Problems when running Temporal Super-resolution Model

[xueziii]

When I try to execute the example commands in the Temporal Super-resolution Model section, I get the following error:

Traceback (most recent call last): File "Experimental_root/test.py", line 21, in test_pipeline(root_path) File "/home/adminroot/anaconda3/lib/python3.8/site-packages/basicsr/test.py", line 28, in test_pipeline test_set = build_dataset(dataset_opt) File "/home/adminroot/anaconda3/lib/python3.8/site-packages/basicsr/data/init.py", line 34, in build_dataset dataset = DATASET_REGISTRY.get(dataset_opt['type'])(dataset_opt) File "/home/adminroot/Desktop/xue/MetaPortrait-main/sr_model/Experimental_root/dataset/metaportrait_video_dataset.py", line 32, in init super(MetaportraitVideoRecurrentTestDataset, self).init(opt) File "/home/adminroot/anaconda3/lib/python3.8/site-packages/basicsr/data/video_test_dataset.py", line 99, in init raise ValueError(f'Non-supported video test dataset: {type(opt["name"])}') ValueError: Non-supported video test dataset: <class 'str'>

How can I solve it? Thanks!

[angussiu260]

I got the same problem. Please help

[xueziii]

I have solved this problem, don't install basicsr with pip, it is wrong to install the official basicsr. Uninstall it if you have it installed. Let the code import the basicsr in the sr_model file given by the author

@angussiu260