Related
I am currently working on a deep learning project in the signal processing domain. The currently used loss function is the mean square error (MSE). However, it turns out that this loss function does not directly reflect my evaluation metric. Thus, I decide to use the alternative loss function, named Zero mean Normalization Cross-Correlation (ZNCC).
Note: I use TensorFlow 2.0 for this project
Here is my defined loss function.
def ZNCC(true, predict):
true = true.numpy()
predict = predict.numpy()
x_bar = np.average(true)
y_bar = np.average(predict)
u = true - x_bar
v = predict - y_bar
top = np.dot(u,v)
bottom = np.linalg.norm(u) * np.linalg.norm(v)
zncc = top/bottom
if zncc<0:
zncc = 0
return tf.convert_to_tensor(1-zncc)
Here is the compilation statement
model = MyModel()
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.002,beta_1=0.99,beta_2=0.989,epsilon=1e-07), loss=ZNCC, run_eagerly=True)
And here is my model.fit() statement
history = model.fit(training_generator,
validation_data=validation_generator,
epochs=150,
callbacks=[tensorboard_callback, model_checkpoint_callback])
After I run the above cell, I run into this error.
Epoch 1/150
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-142-c047e0d40ac5> in <module>
3 validation_data=validation_generator,
4 epochs=150,
----> 5 callbacks=[tensorboard_callback, model_checkpoint_callback])
/tmp/__autograph_generated_file63laq54x.py in tf__ZNCC(true, predict)
14 u = (ag__.ld(true) - ag__.ld(x_bar))
15 v = (ag__.ld(predict) - ag__.ld(y_bar))
---> 16 top = ag__.converted_call(ag__.ld(np).dot, (ag__.ld(u), ag__.ld(v)), None, fscope)
17 bottom = (ag__.converted_call(ag__.ld(np).linalg.norm, (ag__.ld(u),), None, fscope) * ag__.converted_call(ag__.ld(np).linalg.norm, (ag__.ld(v),), None, fscope))
18 zncc = (ag__.ld(top) / ag__.ld(bottom))
<__array_function__ internals> in dot(*args, **kwargs)
ValueError: in user code:
File "<ipython-input-136-e4e00382e336>", line 9, in ZNCC *
top = np.dot(u,v)
File "<__array_function__ internals>", line 6, in dot **
ValueError: shapes (128,3490) and (128,3490) not aligned: 3490 (dim 1) != 128 (dim 0)
Could anyone provide the reason for this error and the solution to fix it?
Much appreciated.
EDIT
I have tried to reimplement the loss function like so:
def ZNCC(true, predict):
x_bar = tf.math.reduce_mean(true)
y_bar = tf.math.reduce_mean(predict)
u = true - x_bar
v = predict - y_bar
print(x_bar)
print(y_bar)
print(u)
print(v)
u = tf.dtypes.cast(u, tf.float64)
v = tf.dtypes.cast(v, tf.float64)
top = tf.tensordot(u,v,1)
bottom = tf.norm(u) * tf.norm(v)
zncc = top/bottom
print(top)
print(bottom)
print(zncc)
zncc = tf.cond(tf.less(zncc,0),lambda: tf.dtypes.cast(0, tf.float64), lambda: zncc)
return 1-zncc
Then I have also try to evaluate the function like so:
x = tf.constant([1, 2, 3, 4, 5])
y = tf.constant([2,2,2,2,1])
ZNCC(x,y)
It return the result as follow as expected:
tf.Tensor(3, shape=(), dtype=int32)
tf.Tensor(1, shape=(), dtype=int32)
tf.Tensor([-2 -1 0 1 2], shape=(5,), dtype=int32)
tf.Tensor([1 1 1 1 0], shape=(5,), dtype=int32)
tf.Tensor(-2.0, shape=(), dtype=float64)
tf.Tensor(6.324555320336759, shape=(), dtype=float64)
tf.Tensor(-0.31622776601683794, shape=(), dtype=float64)
<tf.Tensor: shape=(), dtype=float64, numpy=1.0>
However, when I try to run it as loss function it give the following error:
InvalidArgumentError: Graph execution error:
Detected at node 'ZNCC/Tensordot/MatMul' defined at (most recent call last):
File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.7/dist-packages/traitlets/config/application.py", line 846, in launch_instance
app.start()
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelapp.py", line 612, in start
self.io_loop.start()
File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 132, in start
self.asyncio_loop.run_forever()
File "/usr/lib/python3.7/asyncio/base_events.py", line 541, in run_forever
self._run_once()
File "/usr/lib/python3.7/asyncio/base_events.py", line 1786, in _run_once
handle._run()
File "/usr/lib/python3.7/asyncio/events.py", line 88, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.7/dist-packages/tornado/ioloop.py", line 758, in _run_callback
ret = callback()
File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tornado/gen.py", line 1233, in inner
self.run()
File "/usr/local/lib/python3.7/dist-packages/tornado/gen.py", line 1147, in run
yielded = self.gen.send(value)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 365, in process_one
yield gen.maybe_future(dispatch(*args))
File "/usr/local/lib/python3.7/dist-packages/tornado/gen.py", line 326, in wrapper
yielded = next(result)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 268, in dispatch_shell
yield gen.maybe_future(handler(stream, idents, msg))
File "/usr/local/lib/python3.7/dist-packages/tornado/gen.py", line 326, in wrapper
yielded = next(result)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 545, in execute_request
user_expressions, allow_stdin,
File "/usr/local/lib/python3.7/dist-packages/tornado/gen.py", line 326, in wrapper
yielded = next(result)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/ipkernel.py", line 306, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/zmqshell.py", line 536, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2855, in run_cell
raw_cell, store_history, silent, shell_futures)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2881, in _run_cell
return runner(coro)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/async_helpers.py", line 68, in _pseudo_sync_runner
coro.send(None)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 3058, in run_cell_async
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 3249, in run_ast_nodes
if (await self.run_code(code, result, async_=asy)):
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 3326, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-42-c047e0d40ac5>", line 5, in <module>
callbacks=[tensorboard_callback, model_checkpoint_callback])
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1409, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1051, in train_function
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1040, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1030, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 890, in train_step
loss = self.compute_loss(x, y, y_pred, sample_weight)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 949, in compute_loss
y, y_pred, sample_weight, regularization_losses=self.losses)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 139, in __call__
losses = call_fn(y_true, y_pred)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 243, in call
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "<ipython-input-39-245f12eafcef>", line 9, in ZNCC
top = tf.tensordot(u,v,1)
Node: 'ZNCC/Tensordot/MatMul'
Matrix size-incompatible: In[0]: [128,3490], In[1]: [128,3490]
[[{{node ZNCC/Tensordot/MatMul}}]] [Op:__inference_train_function_3878]
I trying to run on a docker created as follows:
docker run --gpus=all -it -p "8888:8888" -v "/home/miguel/ml-resnet-50/:/notebooks/" --name ml-resnet-50 tensorflow/tensorflow:1.5.0-gpu-py3 jupyter notebook --ip 0.0.0.0 --no-browser --allow-root
On a Linux PC Ubuntu 20.04 with RTX 3070 Nvidia Card the follow code:
model.fit(
x=imgs_train,
y=clss_train,
batch_size=16,
epochs=2,
verbose=1,
validation_data=(imgs_val, clss_val)
)
And getting following error:
InternalError: Blas SGEMM launch failed : m=48400, n=64, k=64
[[Node: res2a_branch2a/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC",
dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1],
use_cudnn_on_gpu=true,
_device="/job:localhost/replica:0/task:0/device:GPU:0"](max_pooling2d/MaxPool,
res2a_branch2a/kernel/read)]] [[Node: loss/mul/_2859 =
_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_15435_loss/mul",
tensor_type=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Caused by op 'res2a_branch2a/Conv2D', defined at: File
"/usr/lib/python3.5/runpy.py", line 184, in _run_module_as_main
"main", mod_spec) File "/usr/lib/python3.5/runpy.py", line 85, in _run_code
exec(code, run_globals) File "/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py", line
16, in
app.launch_new_instance() File "/usr/local/lib/python3.5/dist-packages/traitlets/config/application.py",
line 658, in launch_instance
app.start() File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelapp.py", line
478, in start
self.io_loop.start() File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/ioloop.py", line
177, in start
super(ZMQIOLoop, self).start() File "/usr/local/lib/python3.5/dist-packages/tornado/ioloop.py", line 888,
in start
handler_func(fd_obj, events) File "/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py",
line 277, in null_wrapper
return fn(*args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py",
line 440, in _handle_events
self._handle_recv() File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py",
line 472, in _handle_recv
self._run_callback(callback, msg) File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py",
line 414, in _run_callback
callback(*args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py",
line 277, in null_wrapper
return fn(*args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line
283, in dispatcher
return self.dispatch_shell(stream, msg) File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line
233, in dispatch_shell
handler(stream, idents, msg) File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line
399, in execute_request
user_expressions, allow_stdin) File "/usr/local/lib/python3.5/dist-packages/ipykernel/ipkernel.py", line
208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent) File
"/usr/local/lib/python3.5/dist-packages/ipykernel/zmqshell.py", line
537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs) File
"/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py",
line 2728, in run_cell
interactivity=interactivity, compiler=compiler, result=result) File
"/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py",
line 2850, in run_ast_nodes
if self.run_code(code, result): File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py",
line 2910, in run_code
exec(code_obj, self.user_global_ns, self.user_ns) File "", line 2, in
model = get_model() File "", line 4, in get_model
model = ResNet50(include_top=False,input_shape=(pipeline['img_height'],
pipeline['img_width'], 3)) File
"/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/applications/resnet50.py",
line 235, in ResNet50
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) File
"/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/applications/resnet50.py",
line 122, in conv_block
name=conv_name_base + '2a')(input_tensor) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/engine/topology.py",
line 258, in call
output = super(Layer, self).call(inputs, **kwargs) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py",
line 652, in call
outputs = self.call(inputs, *args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/convolutional.py",
line 167, in call
outputs = self._convolution_op(inputs, self.kernel) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py",
line 838, in call
return self.conv_op(inp, filter) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py",
line 502, in call
return self.call(inp, filter) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py",
line 190, in call
name=self.name) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_nn_ops.py",
line 639, in conv2d
data_format=data_format, dilations=dilations, name=name) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py",
line 787, in _apply_op_helper
op_def=op_def) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py",
line 3160, in create_op
op_def=op_def) File "/usr/local/lib/python3.5/dist-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=48400, n=64, k=64 [[Node: res2a_branch2a/Conv2D =
Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1],
padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true,
_device="/job:localhost/replica:0/task:0/device:GPU:0"](max_pooling2d/MaxPool,
res2a_branch2a/kernel/read)]] [[Node: loss/mul/_2859 =
_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_15435_loss/mul",
tensor_type=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Any idea why it happeds?
I have created a custom layer in keras, which simply perform a dot product between the input and a kernel. But for the kernel I wanted to use the mean of the batch as a kernel initialization, meaning taking the mean of the batch and producing a kernel which initial value is that mean. To do so I have created a custom kernel initializer as follow:
class Tensor_Init(Initializer):
"""Initializer that generates tensors initialized to a given tensor.
# Arguments
Tensor: the generator tensors.
"""
def __init__(self, Tensor=None):
self.Tensor = Tensor
def __call__(self, shape, dtype=None):
return tf.Variable(self.Tensor)
def get_config(self):
return {'Tensor': self.Tensor}
This is the call method of the custom layer in keras. I simply compute the mean of the batch and use it with the above initializer class to produce a kernel. I use it as follow in the custom layer
def call(self, inputs):
data_format = conv_utils.convert_data_format(self.data_format, self.rank + 2)
inputs = tf.extract_image_patches(
inputs,
ksizes=(1,) + self.kernel_size + (1,),
strides=(1,) + self.strides + (1,),
rates=(1,) + self.dilation_rate + (1,),
padding=self.padding.upper(),
)
inputs = K.reshape(inputs,[-1,inputs.get_shape().as_list()[1],inputs.get_shape().as_list()
[2],self.kernel_size[0]*self.kernel_size[1] ,self.output_dim])
self.kernel = self.add_weight(name='kernel',shape=(),initializer=Tensor_Init(Tensor=tf.reduce_mean(inputs, 0)),trainable=True)
outputs = (tf.einsum('NHWKC,HWKC->NHWC',inputs,self.kernel)+self.c)**self.p
if self.data_format == 'channels_first':
outputs = K.permute_dimensions(outputs, (0, 3, 1, 2))
return outputs
Th e model is created and compiled normaly but I start training I am getting this error
InvalidArgumentError: You must feed a value for placeholder tensor 'conv2d_1_input' with dtype float and shape [?,48,48,3]
[[node conv2d_1_input (defined at C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py:736) ]]
Original stack trace for 'conv2d_1_input':
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
app.start()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\kernelapp.py", line 563, in start
self.io_loop.start()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\platform\asyncio.py", line 148, in start
self.asyncio_loop.run_forever()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\asyncio\base_events.py", line 438, in run_forever
self._run_once()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\asyncio\base_events.py", line 1451, in _run_once
handle._run()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\asyncio\events.py", line 145, in _run
self._callback(*self._args)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\ioloop.py", line 690, in <lambda>
lambda f: self._run_callback(functools.partial(callback, future))
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\ioloop.py", line 743, in _run_callback
ret = callback()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 787, in inner
self.run()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 748, in run
yielded = self.gen.send(value)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py", line 378, in dispatch_queue
yield self.process_one()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 225, in wrapper
runner = Runner(result, future, yielded)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 714, in __init__
self.run()
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 748, in run
yielded = self.gen.send(value)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py", line 365, in process_one
yield gen.maybe_future(dispatch(*args))
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 209, in wrapper
yielded = next(result)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py", line 272, in dispatch_shell
yield gen.maybe_future(handler(stream, idents, msg))
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 209, in wrapper
yielded = next(result)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py", line 542, in execute_request
user_expressions, allow_stdin,
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tornado\gen.py", line 209, in wrapper
yielded = next(result)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\ipkernel.py", line 294, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\ipykernel\zmqshell.py", line 536, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py", line 2855, in run_cell
raw_cell, store_history, silent, shell_futures)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in _run_cell
return runner(coro)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\async_helpers.py", line 68, in _pseudo_sync_runner
coro.send(None)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py", line 3058, in run_cell_async
interactivity=interactivity, compiler=compiler, result=result)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py", line 3249, in run_ast_nodes
if (await self.run_code(code, result, async_=asy)):
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py", line 3326, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-2-35eda01d200a>", line 75, in <module>
model = create_vgg16()
File "<ipython-input-2-35eda01d200a>", line 12, in create_vgg16
model.add(Conv2D(64, (5, 5), input_shape=(48,48,3), padding='same'))
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\engine\sequential.py", line 162, in add
name=layer.name + '_input')
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\engine\input_layer.py", line 178, in Input
input_tensor=tensor)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\engine\input_layer.py", line 87, in __init__
name=self.name)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py", line 736, in placeholder
shape=shape, ndim=ndim, dtype=dtype, sparse=sparse, name=name)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\backend.py", line 998, in placeholder
x = array_ops.placeholder(dtype, shape=shape, name=name)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\array_ops.py", line 2143, in placeholder
return gen_array_ops.placeholder(dtype=dtype, shape=shape, name=name)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 7401, in placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 3616, in create_op
op_def=op_def)
File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
I was able to pass the mean of the batch to the kernel by simply creating a zero initialized kernel then assigning the mean value to it, without even creating a custom initilizer. I modified the custom layer as follow
def call(self, inputs):
data_format = conv_utils.convert_data_format(self.data_format, self.rank + 2)
inputs = tf.extract_image_patches(
inputs,
ksizes=(1,) + self.kernel_size + (1,),
strides=(1,) + self.strides + (1,),
rates=(1,) + self.dilation_rate + (1,),
padding=self.padding.upper(),
)
inputs = K.reshape(inputs,[-1,inputs.get_shape().as_list()[1],inputs.get_shape().as_list()
[2],self.kernel_size[0]*self.kernel_size[1] ,self.output_dim])
weights = tf.reduce_mean(inputs, 0)
self.kernel = self.add_weight(name='kernel',
shape=(weights.get_shape().as_list()[0],weights.get_shape().as_list()
[1],weights.get_shape().as_list()[2],weights.get_shape().as_list()[3]),
initializer='zeros',
trainable=True)
tf.compat.v1.assign(self.kernel, weights)
outputs = (tf.einsum('NHWKC,HWKC->NHWC',inputs,self.kernel)+self.c)**self.p
if self.data_format == 'channels_first':
outputs = K.permute_dimensions(outputs, (0, 3, 1, 2))
return outputs
I am trying to use the graph transform tool on a tensorflow object detection model for tensorflow 1.4.1 in Linux Ubuntu 16.04
The instruction used is:
bazel-bin/tensorflow/tools/graph_transforms/transform_graph --in_graph=/tf-optimizations/pascalvoc_gtt/frozen_inference_graph.pb --out_graph=/tf-optimizations/pascalvoc_gtt/optimized_frozen_inference_graph.pb --inputs='image_tensor' --outputs='detection_boxes,detection_scores,detection_classes,num_detections' --transforms='
add_default_attributes
strip_unused_nodes(type=float)
remove_nodes(op=CheckNumerics)
fold_constants(ignore_errors=true)
fold_batch_norms
fold_old_batch_norms
fuse_resize_pad_and_conv
fuse_pad_and_conv
fuse_resize_and_conv
strip_unused_nodes
sort_by_execution_order'
When I try to query the optimized tensorflow graph,
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections], feed_dict={image_tensor: image_np_expanded})
I get the following error:
InvalidArgumentError: NodeDef mentions attr 'identical_element_shapes' not in Op<name=TensorArrayV3; signature=size:int32 -> handle:resource, flow:float; attr=dtype:type; attr=element_shape:shape,default=<unknown>; attr=dynamic_size:bool,default=false; attr=clear_after_read:bool,default=true; attr=tensor_array_name:string,default=""; is_stateful=true>; NodeDef: Preprocessor/map/TensorArray = TensorArrayV3[clear_after_read=true, dtype=DT_FLOAT, dynamic_size=false, element_shape=<unknown>, identical_element_shapes=false, tensor_array_name="", _device="/job:localhost/replica:0/task:0/device:GPU:0"](Preprocessor/map/TensorArrayUnstack/strided_slice). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
[[Node: Preprocessor/map/TensorArray = TensorArrayV3[clear_after_read=true, dtype=DT_FLOAT, dynamic_size=false, element_shape=<unknown>, identical_element_shapes=false, tensor_array_name="", _device="/job:localhost/replica:0/task:0/device:GPU:0"](Preprocessor/map/TensorArrayUnstack/strided_slice)]]
Caused by op u'Preprocessor/map/TensorArray', defined at:
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/usr/local/lib/python2.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python2.7/dist-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelapp.py", line 478, in start
self.io_loop.start()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 281, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 232, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 397, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-7-982229c93a39>", line 7, in <module>
tf.import_graph_def(od_graph_def, name='')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py", line 313, in import_graph_def
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): NodeDef mentions attr 'identical_element_shapes' not in Op<name=TensorArrayV3; signature=size:int32 -> handle:resource, flow:float; attr=dtype:type; attr=element_shape:shape,default=<unknown>; attr=dynamic_size:bool,default=false; attr=clear_after_read:bool,default=true; attr=tensor_array_name:string,default=""; is_stateful=true>; NodeDef: Preprocessor/map/TensorArray = TensorArrayV3[clear_after_read=true, dtype=DT_FLOAT, dynamic_size=false, element_shape=<unknown>, identical_element_shapes=false, tensor_array_name="", _device="/job:localhost/replica:0/task:0/device:GPU:0"](Preprocessor/map/TensorArrayUnstack/strided_slice). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
[[Node: Preprocessor/map/TensorArray = TensorArrayV3[clear_after_read=true, dtype=DT_FLOAT, dynamic_size=false, element_shape=<unknown>, identical_element_shapes=false, tensor_array_name="", _device="/job:localhost/replica:0/task:0/device:GPU:0"](Preprocessor/map/TensorArrayUnstack/strided_slice)]]
I do not know what is wrong, as the original frozen graph works fine.
Problem solved. Its a version issue. The model was generated in a different version than the GTT.
I have implemented autoencoder on my custom images data for sign language recognition.Now i want to save tensors object of the output layer to an numpy array. I tried Session.run(tensor) and tensor.eval(). Here is my code.
#define model
x= tf.placeholder(tf.float32,[None,784])
y_=tf.placeholder(tf.float32,[None,6])
k=190
l=180
m=150
n=130
o=100
num_of_epoch=10
w1=tf.Variable(tf.truncated_normal([784,k],stddev=0.1))
b1=tf.Variable(tf.zeros([k]))
w2=tf.Variable(tf.truncated_normal([k,l],stddev=0.1))
b2=tf.Variable(tf.zeros([l]))
w3=tf.Variable(tf.truncated_normal([l,m],stddev=0.1))
b3=tf.Variable(tf.zeros([m]))
w4=tf.Variable(tf.truncated_normal([m,n],stddev=0.1))
b4=tf.Variable(tf.zeros([n]))
w5=tf.Variable(tf.truncated_normal([n,o],stddev=0.1))
b5=tf.Variable(tf.zeros([o]))
w6=tf.Variable(tf.truncated_normal([o,6],stddev=0.1))
b6=tf.Variable(tf.zeros([6]))
y1=tf.nn.relu(tf.matmul(x,w1)+b1)
y2=tf.nn.relu(tf.matmul(y1,w2)+b2)
y3=tf.nn.relu(tf.matmul(y2,w3)+b3)
y4=tf.nn.relu(tf.matmul(y3,w4)+b4)
y5=tf.nn.relu(tf.matmul(y4,w5)+b5)
y=tf.nn.softmax(tf.matmul(y5,w6)+b6)
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),
reduction_indices=[1]))
train_step=tf.train.GradientDescentOptimizer(0.03).minimize(cross_entropy)
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(num_of_epoch):
train_data = {x:x_train,y_:y_train}
sess.run(train_step,feed_dict=train_data)
currect_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(currect_prediction,tf.float32))
sess.run(accuracy,feed_dict={x:x_train,y_:y_train})
currect_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(currect_prediction,tf.float32))
sess.run(accuracy,feed_dict= {x:x_test,y_:y_test})
y_p = tf.argmax(y, 1).eval() #this line shows me the error
print(y_p)
I am getting the below error. How can I fix this error and save tensor data to numpy array ?
Traceback (most recent call last):
File "<ipython-input-45-5e38490a3e8e>", line 1, in <module>
runfile('C:/Users/RIFAT/PycharmProjects/tensorflow_autoencoder
/autoencoderreconstruction.py',
wdir='C:/Users/RIFAT/PycharmProjects/tensorflow_autoencoder')
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils
\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils
\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/RIFAT/PycharmProjects/tensorflow_autoencoder
/autoencoderreconstruction.py", line 112, in <module>
y_p = tf.argmax(y, 1).eval()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\framework\ops.py", line 606, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\framework\ops.py", line 3928, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python\client
\session.py", line 789, in run
run_metadata_ptr)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python\client
\session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python\client
\session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python\client
\session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
InvalidArgumentError: Shape [-1,784] has negative dimensions
[[Node: Placeholder_62 = Placeholder[dtype=DT_FLOAT, shape=[?,784],
_device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'Placeholder_62', defined at:
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils\ipython
\start_kernel.py", line 231, in <module>
main()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils\ipython
\start_kernel.py", line 227, in main
kernel.start()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel\kernelapp.py",
line 477, in start
ioloop.IOLoop.instance().start()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\zmq\eventloop
\ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tornado\ioloop.py", line
888, in start
handler_func(fd_obj, events)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tornad
\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\zmq\eventloop
\zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\zmq\eventloop
\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\zmq\eventloop
\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tornado
\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel
\kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel
\kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel
\kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel\ipkernel.py",
line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\ipykernel\zmqshell.py",
line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\IPython
\core\interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\IPython
\core\interactiveshell.py", line 2827, in run_ast_nodes
if self.run_code(code, result):
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\IPython
\core\interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-45-5e38490a3e8e>", line 1, in <module>
runfile('C:/Users/RIFAT/PycharmProjects/tensorflow_autoencoder
/autoencoderreconstruction.py', wdir='C:/Users/RIFAT/PycharmProjects
/tensorflow_autoencoder')
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils
\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\spyder\utils
\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/RIFAT/PycharmProjects/tensorflow_autoencoder
/autoencoderreconstruction.py", line 62, in <module>
x= tf.placeholder(tf.float32,[None,784])
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\ops\array_ops.py", line 1530, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\ops\gen_array_ops.py", line 1954, in _placeholder
name=name)
File "C:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
File "C:\Users\RIFAT\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:\Users\RIFAT\Anaconda3\lib\site-packages\tensorflow\python
\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Shape [-1,784] has
negative dimensions
[[Node: Placeholder_62 = Placeholder[dtype=DT_FLOAT, shape=[?,784],
_device="/job:localhost/replica:0/task:0/cpu:0"]()]]
That's because y is a tensor in the graph and not a variable. When you run .eval() on a variable, it gives you the current value held by that variable in that session but if you run .eval() on a tensor instead like tf.argmax(y, 1).eval() in your case then tensor flow runs the graph to that node to get the value of that node. And since in your case, it doesn't get the value of the placeholder x and y_ while running the graph, it gives the error. One way to resolve this error is by passing the values of the placeholders in your eval call like this:
tf.argmax(y, 1).eval(feed_dict= {x:x_test,y_:y_test})
But, a more preferred way is giving the context of your session to the eval call in which case it will return the value of the tensor. Ex:
tf.argmax(y, 1).eval(session = sess)
Your question is not 100% clear. But the error you are seeing is caused by the fact that you try to run the graph without the feed dict in place. To see the output of the prediction (that is with the argmax(y, 1) present) you'd simply run:
y_p = sess.run(tf.argmax(y, 1), feed_dict=train_data)
print(y_p)
But that will give you the actual predicted value (on the train data as this is fed, to get this on the test data, simply geed in the test_data). To get the probabilities you'd pull y without the argmax:
y_p = sess.run(y, feed_dict=train_data)
print(y_p)