hasnainraz / skin-segmentation-tensorflow Goto Github PK
View Code? Open in Web Editor NEWA modified SegNet Convolutional Neural Net for segmenting human skin from images
License: MIT License
A modified SegNet Convolutional Neural Net for segmenting human skin from images
License: MIT License
When I began to train your model, I had this issue, but I have no ideas how to fix it. Could you please help me fix it? Thank you very much
Train loss: 0.0 Train iou: 0.0
Val. loss: 0.6931054 Val. iou: 0.4069072
Starting epoch: 0
Traceback (most recent call last):
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call
return fn(*args)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1341, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[4,256,121,161] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node up2/conv2d_transpose}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
[[iou_metric/confusion_matrix/stack_1/_81]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[4,256,121,161] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node up2/conv2d_transpose}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "model.py", line 232, in <module>
train(image_paths, mask_paths, val_image_paths, val_mask_paths)
File "model.py", line 156, in train
[train, cost, iou_update, seg_image], feed_dict=train_feed_dict)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
run_metadata)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[4,256,121,161] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node up2/conv2d_transpose (defined at /tmp/tmpwtsgo0a_.py:68) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
[[iou_metric/confusion_matrix/stack_1/_81]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[4,256,121,161] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node up2/conv2d_transpose (defined at /tmp/tmpwtsgo0a_.py:68) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations.
0 derived errors ignored.
Errors may have originated from an input operation.
Input Source operations connected to node up2/conv2d_transpose:
up2/stack (defined at /tmp/tmpwtsgo0a_.py:67)
batch_normalization_9/cond/Merge (defined at /tmp/tmp5xi7m83o.py:14)
up2/kernel/read (defined at model.py:33)
Input Source operations connected to node up2/conv2d_transpose:
up2/stack (defined at /tmp/tmpwtsgo0a_.py:67)
batch_normalization_9/cond/Merge (defined at /tmp/tmp5xi7m83o.py:14)
up2/kernel/read (defined at model.py:33)
Original stack trace for 'up2/conv2d_transpose':
File "model.py", line 232, in <module>
train(image_paths, mask_paths, val_image_paths, val_mask_paths)
File "model.py", line 114, in train
logits = inference(image_placeholder, training_flag)
File "model.py", line 79, in inference
up2 = trans_conv_with_bn(unconv3, 256, [3, 3], is_training, name='up2')
File "model.py", line 33, in trans_conv_with_bn
use_bias=use_bias, kernel_initializer=tf.contrib.layers.xavier_initializer(), name=name)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
return func(*args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/layers/convolutional.py", line 1279, in conv2d_transpose
return layer.apply(inputs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1479, in apply
return self.__call__(inputs, *args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/layers/base.py", line 537, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 634, in __call__
outputs = call_fn(inputs, *args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/autograph/impl/api.py", line 146, in wrapper
), args, kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/autograph/impl/api.py", line 450, in converted_call
result = converted_f(*effective_args, **kwargs)
File "/tmp/tmpwtsgo0a_.py", line 68, in tf__call
outputs = ag__.converted_call('conv2d_transpose', backend, ag__.ConversionOptions(recursive=True, force_conversion=False, optional_features=(), internal_convert_user_code=True), (inputs, self.kernel, output_shape_tensor), {'strides': self.strides, 'padding': self.padding, 'data_format': self.data_format, 'dilation_rate': self.dilation_rate})
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/autograph/impl/api.py", line 356, in converted_call
return _call_unconverted(f, args, kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/autograph/impl/api.py", line 253, in _call_unconverted
return f(*args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 4582, in conv2d_transpose
data_format=tf_data_format)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 2147, in conv2d_transpose
name=name)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 2218, in conv2d_transpose_v2
name=name)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 1407, in conv2d_backprop_input
name=name)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/home/user/.local/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
...
line 1291, in _do_call
raise type(e)(node_def, op, message)
InvalidArgumentError: assertion failed: [Need value.shape >= size, got ] [640 427 3] [408 544 3]
[[Node: cond/random_crop/Assert/Assert = Assert[T=[DT_STRING, DT_INT32, DT_INT32], summarize=1000](cond/random_crop/All, cond/random_crop/Assert/Assert/data_0, cond/random_crop/Shape, cond/random_crop/size)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[?,480,640,3], [?,480,640,1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
data = tf.data.Dataset.from_tensor_slices(
AttributeError: module 'tensorflow' has no attribute 'data'
Hi! Thank you so much for your amazing work. May I ask what kind of TensorFlow version are you using? I got so many errors from TensorFlow. Would you please double-check that? Thanks!
('Step:', 9998)
('Step:', 9999)
2018-03-21 22:20:25.266267: W tensorflow/core/framework/op_kernel.cc:1202] OP_REQUIRES failed at iterator_ops.cc:870 : Invalid argument: Cannot batch tensors with different shapes in component 0. First element had shape [640,427,3] and element 1 had shape [1600,1067,3].
Traceback (most recent call last):
File "./model.py", line 235, in <module>
train(image_paths, mask_paths, val_image_paths, val_mask_paths)
File "./model.py", line 169, in train
[val_image_tensor, val_mask_tensor])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 905, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1137, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1355, in _do_run
options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1374, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot batch tensors with different shapes in component 0. First element had shape [640,427,3] and element 1 had shape [1600,1067,3].
[[Node: IteratorGetNext_1 = IteratorGetNext[output_shapes=[[?,480,640,3], [?,480,640,1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator_1)]]
Caused by op u'IteratorGetNext_1', defined at:
File "./model.py", line 235, in <module>
train(image_paths, mask_paths, val_image_paths, val_mask_paths)
File "./model.py", line 104, in train
val_image_path, val_mask_path, augment=False, batch_size=3)
File "/home/ai/Projects/Skin-Segmentation-TensorFlow/utility.py", line 158, in data_batch
next_element = iterator.get_next()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/data/ops/iterator_ops.py", line 330, in get_next
name=name)), self._output_types,
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_dataset_ops.py", line 866, in iterator_get_next
output_shapes=output_shapes, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3271, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1650, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): Cannot batch tensors with different shapes in component 0. First element had shape [640,427,3] and element 1 had shape [1600,1067,3].
[[Node: IteratorGetNext_1 = IteratorGetNext[output_shapes=[[?,480,640,3], [?,480,640,1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator_1)]]
Hello!
Can you show how you prepare data to train?
Is there any open source dataset of skin segmentation? I am recently looking for them to finish a project.
I have prepared (not big) data set with hair masks by analogy with skin
Tell me please does such a idea make any sense whatsoever?
I don't know, maybe I do something wrong but I have GeForce GTX 1080 and see periodicaly used gpu, but not constantly usage and train process is too slow (ofcause with CPU it is tooo slow)
Can you share your results of training? how long does it take? What gpu you use?
NotFoundError: NewRandomAccessFile failed to Create/Open: C:/Users/HP/Desktop/.............\mask-newfamily-08.png : The system cannot find the file specified.
; No such file or directory
[[{{node ReadFile_1}}]]
[[{{node IteratorGetNext}}]]
I am getting this error fro every image in train and test folders while running the code. Even though the images are present on the mentioned path but unable to find the reason for the same.
Is it possible continue train after restart script?
$ ./model.py
Training inititated...
Traceback (most recent call last):
File "./model.py", line 235, in <module>
train(image_paths, mask_paths, val_image_paths, val_mask_paths)
File "./model.py", line 104, in train
val_image_path, val_mask_path, augment=False, batch_size=3)
File "/home/ai/Projects/Skin-Segmentation-TensorFlow/utility.py", line 123, in data_batch
_parse_data, num_parallel_calls=num_threads).prefetch(30)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 792, in map
return ParallelMapDataset(self, map_func, num_parallel_calls)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1628, in __init__
super(ParallelMapDataset, self).__init__(input_dataset, map_func)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1597, in __init__
self._map_func.add_to_graph(ops.get_default_graph())
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/function.py", line 486, in add_to_graph
self._create_definition_if_needed()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/function.py", line 321, in _create_definition_if_needed
self._create_definition_if_needed_impl()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/function.py", line 338, in _create_definition_if_needed_impl
outputs = self._func(*inputs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1560, in tf_map_func
ret = map_func(*nested_args)
File "/home/ai/Projects/Skin-Segmentation-TensorFlow/utility.py", line 87, in _parse_data
image_content = tf.read_file(image_paths)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 382, in read_file
"ReadFile", filename=filename, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 533, in _apply_op_helper
(prefix, dtypes.as_dtype(input_arg.type).name))
TypeError: Input 'filename' of 'ReadFile' Op has type float32 that does not match expected type of string.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.