def read_and_prepocess_single_img(filename_queue, shortside_len, is_training):
img_name, img, gtboxes_and_label, num_objects = read_single_example_and_decode(
filename_queue)
img = tf.cast(img, tf.float32)
if is_training:
# img, gtboxes_and_label = image_preprocess.aspect_ratio_jittering(img, gtboxes_and_label)
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len,
length_limitation=cfgs.IMG_MAX_LENGTH)
img, gtboxes_and_label = image_preprocess.random_flip_left_right(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
else:
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len,
length_limitation=cfgs.IMG_MAX_LENGTH)
if cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d']:
img = img / 255 - tf.constant([[cfgs.PIXEL_MEAN_]])
else:
img = img - tf.constant([[cfgs.PIXEL_MEAN]]) # sub pixel mean at last
return img_name, img, gtboxes_and_label, num_objects, img_h, img_w
def read_and_prepocess_single_img(filename_queue, shortside_len, is_training):
img_name, img, gtboxes_and_label, num_objects = read_single_example_and_decode(
filename_queue)
img = tf.cast(img, tf.float32)
if is_training:
if cfgs.RGB2GRAY:
# img, gtboxes_and_label = image_preprocess.aspect_ratio_jittering(img, gtboxes_and_label)
img = image_preprocess.random_rgb2gray(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
if cfgs.IMG_ROTATE:
# rotate with 0.5 prob. and if rotate, if will random choose a theta from : tf.range(-90, 90+16, delta=15)
img, gtboxes_and_label = image_preprocess.random_rotate_img(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len,
length_limitation=cfgs.IMG_MAX_LENGTH)
if cfgs.HORIZONTAL_FLIP:
img, gtboxes_and_label = image_preprocess.random_flip_left_right(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
if cfgs.VERTICAL_FLIP:
img, gtboxes_and_label = image_preprocess.random_flip_up_down(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
else:
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len,
length_limitation=cfgs.IMG_MAX_LENGTH)
# gtboxes_and_label = tf.reshape(tf.py_func(filter_small_gt, inp=[gtboxes_and_label], Tout=[tf.float32]), [-1, 9])
if cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d']:
img = img / 255 - tf.constant([[cfgs.PIXEL_MEAN_]])
else:
img = img - tf.constant([[cfgs.PIXEL_MEAN]]) # sub pixel mean at last
return img_name, img, gtboxes_and_label, num_objects, img_h, img_w
def read_and_prepocess_single_img(filename_queue, shortside_len, is_training):
img_name, img, gtboxes_and_label, num_objects = read_single_example_and_decode(
filename_queue)
img = tf.cast(img, tf.float32)
img = img - tf.constant(cfgs.PIXEL_MEAN)
if is_training:
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len)
img, gtboxes_and_label = image_preprocess.random_flip_left_right(
img_tensor=img, gtboxes_and_label=gtboxes_and_label)
else:
img, gtboxes_and_label, img_h, img_w = image_preprocess.short_side_resize(
img_tensor=img,
gtboxes_and_label=gtboxes_and_label,
target_shortside_len=shortside_len)
return img_name, img, gtboxes_and_label, num_objects, img_h, img_w
