Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Trying to get your project to go on my computer but getting these final errors - Please help #1

Open
seandrews opened this issue Oct 18, 2021 · 4 comments
Open

Trying to get your project to go on my computer but getting these final errors - Please help #1

seandrews opened this issue Oct 18, 2021 · 4 comments

Comments

@seandrews
Copy link

C:\Users\Stephen\venv\Scripts\python.exe C:/Users/Stephen/PycharmProjects/Stocks-Prediction/tesla/BGRU_LSTM.py
2021-10-18 23:27:59.979789: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cudart64_110.dll
2021-10-18 23:28:04.304261: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library nvcuda.dll
2021-10-18 23:28:05.505473: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1650 Ti computeCapability: 7.5
coreClock: 1.485GHz coreCount: 16 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 178.84GiB/s
2021-10-18 23:28:05.505823: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cudart64_110.dll
2021-10-18 23:28:05.514343: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cublas64_11.dll
2021-10-18 23:28:05.514544: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cublasLt64_11.dll
2021-10-18 23:28:05.520595: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cufft64_10.dll
2021-10-18 23:28:05.522458: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library curand64_10.dll
2021-10-18 23:28:05.525636: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cusolver64_11.dll
2021-10-18 23:28:05.529390: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cusparse64_11.dll
2021-10-18 23:28:05.530409: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cudnn64_8.dll
2021-10-18 23:28:05.530640: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0
2021-10-18 23:28:05.531024: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-10-18 23:28:05.532899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1650 Ti computeCapability: 7.5
coreClock: 1.485GHz coreCount: 16 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 178.84GiB/s
2021-10-18 23:28:05.533461: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0
2021-10-18 23:28:05.990579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-10-18 23:28:05.990779: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0
2021-10-18 23:28:05.990884: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N
2021-10-18 23:28:05.991112: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2143 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce GTX 1650 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
WARNING:tensorflow:Please add keras.layers.InputLayer instead of keras.Input to Sequential model. keras.Input is intended to be used by Functional model.
Traceback (most recent call last):
File "C:\Users\Stephen\PycharmProjects\Stocks-Prediction\tesla\BGRU_LSTM.py", line 32, in
model = rnn_model.build_model(input_shape, layers)
File "C:\Users\Stephen\PycharmProjects\Stocks-Prediction\tesla\rnn_model.py", line 12, in build_model
model.add(layer)
File "C:\Users\Stephen\venv\lib\site-packages\tensorflow\python\training\tracking\base.py", line 522, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\base_layer.py", line 945, in call
return self._functional_construction_call(inputs, args, kwargs,
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\base_layer.py", line 1083, in _functional_construction_call
outputs = self._keras_tensor_symbolic_call(
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\base_layer.py", line 816, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\base_layer.py", line 856, in _infer_output_signature
outputs = call_fn(inputs, *args, **kwargs)
File "C:\Users\Stephen\venv\lib\site-packages\keras\engine\functional.py", line 1442, in call
return getattr(self._module, self._method_name)(*args, **kwargs)
File "C:\Users\Stephen\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1023, in call
self._maybe_build(inputs)
File "C:\Users\Stephen\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 2625, in _maybe_build
self.build(input_shapes) # pylint:disable=not-callable
File "C:\Users\Stephen\venv\lib\site-packages\tensorflow_addons\layers\normalizations.py", line 110, in build
self._check_size_of_dimensions(input_shape)
File "C:\Users\Stephen\venv\lib\site-packages\tensorflow_addons\layers\normalizations.py", line 236, in _check_size_of_dimensions
raise ValueError(
ValueError: Number of groups (32) must be a multiple of the number of channels (100).
@kochlisGit
Copy link
Owner

kochlisGit commented Oct 18, 2021 •
edited

Hello,

This file was written before the lastest Tensorflow addons update, however, it's not much different now..!! Basically, GroupNormalization layer uses "N" groups to normalize its input. The number of groups should be a multiplier of the number of input units, which is 100 in this example. By default, the tensorflow_addons library uses n_groups=32 as a default number of groups in the GroupNormalization layer, which is not a multiplier of 100.

For example, if you use a GRU with 100 units, then acceptable "n_groups" are for example: 2, 5, 10, 20, 25, 50, 100

That being said, you could try to add the following argument:

GroupNormalization(n_groups=25)

This should be working.

@seandrews
Copy link
Author

seandrews commented Oct 18, 2021 via email

@kochlisGit
Copy link
Owner

It looks like there is a mismatch error with the version of keras and tensorflow_addons modules that you have installed in your device. The best solution here is to update both tensorflow & tensorflow_addons versions in your machine.

However, If this is not possible, try replacing Yogi with "adam" algorithm
optimizers='adam' , which is supported just fine!
Google's YOGI is based on adam's algorithm and it's only 1 line of code that it differs from the implementation of adam, so there won't be much difference anyway.

@seandrews
Copy link
Author

seandrews commented Oct 19, 2021 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@seandrews @kochlisGit