channel=channel_mean)
dataset_args["dataset_cls"] = ReferitDataset
dataset_args["expand_objects"] = (args.mode == "crop_all")
dataset_args["crop_builder"] = crop_builder
else:
assert False, "Invalid mode: {}".format(args.mode)
# create network
print("Create network...")
ft_output = resnet.create_resnet(images,
resnet_out=args.feature_name,
resnet_version=args.resnet_version,
is_training=False)
extract_features(
img_input=images,
ft_output=ft_output,
dataset_cstor=dataset_cstor,
dataset_args=dataset_args,
batchifier_cstor=ReferitBatchifier,
out_dir=args.out_dir,
set_type=["all"],
network_ckpt=args.ckpt,
batch_size=args.batch_size,
no_threads=args.no_thread,
gpu_ratio=args.gpu_ratio)
print("Create networks...")
if args.network == "resnet":
ft_output = resnet.create_resnet(images,
resnet_out=args.feature_name,
resnet_version=args.resnet_version,
is_training=False)
# create network
with slim.arg_scope(slim_utils.resnet_arg_scope(is_training=False)):
_, end_points = resnet_v1.resnet_v1_152(images, 1000) # 1000 is the number of softmax class
elif args.network == "vgg":
_, end_points = vgg.vgg_16(images, is_training=False, dropout_keep_prob=1.0)
ft_name = os.path.join("vgg_16", args.feature_name)
ft_output = end_points[ft_name]
else:
assert False, "Incorrect Network"
extract_features(
img_input = images,
ft_output = ft_output,
dataset_cstor = dataset_cstor,
dataset_args = {"folder": args.data_dir, "image_builder":image_builder, "crop_builder":crop_builder, "dataset_name": args.dataset_name},
batchifier_cstor = OracleBatchifier,
out_dir = args.out_dir,
set_type = args.set_type,
network_ckpt=args.ckpt,
batch_size = args.batch_size,
no_threads = args.no_thread,
gpu_ratio = args.gpu_ratio)
source = 'image'
images = tf.placeholder(tf.float32, [None, args.img_size, args.img_size, 3],
name=source)
image_builder = RawImageBuilder(args.img_dir,
height=args.img_size,
width=args.img_size,
channel=channel_mean)
# create network
print("Create network...")
ft_output = resnet.create_resnet(images,
resnet_out=args.feature_name,
resnet_version=args.resnet_version,
is_training=False)
extract_features(img_input=images,
ft_output=ft_output,
dataset_cstor=VQADataset,
dataset_args={
"folder": args.data_dir,
"year": args.year,
"image_builder": image_builder
},
batchifier_cstor=VQABatchifier,
out_dir=args.out_dir,
set_type=args.set_type,
network_ckpt=args.ckpt,
batch_size=args.batch_size,
no_threads=args.no_thread,
gpu_ratio=args.gpu_ratio)