search

clausmichele / ViDeNN

ViDeNN - Deep Blind Video Denoising
MIT License
232 stars 35 forks source link

unexpected keyword "labels" #36

Closed ajeema closed 1 year ago

ajeema commented 1 year ago

Going through the documentation, when I get to running main_temp3CNN.py I get the following errors.

2023-09-27 01:16:46.861651: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0. 2023-09-27 01:16:46.911723: 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 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-09-27 01:16:47.934225: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT GPU

2023-09-27 01:16:51.034872: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:47] Overriding orig_value setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0. 2023-09-27 01:16:51.034925: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1639] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 28359 MB memory: -> device: 0, name: NVIDIA A100-SXM4-40GB, pci bus id: 0000:00:04.0, compute capability: 8.0 /content/drive/MyDrive/ViDeNN/Temp3-CNN/model_temp3CNN.py:16: UserWarning: tf.layers.conv2d is deprecated and will be removed in a future version. Please Use tf.keras.layers.Conv2D instead. output = tf.compat.v1.layers.conv2d(input, 128, 3, padding='same', activation=tf.nn.leaky_relu) /content/drive/MyDrive/ViDeNN/Temp3-CNN/model_temp3CNN.py:19: UserWarning: tf.layers.conv2d is deprecated and will be removed in a future version. Please Use tf.keras.layers.Conv2D instead. output = tf.compat.v1.layers.conv2d(output, 64, 3, padding='same', name='conv%d' % layers, use_bias=False) /content/drive/MyDrive/ViDeNN/Temp3-CNN/model_temp3CNN.py:22: UserWarning: tf.layers.conv2d is deprecated and will be removed in a future version. Please Use tf.keras.layers.Conv2D instead. output = tf.compat.v1.layers.conv2d(output, output_channels, 3, padding='same', use_bias=False) Traceback (most recent call last): File "/content/drive/MyDrive/ViDeNN/Temp3-CNN/main_temp3CNN.py", line 96, in tf.compat.v1.app.run() File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/platform/app.py", line 36, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/usr/local/lib/python3.10/dist-packages/absl/app.py", line 308, in run _run_main(main, args) File "/usr/local/lib/python3.10/dist-packages/absl/app.py", line 254, in _run_main sys.exit(main(argv)) File "/content/drive/MyDrive/ViDeNN/Temp3-CNN/main_temp3CNN.py", line 74, in main model = TemporalDenoiser(sess) File "/content/drive/MyDrive/ViDeNN/Temp3-CNN/model_temp3CNN.py", line 42, in init self.eva_psnr = tfpsnr(self.Y, self.Y[:,:,:,3:6]) File "/content/drive/MyDrive/ViDeNN/Temp3-CNN/utilis.py", line 89, in tf_psnr mse = tf.losses.mean_squared_error(labels=im2 255.0, predictions=im1 255.0) File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler raise e.with_traceback(filtered_tb) from None File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/dispatch.py", line 1170, in op_dispatch_handler result = api_dispatcher.Dispatch(args, kwargs) TypeError: Got an unexpected keyword argument 'labels'

Everything up until this step worked fine. Any idea what could be the issue?

ajeema commented 1 year ago

Found the answer, I had updated the other scripts to tf2 but forgot to update this file. Leaving this here and closing in case anyone else runs into this issue.