Trying to run demo video: missing keys in source state_dict

[DanielG1010]

Hello, I am new to the openMMLabs framework, I tried to run inference on a video by adding a demo_pipeline in the _base_/datasets/hazeworld.py which I have seen from other openMMLabs projects. Here is:

demo_pipeline = [
    dict(type='GenerateSegmentIndices', interval_list=[1]),
    dict(
        type='LoadImageFromFileList',
        io_backend='disk',
        key='lq',
        channel_order='rgb'),
    dict(type='RescaleToZeroOne', keys=['lq']),
    dict(type='FramesToTensor', keys=['lq']),
    dict(type='Collect', keys=['lq'], meta_keys=['lq_path', 'key'])
]

I tried to run inference on the video with the restoration_video_inference() but I am not sure if this function could work for this model, or what could be the problem, in any case I am getting this:

(map-net) dgonzalez@R730-K80:~/map-net/MAP-Net$ python demo/demo.py --window-size 3 configs/dehazers/mapnet/mapnet_hazeworld.py mapnet_hazeworld_40k.pth demo1_input demo1_output
/home/dgonzalez/anaconda3/envs/map-net/lib/python3.10/site-packages/mmcv/__init__.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
  warnings.warn(
2023-08-26 13:16:18,525 - mmedit - INFO - Init weights: None
2023-08-26 13:16:18,538 - mmcv - INFO - initialize ConvNeXt with init_cfg {'type': 'Pretrained', 'checkpoint': 'https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-tiny_3rdparty_32xb128-noema_in1k_20220301-795e9634.pth', 'prefix': 'backbone.'}
2023-08-26 13:16:18,538 - mmcv - INFO - load backbone. in model from: https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-tiny_3rdparty_32xb128-noema_in1k_20220301-795e9634.pth
load checkpoint from http path: https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-tiny_3rdparty_32xb128-noema_in1k_20220301-795e9634.pth
2023-08-26 13:16:18,633 - mmcv - WARNING - The model and loaded state dict do not match exactly

missing keys in source state_dict: norm0.weight, norm0.bias, norm1.weight, norm1.bias, norm2.weight, norm2.bias, norm3.weight, norm3.bias

load checkpoint from local path: mapnet_hazeworld_40k.pth
Traceback (most recent call last):
  File "/home/dgonzalez/map-net/MAP-Net/demo/demo.py", line 86, in <module>
    main()
  File "/home/dgonzalez/map-net/MAP-Net/demo/demo.py", line 62, in main
    output = restoration_video_inference(model, args.input_dir,
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/apis/restoration_video_inference.py", line 112, in restoration_video_inference
    result.append(model(lq=data_i, test_mode=True)['output'].cpu())
  File "/home/dgonzalez/anaconda3/envs/map-net/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/dgonzalez/anaconda3/envs/map-net/lib/python3.10/site-packages/mmcv/runner/fp16_utils.py", line 119, in new_func
    return old_func(*args, **kwargs)
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/models/dehazers/basic_dehazer.py", line 79, in forward
    return self.forward_test(lq, gt, **kwargs)
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/models/dehazers/map.py", line 164, in forward_test
    output = self._get_output_from_dict(self.generator(lq))
  File "/home/dgonzalez/anaconda3/envs/map-net/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/models/backbones/map_backbones/mapnet_net.py", line 376, in forward
    feats = self.decode(feats)
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/models/backbones/map_backbones/mapnet_net.py", line 338, in decode
    feats = self.prior_decoder_layers[s](feats)
  File "/home/dgonzalez/anaconda3/envs/map-net/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/dgonzalez/map-net/MAP-Net/mmedit/models/backbones/map_backbones/mapnet_net.py", line 64, in forward
    .view(1, self.num_trans_bins, 1, 1).to(prob_t.device).repeat(b, 1, h, w)
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

I took the demo.py script from BasicVSR++ repository.