def get_feats():
train_caption_file = 'D:/download/art_desc/train/ann.csv'
eval_caption_file = 'D:/download/art_desc/val/ann.csv'
train_features_dir = 'D:/download/art_desc/train/images_vgg/'
eval_features_dir = 'D:/download/art_desc/val/images_vgg/'
image_loader = ImageLoader('./utils/ilsvrc_2012_mean.npy')
net = VGG19(weights='imagenet')
model = Model(input=net.input, output=net.get_layer('fc2').output)
with open(eval_caption_file, 'r') as f:
reader = csv.reader(f)
for id, file_name, caption in reader:
try:
img = image_loader.load_image(file_name)
fc2 = model.predict(img)
reshaped = np.reshape(fc2, (4096))
np.save(eval_features_dir + 'art_desc' + id, reshaped)
except Exception:
print("cannot identify image file:" + file_name)
pass
def get_feats(dir=False):
train_caption_file = 'D:/download/art_desc/train/ann.csv'
train_features_dir = 'D:/download/art_desc/train/images_vgg_redo/'
eval_caption_file = 'D:/download/art_desc/val/ann.csv'
#eval_image_dir = 'D:/download/art_desc/val/test_images/'
eval_image_dir = 'D:/download/art_desc/val/images_redo/'
eval_features_dir = 'D:/download/art_desc/val/images_vgg_redo/'
#eval_features_dir = 'D:/download/art_desc/val/test_vgg/'
image_loader = ImageLoader('./utils/ilsvrc_2012_mean.npy')
ignore_file = 'D:/download/art_desc/val/ignore.csv'
net = VGG19(weights='imagenet')
model = Model(input=net.input, output=net.get_layer('fc2').output)
bad_ids = []
prev_id = 0
prev_bad = False
if dir:
with open(eval_caption_file, 'r') as f: #caption file
reader = csv.reader(f)
for id, file_name, caption in reader:
try:
img = image_loader.load_image(file_name)
'''
fc2 = model.predict(img)
reshaped = np.reshape(fc2, (4096))
np.save(eval_features_dir + 'art_desc'+ str(id), reshaped)
'''
prev_bad = False
except Exception:
if id != prev_id or prev_bad is False:
print("cannot identify image file:" + file_name)
bad_ids.append(id)
prev_bad = True
prev_id = id
else:
with open(train_caption_file, 'r') as f: #caption file
reader = csv.reader(f)
for id, file_name, caption in reader:
try:
img = image_loader.load_image(file_name)
'''
fc2 = model.predict(img)
reshaped = np.reshape(fc2, (4096))
np.save(train_features_dir + 'art_desc'+ id, reshaped) #feature dir
'''
prev_bad = False
except Exception:
if id != prev_id or prev_bad is False:
print("cannot identify image file:" + file_name)
bad_ids.append(id)
prev_bad = True
prev_id = id
print("Total bad image files:%d" % len(bad_ids))
data = pd.DataFrame({'index': bad_ids})
data.to_csv(ignore_file)