def get_training_batch(self,
batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
real_images = []
wrong_images = []
acoustic_features = []
z_noise = []
image_files = []
for i in range(batch_no * batch_size,
batch_no * batch_size + batch_size):
idx = i % len(loaded_data["image_list"])
real_images.append(
image_processing.load_image_array(
loaded_data["image_list"][idx], image_size))
wrong_images.append(
image_processing.load_image_array(
loaded_data["image_list"][random.randint(
0,
len(loaded_data["image_list"]) - 1)], image_size))
filename = loaded_data["image_list"][idx].split('/')[-1].split(
'.')[0]
acoustic_features.append(
np.load(self.feat_path + filename + ".npy"))
z_noise.append(np.random.uniform(-1, 1, [z_dim]))
image_files.append(filename)
return np.array(real_images), np.array(wrong_images), np.array(
acoustic_features), np.array(z_noise), image_files
def get_training_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, split, data_dir, data_set, loaded_data = None):
if data_set == 'flowers':
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
#caption_text = [None]*batch_size
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir, 'flowers/jpg/'+loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt,:,:,:] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0,len(loaded_data['image_list'])-1)
wrong_image_file = join(data_dir, 'flowers/jpg/'+loaded_data['image_list'][wrong_image_id])
wrong_image_array = image_processing.load_image_array(wrong_image_file, image_size)
wrong_images[cnt, :,:,:] = wrong_image_array
random_caption = random.randint(0,4)
#caption_text[i] = random_caption
captions[cnt,:] = loaded_data['captions'][ loaded_data['image_list'][idx] ][ random_caption ][0:caption_vector_length]
image_files.append( image_file )
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files#, caption_text
def get_training_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, split, method_dir, imgs_dir,
data_set, loaded_data):
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_set, imgs_dir, loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt, :, :, :] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0, len(loaded_data['image_list']) - 1)
wrong_image_file = join(data_set, imgs_dir,
loaded_data['image_list'][wrong_image_id])
wrong_image_array = image_processing.load_image_array(
wrong_image_file, image_size)
wrong_images[cnt, :, :, :] = wrong_image_array
captions[cnt,:] = loaded_data\
['captions'][loaded_data['image_list'][idx]][0][:caption_vector_length]
image_files.append(image_file)
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files
def get_training_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, image_dir, loaded_data):
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
class_name, image_file_name = loaded_data['image_list'][idx]
processed_img_dir = os.path.join(image_dir, class_name)
image_file = join(processed_img_dir, image_file_name)
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt, :, :, :] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0, len(loaded_data['image_list']) - 1)
wrong_class_name, wrong_image_file_name = loaded_data['image_list'][
wrong_image_id]
wrong_processed_img_dir = os.path.join(image_dir, wrong_class_name)
wrong_image_file = join(wrong_processed_img_dir, wrong_image_file_name)
wrong_image_array = image_processing.load_image_array(
wrong_image_file, image_size)
wrong_images[cnt, :, :, :] = wrong_image_array
random_caption = random.randint(0, 4)
captions[cnt, :] = loaded_data['captions'][image_file_name][
random_caption][0:caption_vector_length]
image_files.append(image_file)
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files
def get_training_batch(self, batch_no, batch_size, image_size, z_dim, caption_vector_length, split, data_dir, data_set, loaded_data = None):
real_images = []
wrong_images = []
acoustic_features = []
z_noise = []
class_labels = []
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
#idx = i % len(loaded_data["image_list"])
place_or_object_id = random.randint(0, len(loaded_data["image_list"])-1)
image_index = random.randint(0, len(loaded_data["image_list"][place_or_object_id])-1)
real_images.append(image_processing.load_image_array(loaded_data["image_list"][place_or_object_id][image_index], image_size))
different_place_or_object_id = random.randint(0, len(loaded_data["image_list"])-1)
while different_place_or_object_id == place_or_object_id:
different_place_or_object_id = random.randint(0, len(loaded_data["image_list"])-1)
wrong_images.append(image_processing.load_image_array(loaded_data["image_list"][different_place_or_object_id][random.randint(0, len(loaded_data["image_list"][different_place_or_object_id])-1)], image_size))
filename = loaded_data["image_list"][place_or_object_id][image_index].split('/')[-1].split('.')[0].split('_')[0]
feat_index = random.randint(0, len(self.feat_path_filelist[place_or_object_id])-1)
if self.add_noise == False:
acoustic_features.append(np.load(self.feat_path_list[place_or_object_id] + self.feat_path_filelist[place_or_object_id][feat_index]))
elif self.add_noise == True:
feat = np.load(self.feat_path_list[place_or_object_id] + self.feat_path_filelist[place_or_object_id][feat_index])
acoustic_features.append(feat + np.random.normal(scale=0.01, size=[caption_vector_length]))
#z_noise.append(np.random.uniform(-1, 1, [z_dim]))
z_noise.append(np.random.normal(scale=0.01, size=[z_dim]))
class_label = np.zeros(self.num_class)
class_label[place_or_object_id] = 1
class_labels.append(class_label)
image_files.append(filename)
return np.array(real_images), np.array(wrong_images), np.array(acoustic_features), np.array(z_noise), np.array(class_labels), image_files
def get_training_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, split, data_dir, data_set, loaded_data = None):
if data_set == 'mscoco':
with h5py.File( join(data_dir, 'tvs/'+split + '_tvs_' + str(batch_no))) as hf:
caption_vectors = np.array(hf.get('tv'))
caption_vectors = caption_vectors[:,0:caption_vector_length]
with h5py.File( join(data_dir, 'tvs/'+split + '_tv_image_id_' + str(batch_no))) as hf:
image_ids = np.array(hf.get('tv'))
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
image_files = []
for idx, image_id in enumerate(image_ids):
image_file = join(data_dir, '%s2014/COCO_%s2014_%.12d.jpg'%(split, split, image_id) )
image_array = image_processing.load_image_array(image_file, image_size)
real_images[idx,:,:,:] = image_array
image_files.append(image_file)
# TODO>> As of Now, wrong images are just shuffled real images.
first_image = real_images[0,:,:,:]
for i in range(0, batch_size):
if i < batch_size - 1:
wrong_images[i,:,:,:] = real_images[i+1,:,:,:]
else:
wrong_images[i,:,:,:] = first_image
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, caption_vectors, z_noise, image_files
if data_set == 'faces':
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir, 'faces/jpg/'+loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt,:,:,:] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0,len(loaded_data['image_list'])-1)
wrong_image_file = join(data_dir, 'faces/jpg/'+loaded_data['image_list'][wrong_image_id])
wrong_image_array = image_processing.load_image_array(wrong_image_file, image_size)
wrong_images[cnt, :,:,:] = wrong_image_array
random_caption = random.randint(0,4)
captions[cnt,:] = loaded_data['captions'][ loaded_data['image_list'][idx] ][ random_caption ][0:caption_vector_length]
image_files.append( image_file )
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files
def get_training_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, split, data_dir, data_set, loaded_data = None):
if data_set == 'mscoco':
with h5py.File( join(data_dir, 'tvs/'+split + '_tvs_' + str(batch_no))) as hf:
caption_vectors = np.array(hf.get('tv'))
caption_vectors = caption_vectors[:,0:caption_vector_length]
with h5py.File( join(data_dir, 'tvs/'+split + '_tv_image_id_' + str(batch_no))) as hf:
image_ids = np.array(hf.get('tv'))
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
image_files = []
for idx, image_id in enumerate(image_ids):
image_file = join(data_dir, '%s2014/COCO_%s2014_%.12d.jpg'%(split, split, image_id) )
image_array = image_processing.load_image_array(image_file, image_size)
real_images[idx,:,:,:] = image_array
image_files.append(image_file)
# TODO>> As of Now, wrong images are just shuffled real images.
first_image = real_images[0,:,:,:]
for i in range(0, batch_size):
if i < batch_size - 1:
wrong_images[i,:,:,:] = real_images[i+1,:,:,:]
else:
wrong_images[i,:,:,:] = first_image
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, caption_vectors, z_noise, image_files
if data_set == 'flowers':
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir, 'flowers/jpg/'+loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt,:,:,:] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0,len(loaded_data['image_list'])-1)
wrong_image_file = join(data_dir, 'flowers/jpg/'+loaded_data['image_list'][wrong_image_id])
wrong_image_array = image_processing.load_image_array(wrong_image_file, image_size)
wrong_images[cnt, :,:,:] = wrong_image_array
random_caption = random.randint(0,4)
captions[cnt,:] = loaded_data['captions'][ loaded_data['image_list'][idx] ][ random_caption ][0:caption_vector_length]
image_files.append( image_file )
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files
def get_augment_batch(image_size, data_dir, batch_no, augment_batch_size, loaded_data, image_captions):
real_images = np.zeros((augment_batch_size, 64, 64, 3))
text_captions = []
cnt = 0
for i in range(batch_no * augment_batch_size, batch_no * augment_batch_size + augment_batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir, 'augment/'+ loaded_data['image_list'][idx])
ugly = 1
while(ugly):
try:
image_array = image_processing.load_image_array(image_file, image_size)
if image_array.shape[2] != 3:
print('image file wrong number of channels. Deleting at :', image_file)
os.remove(image_file)
image_file = join(data_dir, 'augment/' +
loaded_data['image_list'][np.random.randint(1,len(loaded_data['image_list'])-1)])
continue
ugly=0
except:
print('image file broken at :', image_file)
image_file = join(data_dir, 'augment/' +
loaded_data['image_list'][np.random.randint(1,len(loaded_data['image_list'])-1)])
real_images[cnt,:,:,:] = image_array
text_captions.append(image_captions[loaded_data['image_list'][idx]])
cnt += 1
return text_captions, real_images
def get_coco_batch(image_size, dataDir, dataType, coco, coco_caps,
coco_batch_size, imgIds):
coco_real_images = np.zeros((coco_batch_size, 64, 64, 3))
coco_wrong_images = np.zeros((coco_batch_size, 64, 64, 3))
coco_ann = []
ann_temp = []
image_files = []
for idx in range(coco_batch_size):
img = coco.loadImgs(imgIds[np.random.randint(0, len(imgIds))])[0]
image_file = '%s/%s/%s' % (dataDir, dataType, img['file_name'])
image_array = image_processing.load_image_array(image_file, image_size)
annIds = coco_caps.getAnnIds(imgIds=img['id'])
anns = coco_caps.loadAnns(annIds)
#coco_ann.append(coco_caps.showAnns(anns))
coco_real_images[idx, :, :, :] = image_array
for i in anns:
ann_temp.append(i['caption'])
coco_ann.append(ann_temp)
ann_temp = []
image_files.append(image_file)
first_image = coco_real_images[0, :, :, :]
for i in range(0, coco_batch_size):
if i < coco_batch_size - 1:
coco_wrong_images[i, :, :, :] = coco_real_images[i + 1, :, :, :]
else:
coco_wrong_images[i, :, :, :] = first_image
return coco_ann, coco_real_images, coco_wrong_images, image_files
def save_for_viz_val(data_dir, generated_images, image_files, image_caps,
image_ids, image_size, id):
generated_images = np.squeeze(np.array(generated_images))
for i in range(0, generated_images.shape[0]):
image_dir = join(data_dir, str(image_ids[i]))
if not os.path.exists(image_dir):
os.makedirs(image_dir)
real_image_path = join(image_dir, '{}.tif'.format(image_ids[i]))
if os.path.exists(image_dir):
real_images_255 = image_processing.load_image_array(image_files[i],
image_size,
image_ids[i],
mode='val')
imageio.imwrite(real_image_path, real_images_255)
caps_dir = join(image_dir, "caps.txt")
if not os.path.exists(caps_dir):
with open(caps_dir, "w") as text_file:
text_file.write(image_caps[i] + "\n")
fake_images_255 = generated_images[i]
imageio.imwrite(join(image_dir, 'fake_image_{}.tif'.format(id)),
fake_images_255)
def get_test_batch(batch_no, batch_size, image_size, z_dim,
caption_vector_length, data_dir, data_set, loaded_data = None):
if data_set == 'shapes':
real_images = np.zeros((batch_size, 64, 64, 3))
#wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
#image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
#for i in range(num_images):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir, 'shapes/images/'+loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt,:,:,:] = image_array
# Improve this selection of wrong image
#wrong_image_id = random.randint(0,len(loaded_data['image_list'])-1)
#wrong_image_file = join(data_dir, 'shapes/images/'+loaded_data['image_list'][wrong_image_id])
#wrong_image_array = image_processing.load_image_array(wrong_image_file, image_size)
#wrong_images[cnt, :,:,:] = wrong_image_array
random_caption = random.randint(0,4)
captions[cnt,:] = loaded_data['captions'][ loaded_data['image_list'][idx] ][ random_caption ][0:caption_vector_length]
#image_files.append( image_file )
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, captions, z_noise
def get_flower_batch(image_size, data_dir, batch_no, flower_batch_size,
loaded_data, image_captions):
real_images = np.zeros((flower_batch_size, 64, 64, 3))
wrong_images = np.zeros((flower_batch_size, 64, 64, 3))
captions = np.zeros((flower_batch_size, 556))
text_captions = []
cnt = 0
image_files = []
for i in range(batch_no * flower_batch_size,
batch_no * flower_batch_size + flower_batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir,
'flowers/jpg/' + loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt, :, :, :] = image_array
ann_idx = random.randint(0, 4)
#image_captions['image_02267.jpg']
text_captions.append(
image_captions[loaded_data['image_list'][idx]][ann_idx])
# Improve this selection of wrong image
random_caption = random.randint(0, 4)
#captions[cnt,:] = loaded_data['captions'][loaded_data['image_list'][idx]][ random_caption ][0: 100]
image_files.append(image_file)
cnt += 1
#z_noise = np.random.uniform(-1, 1, [flower_batch_size, z_dim])
#return real_images, wrong_images, captions, z_noise, image_files
return text_captions, real_images
def get_training_batch(batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
captions = np.zeros((batch_size, caption_vector_length))
cnt = 0
image_files = []
for i in range(batch_no * batch_size, batch_no * batch_size + batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(
data_dir, 'faces/jpg/' + loaded_data['image_list'][idx] + '.jpg')
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt, :, :, :] = image_array
# Improve this selection of wrong image
wrong_image_id = random.randint(0, len(loaded_data['image_list']) - 1)
wrong_image_file = join(
data_dir,
'faces/jpg/' + loaded_data['image_list'][wrong_image_id] + '.jpg')
wrong_image_array = image_processing.load_image_array(
wrong_image_file, image_size)
wrong_images[cnt, :, :, :] = wrong_image_array
random_caption = random.randint(0, 4)
caption_file = join(
data_dir,
'faces/captions/' + loaded_data['image_list'][idx] + '.txt')
with open(caption_file, 'r') as f:
c = f.read().split('\n')[random_caption]
c = word2vec.embed_sentence(c)
captions[cnt, :] = c[0:caption_vector_length]
image_files.append(image_file)
cnt += 1
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, captions, z_noise, image_files
def get_training_batch(self,
batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
real_images = [] # (batch_size, image_size, image_size, channel)
wrong_images = [] # (batch_size, image_size, image_size, channel)
captions = [] # (batch_size, sentence_vector_size=2400)
z_noise = [] # (batch_size, noise_vector_size=100)
image_files = [] # (batch_size)
for i in range(batch_no * batch_size,
batch_no * batch_size + batch_size):
idx = i % len(loaded_data["image_list"])
real_images.append(
image_processing.load_image_array(
loaded_data["image_list"][idx], image_size))
wrong_images.append(
image_processing.load_image_array(
loaded_data["image_list"][random.randint(
0,
len(loaded_data["image_list"]) - 1)], image_size))
video_name = loaded_data["image_list"][idx].split('/')[-1].split(
'.')[0].split('-')[0]
caption_path = "/mnt/ntu/text_to_video/data/sentences/vectors/"
caption_npy = np.load(open(caption_path + video_name + ".npy",
'r'))
captions.append(caption_npy[random.randint(
0, caption_npy.shape[0] - 1)])
z_noise.append(np.random.uniform(-1, 1, [z_dim]))
image_files.append(video_name)
#return real_images, wrong_images, captions, z_noise, image_files
return np.array(real_images), np.array(wrong_images), np.array(
captions), np.array(z_noise), image_files
def get_training_batch(self,
batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
real_images = []
wrong_images = []
acoustic_features = []
z_noise = []
image_files = []
for i in range(batch_no * batch_size,
batch_no * batch_size + batch_size):
idx = i % len(loaded_data["image_list"])
real_images.append(
image_processing.load_image_array(
loaded_data["image_list"][idx], image_size))
wrong_images.append(
image_processing.load_image_array(
loaded_data["image_list"][random.randint(
0,
len(loaded_data["image_list"]) - 1)], image_size))
filename = loaded_data["image_list"][idx].split('/')[-1].split(
'.')[0]
onehot = np.zeros(len(self.training_data_list))
onehot[loaded_data["class_label"][idx]] = 1
acoustic_features.append(onehot)
#z_noise.append(np.random.uniform(-1, 1, [z_dim]))
z_noise.append(np.random.normal(scale=0.01, size=[z_dim]))
image_files.append(filename)
return np.array(real_images), np.array(wrong_images), np.array(
acoustic_features), np.array(z_noise), image_files
def get_augment_batch(image_size, data_dir, batch_no, augment_batch_size,
loaded_data, image_captions):
real_images = np.zeros((augment_batch_size, 64, 64, 3))
text_captions = []
cnt = 0
for i in range(batch_no * augment_batch_size,
batch_no * augment_batch_size + augment_batch_size):
idx = i % len(loaded_data['image_list'])
image_file = join(data_dir,
'augment/' + loaded_data['image_list'][idx])
image_array = image_processing.load_image_array(image_file, image_size)
real_images[cnt, :, :, :] = image_array
text_captions.append(image_captions[loaded_data['image_list'][idx]])
cnt += 1
return text_captions, real_images
def get_training_batch(batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
if data_set == 'mscoco':
with h5py.File(join(data_dir,
'tvs/' + split + '_tvs_' + str(batch_no))) as hf:
caption_vectors = np.array(hf.get('tv'))
caption_vectors = caption_vectors[:, 0:caption_vector_length]
with h5py.File(
join(data_dir,
'tvs/' + split + '_tv_image_id_' + str(batch_no))) as hf:
image_ids = np.array(hf.get('tv'))
real_images = np.zeros((batch_size, 64, 64, 3))
wrong_images = np.zeros((batch_size, 64, 64, 3))
image_files = []
for idx, image_id in enumerate(image_ids):
image_file = join(
data_dir,
'%s2014/COCO_%s2014_%.12d.jpg' % (split, split, image_id))
image_array = image_processing.load_image_array(
image_file, image_size)
real_images[idx, :, :, :] = image_array
image_files.append(image_file)
# TODO>> As of Now, wrong images are just shuffled real images.
first_image = real_images[0, :, :, :]
for i in range(0, batch_size):
if i < batch_size - 1:
wrong_images[i, :, :, :] = real_images[i + 1, :, :, :]
else:
wrong_images[i, :, :, :] = first_image
z_noise = np.random.uniform(-1, 1, [batch_size, z_dim])
return real_images, wrong_images, caption_vectors, z_noise, image_files
def get_training_batch(self,
batch_no,
batch_size,
image_size,
z_dim,
caption_vector_length,
split,
data_dir,
data_set,
loaded_data=None):
real_images = []
image_files = []
for i in range(batch_no * batch_size,
batch_no * batch_size + batch_size):
idx = i % len(loaded_data["image_list"])
real_images.append(
image_processing.load_image_array(
loaded_data["image_list"][idx], 64))
filename = loaded_data["image_list"][idx]
image_files.append(filename)
return np.array(real_images), image_files
import tensorflow as tf
import numpy as np
output_dir = "./images_Many1/"
num_stages = 5
image_size = 64
#def load_test_data(output_dir, image_size, num_stages):
#image_file = join(data_dir, 'flowers/jpg/'+loaded_data['image_list'][idx])
image_list = [f for f in listdir(output_dir) if f[-3:] == 'jpg']
image_list.sort(key=lambda x: int(x[:x.index("_")]))
num_group = len(image_list) / (num_stages + 1)
for i in range(num_group):
real_image_name = image_list[i * (num_stages + 1)]
fake_image_name = image_list[i * (num_stages + 1) + 5]
real_image = image_processing.load_image_array(
join(output_dir, real_image_name), image_size)
fake_image = image_processing.load_image_array(
join(output_dir, fake_image_name), image_size)
real_image = np.einsum('ijk->kij', real_image)
fake_image = np.einsum('ijk->kij', fake_image)
t_real_image = tf.placeholder('float32', [3, image_size, image_size],
name='real_image')
t_fake_image = tf.placeholder('float32', [3, image_size, image_size],
name='fake_image')
s_r = tf.svd(t_real_image, compute_uv=False)
s_f = tf.svd(t_fake_image, compute_uv=False)
with tf.Session() as sess:
sess.run([s_r], feed_dict={t_real_image: real_image})
sess.run([s_f], feed_dict={t_fake_image: fake_image})
print fake_image