search

rizkiarm / LipNet

Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
MIT License
638 stars 226 forks source link

is this supposed to be run on python 2? #99

Open akouminov opened 4 years ago

akouminov commented 4 years ago

it seems that this should be run on python 2, please add in read me if so

iares777 commented 4 years ago

I also think this is for python 2, but installation error: File "c:\users\ares\appdata\local\temp\easy_install-ioi9x4\numpy-1.18.3\setup.py", line 32, in

these are required to build h5py

RuntimeError: Python version >= 3.5 required.

1

jeonsanghun commented 4 years ago

it seems that this should be run on python 2, please add in read me if so

I am now catching an error to change this code running in Python 2.7 to Python 3.6. If the code runs in 3.6, can you share it?

akouminov commented 4 years ago

I have a version that I modified if you would like to take a look akoumino/LipNet

jeonsanghun commented 4 years ago

I have a version that I modified if you would like to take a look akoumino/LipNet

Can I receive it by e-mail? (jeon7887@gmail.com) Is it correct with python 3.x and running fine?

nmstoker commented 4 years ago

@jeonsanghun - I think this is what you were after: https://github.com/akouminov/LipNet

Akouminov had accidentally missed a "v" out of his username name earlier

arindam999 commented 4 years ago

Hi @akouminov - running your code but running into following error. Any help ?

!./predict evaluation/models/overlapped-weights368.h5 evaluation/samples/id2_vcd_swwp2s.mpg

2020-09-21 02:55:54.328514: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1

Loading data from disk... Data loaded.

WARNING:tensorflow:From /content/LipNet/LipNet/lipnet/model2.py:15: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead.

2020-09-21 02:56:04.498704: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1 2020-09-21 02:56:04.558177: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.558868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:00:04.0 name: Tesla V100-SXM2-16GB computeCapability: 7.0 coreClock: 1.53GHz coreCount: 80 deviceMemorySize: 15.75GiB deviceMemoryBandwidth: 836.37GiB/s 2020-09-21 02:56:04.558911: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-09-21 02:56:04.558966: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2020-09-21 02:56:04.706921: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2020-09-21 02:56:04.707073: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2020-09-21 02:56:04.707102: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2020-09-21 02:56:04.733860: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2020-09-21 02:56:04.733997: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2020-09-21 02:56:04.734122: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.734888: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.735482: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2020-09-21 02:56:04.735846: 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: AVX512F To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2020-09-21 02:56:04.751132: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2000165000 Hz 2020-09-21 02:56:04.751413: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x26ffb80 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2020-09-21 02:56:04.751459: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2020-09-21 02:56:04.896747: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.897515: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xb058380 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2020-09-21 02:56:04.897572: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Tesla V100-SXM2-16GB, Compute Capability 7.0 2020-09-21 02:56:04.898950: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.899536: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:00:04.0 name: Tesla V100-SXM2-16GB computeCapability: 7.0 coreClock: 1.53GHz coreCount: 80 deviceMemorySize: 15.75GiB deviceMemoryBandwidth: 836.37GiB/s 2020-09-21 02:56:04.899621: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-09-21 02:56:04.899659: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2020-09-21 02:56:04.899682: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2020-09-21 02:56:04.899695: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2020-09-21 02:56:04.899708: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2020-09-21 02:56:04.899721: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2020-09-21 02:56:04.899734: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2020-09-21 02:56:04.899798: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.900359: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:04.900911: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2020-09-21 02:56:04.906025: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2020-09-21 02:56:08.762899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix: 2020-09-21 02:56:08.762957: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] 0 2020-09-21 02:56:08.762966: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0: N 2020-09-21 02:56:08.769087: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:08.769850: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-21 02:56:08.770436: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0. 2020-09-21 02:56:08.770503: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14756 MB memory) -> physical GPU (device: 0, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:04.0, compute capability: 7.0) Traceback (most recent call last): File "/content/LipNet/LipNet/evaluation/predict.py", line 60, in video, result = predict(sys.argv[1], sys.argv[2]) File "/content/LipNet/LipNet/evaluation/predict.py", line 53, in predict y_pred = lipnet.predict(X_data) File "/content/LipNet/LipNet/lipnet/model2.py", line 75, in predict return self.test_function([input_batch, 0])[0] # the first 0 indicates test File "/content/LipNet/LipNet/lipnet/model2.py", line 80, in test_function return K.function([self.input_data, K.learning_phase()], [self.y_pred, K.learning_phase()]) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 3936, in function model = models.Model(inputs=inputs, outputs=outputs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py", line 242, in new return functional.Functional(*args, kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py", line 457, in _method_wrapper result = method(self, *args, *kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py", line 115, in init self._init_graph_network(inputs, outputs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py", line 457, in _method_wrapper result = method(self, args, kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py", line 142, in _init_graph_network base_layer_utils.create_keras_history(self._nested_outputs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 191, in create_kerashistory , created_layers = _create_keras_history_helper(tensors, set(), []) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 226, in _create_keras_history_helper op = tensor.op # The Op that created this Tensor. AttributeError: 'int' object has no attribute 'op'

jainnimish commented 3 years ago

It can only run on Python 3.5 to Python 3.7 because TensorFlow only supports these versions of python as of October 2020.

akouminov commented 3 years ago

@arindam999 , have run into this before, this is an environment issue, if you still need it I can look into it for you