def run_for_eval(input_image):
H, W, channel = input_image.shape
# < in case that input_image is smaller than crop_size >
dif_height = H - crop_size
dif_width = W - crop_size
if dif_height < 0 or dif_width < 0:
input_image = helper.numpy_pad_image(input_image, dif_height,
dif_width)
H, W, channel = input_image.shape
# < split >
split_crops = []
heights = helper.decide_intersection(H, crop_size)
widths = helper.decide_intersection(W, crop_size)
for height in heights:
for width in widths:
image_crop = input_image[height:height + crop_size,
width:width + crop_size]
split_crops.append(image_crop[np.newaxis, :])
feed_dict = {}
splitters = chunks(split_crops, gpu_num())
for list_index in range(len(splitters) - 1):
piece_crops = np.concatenate(
split_crops[splitters[list_index]:splitters[list_index + 1]])
feed_dict[eval_image_pl[list_index]] = piece_crops
for i in range(gpu_num()):
if eval_image_pl[i] not in feed_dict.keys():
feed_dict[eval_image_pl[i]] = np.zeros(
(1, crop_size, crop_size, 3), np.float32)
proba_crops_pieces = sess.run(eval_probas_op, feed_dict=feed_dict)
proba_crops = np.concatenate(proba_crops_pieces)
# < reassemble >
reassemble = np.zeros((H, W, eval_image_reader.num_classes),
np.float32)
index = 0
for height in heights:
for width in widths:
reassemble[height:height + crop_size,
width:width + crop_size] += proba_crops[index]
index += 1
# < crop to original image >
if dif_height < 0 or dif_width < 0:
reassemble = helper.numpy_crop_image(reassemble, dif_height,
dif_width)
return reassemble
def run_once(input_image):
H, W, channel = input_image.shape
# < in case that input_image is smaller than crop_size >
dif_height = H - crop_size
dif_width = W - crop_size
if dif_height < 0 or dif_width < 0:
input_image = helper.numpy_pad_image(input_image, dif_height,
dif_width)
H, W, channel = input_image.shape
# < split this image into crops >
split_crops = []
heights = helper.decide_intersection(H, crop_size)
widths = helper.decide_intersection(W, crop_size)
for height in heights:
for width in widths:
image_crop = input_image[height:height + crop_size,
width:width + crop_size]
split_crops.append(image_crop[np.newaxis, :])
# < >
num_chunks = int((len(split_crops) - 1) / FLAGS.batch_size) + 1
proba_crops_list = []
for chunk_i in range(num_chunks):
feed_dict = {}
start = chunk_i * FLAGS.batch_size
end = min((chunk_i + 1) * FLAGS.batch_size, len(split_crops))
feed_dict[images_pl[0]] = np.concatenate(split_crops[start:end])
proba_crops_part = sess.run(eval_probas_op, feed_dict=feed_dict)
proba_crops_list.append(proba_crops_part[0])
proba_crops = np.concatenate(proba_crops_list)
# < reassemble >
reassemble = np.zeros((H, W, num_classes), np.float32)
index = 0
for height in heights:
for width in widths:
reassemble[height:height + crop_size,
width:width + crop_size] += proba_crops[index]
index += 1
# < crop to original image >
if dif_height < 0 or dif_width < 0:
reassemble = helper.numpy_crop_image(reassemble, dif_height,
dif_width)
return reassemble