againerju / tcg_recognition

Training and evaluation kit for traffic control gesture recognition on the TCG dataset.
MIT License
21 stars 6 forks source link

Shape mismatch in layer #0 #2

Open chrissunny94 opened 1 year ago

chrissunny94 commented 1 year ago

ValueError: Shape mismatch in layer #0 (named tcn_1) for weight tcn_1/residual_block_0/conv1D_0/kernel:0. Weight expects shape (2, 64, 64). Received saved weight with shape (1, 64, 64)

python3 evaluate.py 2023-07-23 09:13:34.893970: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-07-23 09:13:35.435343: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT <configparser.ConfigParser object at 0x7f443f70f7c0> /home/chris/AI/tcg_recognition/config/../baselines/tcn_xv_major Finished opening TCG dataset. 2023-07-23 09:13:42.535148: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:995] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 2023-07-23 09:13:42.557690: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1960] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... Traceback (most recent call last): File "/home/chris/AI/tcg_recognition/evaluate.py", line 92, in <module> performance = test_model(config, baseline_path) File "/home/chris/AI/tcg_recognition/evaluate.py", line 35, in test_model model = utils.load_model_TCN(os.path.join(model_name, "combination_{}".format(run_id+1))) File "/home/chris/AI/tcg_recognition/utils.py", line 330, in load_model_TCN reloaded_model.load_weights(os.path.join(model_path + '.h5'),by_name=True) File "/home/chris/AI/tcg_recognition/venv_name/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler raise e.with_traceback(filtered_tb) from None File "/home/chris/AI/tcg_recognition/venv_name/lib/python3.10/site-packages/keras/src/saving/legacy/hdf5_format.py", line 943, in load_weights_from_hdf5_group_by_name raise ValueError( ValueError: Shape mismatch in layer #0 (named tcn_1) for weight tcn_1/residual_block_0/conv1D_0/kernel:0. Weight expects shape (2, 64, 64). Received saved weight with shape (1, 64, 64)