOfN=numberOfN,
distance='cosine',
algo='brute')
conf_matrix = 0
pickle.dump([img_paths, gt_labels, indices, conf_matrix],
open(file_name_l + '.p', 'wb'))
file_text_labels_pascal = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
text_labels_pascal = np.loadtxt(file_text_labels_pascal,
str,
delimiter='\t')
for layer in layers:
print layer
file_name_l = file_name + '_' + layer
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
img_paths_curr = [
x.replace(relativePaths[0], relativePaths[1]) for x in img_paths
]
im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid(
img_paths_curr, gt_labels, indices, text_labels)
script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html',
im_paths, captions)
no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches(
indices, gt_labels)
print no_correct
with open(file_name_l + '.txt', 'wb') as f:
for no_correct_curr in no_correct:
f.write(str(no_correct_curr) + ' ')
file_name_l = file_name + '_' + layer + '_pascal'
im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid(
img_paths_curr, gt_labels_pascal, indices, text_labels_pascal)
script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html',
im_paths, captions)
no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches(
indices, gt_labels_pascal)
with open(file_name_l + '.txt', 'wb') as f:
for no_correct_curr in no_correct:
f.write(str(no_correct_curr) + ' ')
print no_correct
def script_runNNOnPascalIncludedInTraining():
path_to_file = '../../data/ilsvrc12/synset_words.txt'
val_ids = imagenet.readLabelsFile(path_to_file)
val_just_ids = list(zip(*val_ids)[0])
val_just_labels = list(zip(*val_ids)[1])
pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
pascal_ids = imagenet.readLabelsFile(pascal_ids_file)
pascal_just_ids = list(zip(*pascal_ids)[0])
to_exclude = imagenet.removeClassesWithOverlap(val_just_ids,
pascal_just_ids,
keepMapping=True)
val_gt_file = '../../data/ilsvrc12/val.txt'
list_of_ids_im = [id for id_list in to_exclude for id in id_list]
mapping_file = '../../data/ilsvrc12/synsets.txt'
list_of_ids = imagenet.getImagenetIdToTrainingIdMapping(
mapping_file, list_of_ids_im)
print len(list_of_ids)
list_of_ids_pascal = []
for id_no in range(len(to_exclude)):
list_of_ids_pascal = list_of_ids_pascal + [id_no] * len(
to_exclude[id_no])
path_to_val = '/disk2/imagenet/val'
test_set = imagenet.selectTestSetByID(val_gt_file, list_of_ids,
path_to_val)
out_dir = '/disk2/octoberExperiments/nn_performance_without_pascal/trained'
layers = ['pool5', 'fc6', 'fc7']
gpu_no = 0
path_to_classify = '..'
numberOfN = 5
relativePaths = ['/disk2', '../../../..']
# out_file=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers)
file_name = '/disk2/octoberExperiments/nn_performance_without_pascal/trained/20151023153522'
file_text_labels = '../../data/ilsvrc12/synset_words.txt'
text_labels = np.loadtxt(file_text_labels, str, delimiter='\t')
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])
gt_labels_pascal = [
list_of_ids_pascal[list_of_ids.index(gt_label)]
for gt_label in gt_labels
]
# for layer in layers:
# file_name_l=file_name+'_'+layer;
# indices,conf_matrix=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'));
file_text_labels_pascal = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt'
text_labels_pascal = np.loadtxt(file_text_labels_pascal,
str,
delimiter='\t')
for layer in layers:
print layer
file_name_l = file_name + '_' + layer
[img_paths, gt_labels, indices,
_] = pickle.load(open(file_name_l + '.p', 'rb'))
img_paths_curr = [
x.replace(relativePaths[0], relativePaths[1]) for x in img_paths
]
im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid(
img_paths_curr, gt_labels, indices, text_labels)
script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html',
im_paths, captions)
no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches(
indices, gt_labels)
print no_correct
with open(file_name_l + '.txt', 'wb') as f:
for no_correct_curr in no_correct:
f.write(str(no_correct_curr) + ' ')
file_name_l = file_name + '_' + layer + '_pascal'
im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid(
img_paths_curr, gt_labels_pascal, indices, text_labels_pascal)
script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html',
im_paths, captions)
no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches(
indices, gt_labels_pascal)
with open(file_name_l + '.txt', 'wb') as f:
for no_correct_curr in no_correct:
f.write(str(no_correct_curr) + ' ')
print no_correct
def main():
# in_file='/disk2/temp/small_set.txt';
path_to_val = "/disk2/imagenet/val"
# val_gt_file='../../data/ilsvrc12/val.txt'
# synset_words='../../data/ilsvrc12/synset_words.txt'
# deploy_file='../../models/bvlc_reference_caffenet/deploy.prototxt';
# model_file='../../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel';
# mean_file='../../python/caffe/imagenet/ilsvrc_2012_mean.npy';
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/val_performance_top5_trained.p';
val_gt_file = "/disk2/octoberExperiments/nn_performance_without_pascal/val.txt"
synset_words = "/disk2/octoberExperiments/nn_performance_without_pascal/synset_words.txt"
deploy_file = "/disk2/octoberExperiments/nn_performance_without_pascal/deploy.prototxt"
model_file = "/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel"
mean_file = "/disk2/octoberExperiments/nn_performance_without_pascal/mean.npy"
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/new_val_performance_top5_no_trained.p';
val_gt = imagenet.readLabelsFile(val_gt_file)
im_files = list(zip(*val_gt)[0])
im_files = [os.path.join(path_to_val, im_file) for im_file in im_files]
im_files = im_files[:200]
imagenet_idx_mapped = list(zip(*val_gt)[1])
imagenet_idx_mapped = [int(x) for x in imagenet_idx_mapped]
batch_size = 1000
top_n = 5
gpu_no = 1
getClasses = True
net, transformer = setUpNet(model_file, deploy_file, mean_file, gpu_no)
out_file = "temp"
in_file_text = "temp.txt"
with open(in_file_text, "wb") as f:
for im_file in im_files:
f.write(im_file + "\n")
layers = ["fc7"]
saveLayers(net, transformer, in_file_text, layers, out_file)
vals = np.load(out_file + ".npz")
print vals.keys()
for k in vals.keys():
print k, vals[k].shape
# error_bin,pred_classes=getTopNError(net,transformer,im_files,imagenet_idx_mapped,batch_size,top_n,printDebug=True,pred_classes=True)
# print sum(error_bin),len(error_bin)
# print pred_classes[:10]
# pickle.dump([error_bin,pred_classes],open(out_file_topk,'wb'));
return
db_path = "sqlite://///disk2/novemberExperiments/nn_imagenet/nn_imagenet.db"
all_pascal_id = [
"boat",
"train",
"bicycle",
"chair",
"motorbike",
"aeroplane",
"sofa",
"diningtable",
"bottle",
"tvmonitor",
"bus",
"car",
]
batch_size = 1000
top_n = 1
gpu_no = 1
getClasses = True
ids_labels = imagenet.readLabelsFile(synset_words)
labels = list(zip(*ids_labels)[1])
imagenet_ids = list(zip(*ids_labels)[0])
net, transformer = setUpNet(model_file, deploy_file, mean_file, gpu_no)
for pascal_id in ["car"]:
# all_pascal_id:
print pascal_id
out_file_topk = "/disk2/novemberExperiments/nn_imagenet/" + pascal_id + "_pred_no_train.p"
out_file_topk_txt = "/disk2/novemberExperiments/nn_imagenet/" + pascal_id + "_pred_no_train.txt"
mani = Imagenet_Manipulator(db_path)
mani.openSession()
criterion = (Imagenet.class_id_pascal == pascal_id,)
vals = mani.select((Imagenet.img_path,), criterion, distinct=True)
mani.closeSession()
im_files = [val[0] for val in vals]
imagenet_idx_mapped = [772] * len(im_files)
print len(im_files)
# return
# error_bin=pickle.load(open(out_file_topk,'rb'));
# print sum(error_bin),len(error_bin),sum(error_bin)/float(len(error_bin))
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/val_performance_top5_trained.p';
# error_bin=pickle.load(open(out_file_topk,'rb'));
# print sum(error_bin),len(error_bin),sum(error_bin)/float(len(error_bin))
# return
# val_gt=imagenet.readLabelsFile(val_gt_file);
# im_files=list(zip(*val_gt)[0]);
# im_files=[os.path.join(path_to_val,im_file) for im_file in im_files]
# imagenet_idx_mapped=list(zip(*val_gt)[1])
# imagenet_idx_mapped=[int(x) for x in imagenet_idx_mapped];
# print idx_mapped_simple[:10],len(idx_mapped_simple);
# print 'getting mapping'
# imagenet_idx_mapped,imagenet_ids_mapped,imagenet_labels_mapped=imagenet.getMappingInfo(im_files,synset_words,val_gt_file)
# print imagenet_idx_mapped[:10],len(imagenet_idx_mapped),type(imagenet_idx_mapped),type(imagenet_idx_mapped[0]),type(idx_mapped_simple),type(idx_mapped_simple[0])
# for idx_idx,idx in enumerate(idx_mapped_simple):
# print idx,imagenet_idx_mapped[idx_idx]
# assert idx==imagenet_idx_mapped[idx_idx]
# return
error_bin, pred_classes = getTopNError(
net, transformer, im_files, imagenet_idx_mapped, batch_size, top_n, printDebug=True, pred_classes=True
)
print sum(error_bin), len(error_bin)
print pred_classes[:10]
pickle.dump([error_bin, pred_classes], open(out_file_topk, "wb"))
pred_classes = pred_classes.ravel()
tuples = []
for class_curr in np.unique(pred_classes):
# print imagenet_ids[class_curr],labels[class_curr];
tuples.append((class_curr, labels[class_curr], sum(pred_classes == class_curr) / float(len(pred_classes))))
tuples = sorted(tuples, key=lambda x: x[2])[::-1]
with open(out_file_topk_txt, "wb") as f:
for tuple_curr in tuples:
print imagenet_ids[tuple_curr[0]], tuple_curr
f.write(str(tuple_curr[0]) + "\t" + str(tuple_curr[1]) + "\t" + str(round(tuple_curr[2] * 100, 2)))
f.write("\n")
def main():
# in_file='/disk2/temp/small_set.txt';
path_to_val = '/disk2/imagenet/val'
# val_gt_file='../../data/ilsvrc12/val.txt'
# synset_words='../../data/ilsvrc12/synset_words.txt'
# deploy_file='../../models/bvlc_reference_caffenet/deploy.prototxt';
# model_file='../../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel';
# mean_file='../../python/caffe/imagenet/ilsvrc_2012_mean.npy';
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/val_performance_top5_trained.p';
val_gt_file = '/disk2/octoberExperiments/nn_performance_without_pascal/val.txt'
synset_words = '/disk2/octoberExperiments/nn_performance_without_pascal/synset_words.txt'
deploy_file = '/disk2/octoberExperiments/nn_performance_without_pascal/deploy.prototxt'
model_file = '/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel'
mean_file = '/disk2/octoberExperiments/nn_performance_without_pascal/mean.npy'
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/new_val_performance_top5_no_trained.p';
val_gt = imagenet.readLabelsFile(val_gt_file)
im_files = list(zip(*val_gt)[0])
im_files = [os.path.join(path_to_val, im_file) for im_file in im_files]
im_files = im_files[:200]
imagenet_idx_mapped = list(zip(*val_gt)[1])
imagenet_idx_mapped = [int(x) for x in imagenet_idx_mapped]
batch_size = 1000
top_n = 5
gpu_no = 1
getClasses = True
net, transformer = setUpNet(model_file, deploy_file, mean_file, gpu_no)
out_file = 'temp'
in_file_text = 'temp.txt'
with open(in_file_text, 'wb') as f:
for im_file in im_files:
f.write(im_file + '\n')
layers = ['fc7']
saveLayers(net, transformer, in_file_text, layers, out_file)
vals = np.load(out_file + '.npz')
print vals.keys()
for k in vals.keys():
print k, vals[k].shape
# error_bin,pred_classes=getTopNError(net,transformer,im_files,imagenet_idx_mapped,batch_size,top_n,printDebug=True,pred_classes=True)
# print sum(error_bin),len(error_bin)
# print pred_classes[:10]
# pickle.dump([error_bin,pred_classes],open(out_file_topk,'wb'));
return
db_path = 'sqlite://///disk2/novemberExperiments/nn_imagenet/nn_imagenet.db'
all_pascal_id = [
'boat', 'train', 'bicycle', 'chair', 'motorbike', 'aeroplane', 'sofa',
'diningtable', 'bottle', 'tvmonitor', 'bus', 'car'
]
batch_size = 1000
top_n = 1
gpu_no = 1
getClasses = True
ids_labels = imagenet.readLabelsFile(synset_words)
labels = list(zip(*ids_labels)[1])
imagenet_ids = list(zip(*ids_labels)[0])
net, transformer = setUpNet(model_file, deploy_file, mean_file, gpu_no)
for pascal_id in ['car']:
# all_pascal_id:
print pascal_id
out_file_topk = '/disk2/novemberExperiments/nn_imagenet/' + pascal_id + '_pred_no_train.p'
out_file_topk_txt = '/disk2/novemberExperiments/nn_imagenet/' + pascal_id + '_pred_no_train.txt'
mani = Imagenet_Manipulator(db_path)
mani.openSession()
criterion = (Imagenet.class_id_pascal == pascal_id, )
vals = mani.select((Imagenet.img_path, ), criterion, distinct=True)
mani.closeSession()
im_files = [val[0] for val in vals]
imagenet_idx_mapped = [772] * len(im_files)
print len(im_files)
# return
# error_bin=pickle.load(open(out_file_topk,'rb'));
# print sum(error_bin),len(error_bin),sum(error_bin)/float(len(error_bin))
# out_file_topk='/disk2/octoberExperiments/nn_performance_without_pascal/val_performance_top5_trained.p';
# error_bin=pickle.load(open(out_file_topk,'rb'));
# print sum(error_bin),len(error_bin),sum(error_bin)/float(len(error_bin))
# return
# val_gt=imagenet.readLabelsFile(val_gt_file);
# im_files=list(zip(*val_gt)[0]);
# im_files=[os.path.join(path_to_val,im_file) for im_file in im_files]
# imagenet_idx_mapped=list(zip(*val_gt)[1])
# imagenet_idx_mapped=[int(x) for x in imagenet_idx_mapped];
# print idx_mapped_simple[:10],len(idx_mapped_simple);
# print 'getting mapping'
# imagenet_idx_mapped,imagenet_ids_mapped,imagenet_labels_mapped=imagenet.getMappingInfo(im_files,synset_words,val_gt_file)
# print imagenet_idx_mapped[:10],len(imagenet_idx_mapped),type(imagenet_idx_mapped),type(imagenet_idx_mapped[0]),type(idx_mapped_simple),type(idx_mapped_simple[0])
# for idx_idx,idx in enumerate(idx_mapped_simple):
# print idx,imagenet_idx_mapped[idx_idx]
# assert idx==imagenet_idx_mapped[idx_idx]
# return
error_bin, pred_classes = getTopNError(net,
transformer,
im_files,
imagenet_idx_mapped,
batch_size,
top_n,
printDebug=True,
pred_classes=True)
print sum(error_bin), len(error_bin)
print pred_classes[:10]
pickle.dump([error_bin, pred_classes], open(out_file_topk, 'wb'))
pred_classes = pred_classes.ravel()
tuples = []
for class_curr in np.unique(pred_classes):
# print imagenet_ids[class_curr],labels[class_curr];
tuples.append(
(class_curr, labels[class_curr],
sum(pred_classes == class_curr) / float(len(pred_classes))))
tuples = sorted(tuples, key=lambda x: x[2])[::-1]
with open(out_file_topk_txt, 'wb') as f:
for tuple_curr in tuples:
print imagenet_ids[tuple_curr[0]], tuple_curr
f.write(
str(tuple_curr[0]) + '\t' + str(tuple_curr[1]) + '\t' +
str(round(tuple_curr[2] * 100, 2)))
f.write('\n')
