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 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