I was trying to freeze the graph however you are using tensorflow input pipeline instead of a placeholder. Could you please explain, how to remove input pipeline and add a node for reading input image?

Thanks!

Hi @kwotsin This is brilliant work. Thanks for sharing this. I want to freeze this model and serve it through an android app. Can it be done? Do you have any pointers as to where to start from..

InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels: device='GPU'; Targmax in [DT_INT64]; T in [DT_DOUBLE] device='GPU'; Targmax in [DT_INT64]; T in [DT_FLOAT] device='GPU'; Targmax in [DT_INT64]; T in [DT_HALF]

 [[Node: ENet_1/bottleneck1_0_main_max_pool = MaxPoolWithArgmax[T=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]](ENet_1/initial_block_1_concat)]]

I tried to train the Enet with own data but it caused a error. It is a problem with FIFOQueue. Our data have 715 images for training and 105 for validation and 100 for testing.

Can you help me to figure out this problem. Thanks a lot. Anh

2017-08-15 16:48:45.882942: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
2017-08-15 16:48:45.883176: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
2017-08-15 16:48:45.883198: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
2017-08-15 16:48:45.883214: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
2017-08-15 16:48:45.883861: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
2017-08-15 16:48:45.886415: W tensorflow/core/framework/op_kernel.cc:1158] Out of range: FIFOQueue '_1_batch/fifo_queue' is closed and has insufficient elements (requested 5, current size 0)
	 [[Node: batch = QueueDequeueUpToV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, batch/n)]]
Traceback (most recent call last):
  File "train_enet.py", line 357, in <module>
    run()
  File "train_enet.py", line 172, in run
    with slim.arg_scope(ENet_arg_scope(weight_decay=weight_decay)):
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/contextlib.py", line 35, in __exit__
    self.gen.throw(type, value, traceback)
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 964, in managed_session
    self.stop(close_summary_writer=close_summary_writer)
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 792, in stop
    stop_grace_period_secs=self._stop_grace_secs)
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
    six.reraise(*self._exc_info_to_raise)
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/training/queue_runner_impl.py", line 238, in _run
    enqueue_callable()
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1063, in _single_operation_run
    target_list_as_strings, status, None)
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/contextlib.py", line 24, in __exit__
    self.gen.next()
  File "/home/leducanh/.pyenv/versions/anaconda3-2.5.0/envs/tensorflow120/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape mismatch in tuple component 1. Expected [202,360,1], got [202,360,3]
	 [[Node: batch/fifo_queue_enqueue = QueueEnqueueV2[Tcomponents=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batch/fifo_queue, Squeeze/_2975, Squeeze_1/_2977)]]

hi, Kwotsin Thank you so much for the implementation! I trained the model with my data and got much better mIOU comparing to legacy method.

However, the inference performance is not good as the stats from the paper. My result is about 0.5~1 fps for 1280x720 image, on GeForce GTX 1080. My class number is 2 so it might save much MIPS. I run the inference with OpenCV real-time images.

Any idea about the root cause?

thanks a lot, BRS, Dell

Caused by op 'ENet/Relu_67', defined at: File "D:/Python/code/Semantic Segmentation/TensorFlow-ENet-master/train_enet.py", line 337, in run() File "D:/Python/code/Semantic Segmentation/TensorFlow-ENet-master/train_enet.py", line 162, in run skip_connections=skip_connections) File "D:\Python\code\Semantic Segmentation\TensorFlow-ENet-master\enet.py", line 455, in ENet net = bottleneck(net, output_depth=128, filter_size=3, dilated=True, dilation_rate=16, scope='bottleneck'+str(i)+'_8') File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args return func(*args, **current_args) File "D:\Python\code\Semantic Segmentation\TensorFlow-ENet-master\enet.py", line 264, in bottleneck net = prelu(net, scope=scope+'_prelu4') File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args return func(*args, **current_args) File "D:\Python\code\Semantic Segmentation\TensorFlow-ENet-master\enet.py", line 35, in prelu pos = tf.nn.relu(x) File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 2272, in relu result = _op_def_lib.apply_op("Relu", features=features, name=name) File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op op_def=op_def) File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op original_op=self._default_original_op, op_def=op_def) File "C:\ProgramData\Anaconda2\envs\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in init self._traceback = _extract_stack()

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[10,45,60,128]

I want to use this model for my own dataset(classes 2:car and backgroud) However the accuracy is so low with the loss falling the mean_iou is falling 。the model is not work for this dataset
what is the problem？

Hi, Thank you for providing a good code.

I have a one question.

Can I use predict code in real time in a webcam? If there is a way, can you let me know?

Regard.

I modefied the code file:predict_segmentation.py to predict the video frame, but there are problems, please help me , Thanks ! here is the error: +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ python pre_video.py /home/yh/.conda/envs/yh/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type. from ._conv import register_converters as _register_converters Traceback (most recent call last): File "pre_video.py", line 122, in skip_connections=skip_connections) File "/home/yh/Work/TensorFlow-ENet/enet.py", line 464, in ENet pooling_indices=pooling_indices_2, output_shape=inputs_shape_2, scope=bottleneck_scope_name+'_0') File "/home/yh/.conda/envs/yh/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args return func(*args, **current_args) File "/home/yh/Work/TensorFlow-ENet/enet.py", line 321, in bottleneck net_unpool = unpool(net_unpool, pooling_indices, output_shape=output_shape, scope='unpool') File "/home/yh/Work/TensorFlow-ENet/enet.py", line 101, in unpool y = mask // (output_shape[2] * output_shape[3]) TypeError: unsupported operand type(s) for *: 'NoneType' and 'int' +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

here is my modefied code:

import tensorflow as tf import os import matplotlib.pyplot as plt from enet import ENet, ENet_arg_scope from preprocessing import preprocess from scipy.misc import imsave import numpy as np import cv2 import time

slim = tf.contrib.slim

#指定GPU os.environ["CUDA_VISIBLE_DEVICES"]="1"

W = 500 H = 400

batch_size = 1 num_classes = 2

path = '/home/yh/data/dataset/zhijia/' filename = 'day.avi' #'20170920_124050_872.avi' cap = cv2.VideoCapture(path+filename) #size=(W,H) fourcc = cv2.VideoWriter_fourcc('M','J','P','G') #opencv3.0

checkpoint_dir = "./checkpoint_mfb" checkpoint = tf.train.latest_checkpoint(checkpoint_dir)

num_initial_blocks = 1 skip_connections = False stage_two_repeat = 2 ''' #Labels to colours are obtained from here: https://github.com/alexgkendall/SegNet-Tutorial/blob/c922cc4a4fcc7ce279dd998fb2d4a8703f34ebd7/Scripts/test_segmentation_camvid.py

However, the road_marking class is collapsed into the road class in the dataset provided.

Classes:

Sky = [128,128,128] Building = [128,0,0] Pole = [192,192,128] Road_marking = [255,69,0] Road = [128,64,128] Pavement = [60,40,222] Tree = [128,128,0] SignSymbol = [192,128,128] Fence = [64,64,128] Car = [64,0,128] Pedestrian = [64,64,0] Bicyclist = [0,128,192] Unlabelled = [0,0,0] ''' label_to_colours = {0: [0,0,0], 1: [0,128,0], 2: [192,192,128], 3: [128,64,128], 4: [60,40,222], 5: [128,128,0], 6: [192,128,128], 7: [64,64,128], 8: [64,0,128], 9: [64,64,0], 10: [0,128,192], 11: [128,128,128]}

#Create the photo directory photo_dir = checkpoint_dir + "/test_images" if not os.path.exists(photo_dir): os.mkdir(photo_dir)

def vis_segmentation(image, seg_map): """Visualizes input image, segmentation map and overlay view."""

image_width, image_height = image.size
colored_label = label_to_color_image(seg_map).astype(np.uint8)
image_empty = np.zeros((image_height,2*image_width,3),np.uint8)
image_empty[:image_height,:image_width] = image.copy()
image_empty[:image_height,image_width:] = colored_label.copy()
image_empty[:image_height,:image_width] = image.copy()
image_empty[:image_height,image_width:] = colored_label.copy()

alpha = 0.35
beta = 1-alpha
gamma = 0
img_add = cv2.addWeighted(np.array(image), alpha, seg_map, beta, gamma)
return img_add

#Create a function to convert each pixel label to colour. def grayscale_to_colour(image): print('Converting image...') image = image.reshape((H, W, 1)) image = np.repeat(image, 3, axis=-1) for i in range(image.shape[0]): for j in range(image.shape[1]): label = int(image[i][j][0]) image[i][j] = np.array(label_to_colours[label])

return image

def model_run(image):

return predictions   

with tf.Graph().as_default() as graph:

image_tensor = tf.placeholder(tf.float32, [None, None, 3])
images = tf.expand_dims(image_tensor,0)

#Create the model inference
with slim.arg_scope(ENet_arg_scope()):
    logits, probabilities = ENet(images,
                                 num_classes=num_classes,
                                 batch_size=batch_size,
                                 is_training=False,
                                 reuse=None,
                                 num_initial_blocks=num_initial_blocks,
                                 stage_two_repeat=stage_two_repeat,
                                 skip_connections=skip_connections)

variables_to_restore = slim.get_variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
def restore_fn(sess):
    return saver.restore(sess, checkpoint)

predictions = tf.argmax(probabilities, -1)
predictions = tf.cast(predictions, tf.float32)
print('HERE', predictions.get_shape())

sv = tf.train.Supervisor(logdir=None, init_fn=restore_fn)

with sv.managed_session() as sess:
     now = 0.0
     while(cap.isOpened()):
          ret, frame = cap.read()
          if (ret == False):
              print('~~~~~~~~~~~~~~~~~~did not get any frame~~~~~~~~~~~~~~~~~~')
              break  
          image = frame.copy()             
          image = np.asarray(image, np.float32)/255           
          print('~~~~~~~~~~~~~~',sess.run(image_tensor))
          segmentations = sess.run(predictions, feed_dict={image_tensor:image})

          #cv2.imshow('pre',segmentations[0])
          #cv2.waitKey(0)

          #T = time.time() - now
          #print(int(1/T))
          #now = time.time()

cap.release() cv2.destroyAllWindows()

===============================================================================

I'm trying to use the network to train on 4-Channel Images. The changes in the code are

tf.image.decode_image(image, channels=4) in train_enet.py

and changed the number of channels in preprocessing.py. Now when I try to train the network I get the following error

tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot reshape a tensor with 734400 elements to shape [4,172800] (691200 elements) for 'ENet/unpool_1/Reshape_1' (op: 'Reshape') with input shapes: [4,1,90,120,17], [2] and with input tensors computed as partial shapes: input[1] = [4,172800].

Traceback (most recent call last):
  File "train_enet.py", line 337, in <module>
 run()
  File "train_enet.py", line 162, in run
	skip_connections=skip_connections)
  File "enet.py", line 476, in ENet
	pooling_indices=pooling_indices_1, output_shape=inputs_shape_1, scope=bottleneck_scope_name+'_0')
  File "Anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args
	return func(*args, **current_args)
  File "enet.py", line 321, in bottleneck
	net_unpool = unpool(net_unpool, pooling_indices, output_shape=output_shape, scope='unpool')
  File "enet.py", line 108, in unpool
	indices = tf.transpose(tf.reshape(tf.stack([b, y, x, f]), [4, updates_size]))
  File "Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 2451, in reshape
	name=name)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
	op_def=op_def)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2508, in create_op
	set_shapes_for_outputs(ret)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1873, in set_shapes_for_outputs
	shapes = shape_func(op)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1823, in call_with_requiring
	return call_cpp_shape_fn(op, require_shape_fn=True)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 610, in call_cpp_shape_fn
	debug_python_shape_fn, require_shape_fn)
  File "Anaconda3\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 676, in _call_cpp_shape_fn_impl
	raise ValueError(err.message)
ValueError: Cannot reshape a tensor with 734400 elements to shape [4,172800] (691200 elements) for 'ENet/unpool_1/Reshape_1' (op: 'Reshape') with input shapes: [4,1,90,120,17], [2] and with input tensors computed as partial shapes: input[1] = [4,172800].

Do I need to make any other changes ? Will this network even work for 4-channel images?

When I run ./train.sh, I find this error. Is this because of the Tensorflow version or I need to define the gradient of ENet/bottleneck2_0_main_max_pool myself? Thx!

Hello, when I using your demo code for training, I met a problem : Caused by op u'ENet/bottleneck1_0_conv3/Conv2D', defined at: File "train_enet.py", line 341, in run() File "train_enet.py", line 162, in run skip_connections=skip_connections) File "/home/yt/TensorFlow-ENet/enet.py", line 433, in ENet net, pooling_indices_1, inputs_shape_1 = bottleneck(net, output_depth=64, filter_size=3, regularizer_prob=0.01, downsampling=True, scope='bottleneck1_0') File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(*args, **current_args) File "/home/yt/TensorFlow-ENet/enet.py", line 223, in bottleneck net = slim.conv2d(net, output_depth, [1,1], scope=scope+'_conv3') File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(*args, **current_args) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1057, in convolution outputs = layer.apply(inputs) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 762, in apply return self.call(inputs, *args, **kwargs) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 652, in call outputs = self.call(inputs, *args, **kwargs) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/layers/convolutional.py", line 167, in call outputs = self._convolution_op(inputs, self.kernel) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 838, in call return self.conv_op(inp, filter) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 502, in call return self.call(inp, filter) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 190, in call name=self.name) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 639, in conv2d data_format=data_format, dilations=dilations, name=name) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3160, in create_op op_def=op_def) File "/home/yt/miniconda3/envs/enet_py2.7/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1625, in init self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InternalError (see above for traceback): Blas SGEMM launch failed : m=108000, n=64, k=4 [[Node: ENet/bottleneck1_0_conv3/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](ENet/add_2, ENet/bottleneck1_0_conv3/weights/read)]] [[Node: Adam/update_ENet/bottleneck2_5_batch_norm1/beta/ApplyAdam/_8812 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_17711_Adam/update_ENet/bottleneck2_5_batch_norm1/beta/ApplyAdam", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

my environment setup is: 2080ti tensorflow-gpu=1.5.0 python=2.7 can you please help me? and where to indicated which gpu to run the training code, I didn't find it

I runed the demo code, it perfect and no errors.

but shows errors when using my own dataset.

the image size is 400x400, the annotated image has same size, the background is 0, the target eara is 1.

(py36) [[email protected] TensorFlow-ENet]$ python train_enet.py --weighting="ENET" --num_epochs=300 --logdir="./log/train_original_E Net_knot" --num_classes=2 --image_width=400 --image_height=400
========= ENet Class Weights =========
[1.8298322321992648, 3.6742181094502975, 50.4983497918439, 50.4983497918439, 50.4983497918439, 50.4983497918439, 50.4983497918 439, 50.4983497918439, 50.4983497918439, 50.4983497918439, 50.4983497918439, 0.0]
WARNING:tensorflow:From train_enet.py:142: slice_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(tuple(tensor_list)).shuffl e(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/input.py:372: ran ge_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.range(limit).shuffle(limit).repeat(num_epochs ). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/input.py:318: inp ut_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.s hape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: lim it_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensors(tensor).repeat(num_epochs).
WARNING:tensorflow:From /home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: Que ueRunner.init (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From /home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add _queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From train_enet.py:152: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.batch(batch_size) (or padded_batch(...) if dynamic_pad=True).
inputs_shape [None, 400, 400, 3] Traceback (most recent call last): File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1628, in _create_c _op
c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 2 and 12 for 'mul' (op: 'Mul') with input shapes: [10,400,400,2], [12].

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train_enet.py", line 338, in run() File "train_enet.py", line 170, in run loss = weighted_cross_entropy(logits=logits, onehot_labels=annotations_ohe, class_weights=class_weights) File "train_enet.py", line 128, in weighted_cross_entropy weights = onehot_labels * class_weights File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 878, in binary_op_w rapper
return func(x, y, name=name) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1131, in _mul_dispa tch
return gen_math_ops.mul(x, y, name=name) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 5042, in mul
"Mul", x=x, y=y, name=name) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_fun c
return func(*args, **kwargs) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1792, in init control_input_ops) File "/home/syk/miniconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1631, in _create_c _op
raise ValueError(str(e)) ValueError: Dimensions must be equal, but are 2 and 12 for 'mul' (op: 'Mul') with input shapes: [10,400,400,2], [12].

I am getting the following error on running the train_enet.py file in python=3.6 TensorFlow=1.12. Can someone help with this error?

INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, indices[172800] = [1, 91, 1, 0] does not index into shape [25,90,120,64]
	 [[node ENet_1/unpool/ScatterNd (defined at /media/rohit/Data/water-segmentation/TensorFlow-ENet/enet.py:112)  = ScatterNd[T=DT_FLOAT, Tindices=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ENet_1/unpool/transpose, ENet_1/unpool/Reshape_2, ENet_1/unpool/ScatterNd/shape)]]

Caused by op 'ENet_1/unpool/ScatterNd', defined at:
  File "train_enet.py", line 337, in <module>
    run()
  File "train_enet.py", line 234, in run
    skip_connections=skip_connections)
  File "/media/rohit/Data/water-segmentation/TensorFlow-ENet/enet.py", line 467, in ENet
    pooling_indices=pooling_indices_2, output_shape=inputs_shape_2, scope=bottleneck_scope_name+'_0')
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args
    return func(*args, **current_args)
  File "/media/rohit/Data/water-segmentation/TensorFlow-ENet/enet.py", line 324, in bottleneck
    net_unpool = unpool(net_unpool, pooling_indices, output_shape=output_shape, scope='unpool')
  File "/media/rohit/Data/water-segmentation/TensorFlow-ENet/enet.py", line 112, in unpool
    ret = tf.scatter_nd(indices, values, output_shape)
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 7077, in scatter_nd
    "ScatterNd", indices=indices, updates=updates, shape=shape, name=name)
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
    return func(*args, **kwargs)
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
    op_def=op_def)
  File "/home/rohit/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
    self._traceback = tf_stack.extract_stack()

When I training my own dataset,i'm using tensorboard to supervise the trend of my training,I found that my training accuracy going higher and higher,but the training mIOU going lower and lower?These two lines have the opposite trend but keep pace. Could anyone else tell me why?Thanks a lot!