def preprocess_image(image, label, is_training):
'''数据预处理'''
if is_training:
image, label = preprocessing.random_rescale_image_and_label(
image, label, _MIN_SCALE, _MAX_SCALE)
image, label = preprocessing.random_crop_or_pad_image_and_label(
image, label, _HEIGHT, _WIDTH, _IGNORE_LABEL)
image, label = preprocessing.random_filp_left_right_image_and_label(
image, label)
image.set_shape([_HEIGHT, _WIDTH, 3])
label.set_shape([_HEIGHT, _WIDTH, 1])
image = preprocessing.mean_image_subtraction(image)
return image, label
def preprocess_image(image, label, is_training):
"""Preprocess a single image of layout [height, width, depth]."""
if is_training:
# Randomly scale the image and label.
image, label = preprocessing.random_rescale_image_and_label(
image, label, _MIN_SCALE, _MAX_SCALE)
# Randomly crop or pad a [_HEIGHT, _WIDTH] section of the image and label.
image, label = preprocessing.random_crop_or_pad_image_and_label(
image, label, _HEIGHT, _WIDTH, _IGNORE_LABEL)
# Randomly flip the image and label horizontally.
image, label = preprocessing.random_flip_left_right_image_and_label(
image, label)
image.set_shape([_HEIGHT, _WIDTH, 3])
label.set_shape([_HEIGHT, _WIDTH, 1])
if 'B2' in FLAGS.bands:
image = preprocessing.mean_image_subtraction(image, S2=True)
elif 'R' in FLAGS.bands:
image = preprocessing.mean_image_subtraction(image, S2=False)
return image, label
def preprocess_image(image, sem, disp, is_training):
"""Preprocess a single image of layout [height, width, depth]."""
disp_ori = disp
disp_ori.set_shape([_EVAL_HEIGHT, _EVAL_WIDTH, 1])
if is_training:
# Randomly scale the image and label.
image, sem, disp = preprocessing.random_rescale_image_and_label(
image, sem, disp, _HEIGHT, _WIDTH, _EVAL_WIDTH / _WIDTH,
_MIN_SCALE, _MAX_SCALE)
# Randomly crop or pad a [_HEIGHT, _WIDTH] section of the image and label.
image, sem, disp = preprocessing.random_crop_or_pad_image_and_label(
image, sem, disp, _HEIGHT, _WIDTH, _IGNORE_LABEL)
# Randomly flip the image and label horizontally.
image, sem, disp = preprocessing.random_flip_left_right_image_and_label(
image, sem, disp)
image.set_shape([_HEIGHT, _WIDTH, 3])
sem.set_shape([_HEIGHT, _WIDTH, 1])
disp.set_shape([_HEIGHT, _WIDTH, 1])
else:
image.set_shape([None, None, 3])
image = tf.image.resize_images(image, (_HEIGHT, _WIDTH),
method=tf.image.ResizeMethod.BILINEAR)
sem.set_shape([None, None, 1])
sem = tf.image.resize_images(sem, (_HEIGHT, _WIDTH),
method=tf.image.ResizeMethod.BILINEAR)
sem = tf.to_int32(sem)
disp.set_shape([None, None, 1])
disp = tf.image.resize_images(disp, (_HEIGHT, _WIDTH),
method=tf.image.ResizeMethod.BILINEAR)
disp = tf.to_int32(disp)
image = preprocessing.mean_image_subtraction(image)
disp = preprocessing.normalization(disp, dataset=FLAGS.dataset)
return image, sem, disp
def decode_powerline_func(x):
features = tf.io.parse_single_example(x, feature)
jpg_array_img = tf.io.decode_jpeg(features['image'], channels=3)
jpg_array_gt = tf.io.decode_jpeg(features['gt'], channels=1)
initial_width = tf.cast(tf.shape(jpg_array_img)[0], tf.float32)
initial_height = tf.cast(tf.shape(jpg_array_img)[1], tf.float32)
if Mode_128:
# If the shape of image is 128x128, uncomment this:
img = jpg_array_img
gt = jpg_array_gt
else:
# If the shape of image IS NOT 128x128, the following is not required.
lo_dim = 130.0
# Take the greater value, and use it for the ratio
min_ = tf.minimum(initial_width, initial_height)
ratio = min_ / lo_dim
new_width = tf.cast(initial_width / ratio, tf.int32)
new_height = tf.cast(initial_height / ratio, tf.int32)
img = tf.image.resize_images(jpg_array_img, (new_width, new_height), preserve_aspect_ratio=False)
img = tf.cast(img, tf.uint8)
img = tf.image.random_crop(img, (128, 128, 3), 1)
gt = tf.image.resize_images(jpg_array_gt, (new_width, new_height), preserve_aspect_ratio=False)
gt = tf.cast(gt, tf.uint8)
gt = tf.image.random_crop(gt, (128, 128, 1), 1)
if Random_Size:
exp = tf.random.uniform(())
img = tf.image.resize_images(img, (128 + tf.cast(256 * exp, tf.int32), 128 + tf.cast(256 * exp, tf.int32)),
preserve_aspect_ratio=False)
img = tf.image.random_crop(img, (128, 128, 3))
if Hue_Distort and not Gray_Mode:
img = tf.image.random_hue(img, 0.5)
img, gt = tf.cond(tf.random.uniform(()) > 0.5,
lambda: (tf.image.flip_left_right(img), tf.image.flip_left_right(gt)), lambda: (img, gt))
gt = tf.where(gt > 128, tf.constant(1, tf.uint8, (128, 128, 1)), tf.constant(0, tf.uint8, (128, 128, 1)),
name='binary_img')
img = tf.cast(img, tf.float32)
features['image'] = preprocessing.mean_image_subtraction(img)
features['gt'] = gt
return features
def _parse_function(filename, is_label):
if not is_label:
image_filename, label_filename = filename, None
else:
image_filename, label_filename = filename
image_string = tf.read_file(image_filename)
image = tf.image.decode_image(image_string)
image = tf.to_float(tf.image.convert_image_dtype(image,
dtype=tf.uint8))
image.set_shape([None, None, 4])
image = preprocessing.mean_image_subtraction(image)
if not is_label:
return image
else:
label_string = tf.read_file(label_filename)
label = tf.image.decode_image(label_string)
label = tf.to_int32(
tf.image.convert_image_dtype(label, dtype=tf.uint8))
label.set_shape([None, None, 1])
return image, label
image, label = preprocessing.random_rescale_image_and_label(
image, label, _MIN_SCALE, _MAX_SCALE)
# Randomly crop or pad a [_HEIGHT, _WIDTH] section of the image and label.
image, label = preprocessing.random_crop_or_pad_image_and_label(
image, label, _HEIGHT, _WIDTH, _IGNORE_LABEL)
# Randomly flip the image and label horizontally.
image, label = preprocessing.random_flip_left_right_image_and_label(
image, label)
'''
image.set_shape([_HEIGHT, _WIDTH, 3])
label.set_shape([_HEIGHT, _WIDTH, 1])
image = preprocessing.mean_image_subtraction(image)
return image, label
def input_fn(is_training, data_dir, batch_size, num_epochs=1):
"""Input_fn using the tf.data input pipeline for CIFAR-10 dataset.
Args:
is_training: A boolean denoting whether the input is for training.
data_dir: The directory containing the input data.
batch_size: The number of samples per batch.
num_epochs: The number of epochs to repeat the dataset.
Returns:
A tuple of images and labels.
def main():
image = tf.placeholder(tf.float32, [None, None, 3])
inputs = preprocessing.mean_image_subtraction(image)
inputs = tf.expand_dims(inputs, axis=0)
model = deeplab_model.model_generator(
FLAGS.num_classes,
FLAGS.output_stride,
FLAGS.base_architecture,
FLAGS.pre_trained_model,
None,
)
logits = model(inputs, False)
#预测类别shape[batch,h,w,1]
pred_classes = tf.expand_dims(tf.argmax(logits,
axis=3,
output_type=tf.int32),
axis=3)
#图片上色形式shape[batch,h,w,3]
pred_decoded_labels = tf.py_func(preprocessing.decode_labels,
[pred_classes, 1, FLAGS.num_classes],
tf.uint8)
pred_decoded_labels = tf.squeeze(pred_decoded_labels)
saver = tf.train.Saver()
sess = tf.Session()
model_file = tf.train.latest_checkpoint(FLAGS.model_dir)
saver.restore(sess, model_file)
if FLAGS.test_mode == '1':
for filename in os.listdir(FLAGS.pictue):
x = cv2.imread(FLAGS.pictue + filename)
x1 = cv2.cvtColor(x, cv2.COLOR_BGR2RGB)
out = sess.run(pred_decoded_labels, feed_dict={image: x1})
out = cv2.cvtColor(out, cv2.COLOR_RGB2BGR)
out = np.concatenate([x, out], axis=1)
cv2.imshow('im', out)
k = cv2.waitKey(0) & 0xFF
if k == 27:
cv2.imwrite(FLAGS.output + filename, out)
cv2.destroyAllWindows()
if FLAGS.test_mode == '2':
cap = cv2.VideoCapture(0)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(FLAGS.output + 'out.mp4', fourcc, 10,
(1280, 480))
while True:
ret, frame = cap.read()
if ret == True:
frame1 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
result = sess.run(pred_decoded_labels,
feed_dict={image: frame1})
result = cv2.cvtColor(result, cv2.COLOR_RGB2BGR)
result1 = np.concatenate([frame, result], axis=1)
a = out.write(result1)
cv2.imshow("result", result1)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
sess.close()
