yanghhx

when run'demo_camera.py', error like this

2

File "demo_camera.py", line 15, in print(f"Torch device: {torch.cuda.get_device_name()}") TypeError: get_device_name() missing 1 required positional argument: 'device'

When I run the main.py, it comes out the question. How can I solve it?

ImportError: cannot import name 'import_class' from 'torchlight'

2

I have finished the torchlight installed ,but it remains the import error: Processing dependencies for torchlight==1.0 Finished processing dependencies for torchlight==1.0 ImportError: cannot import name 'import_class' from 'torchlight'

ModuleNotFoundError: No module named 'data_gen'

2

how can I solve it?

TypeError: gendata() got an unexpected keyword argument 'part'

3

when I run a commad "python ntu_gen_preprocess.py xsub train".It appears the problem :Traceback (most recent call last): File "ntu_gen_preprocess.py", line 143, in gendata(arg.data_path, out_path, arg.ignored_sample_path, benchmark=b, part=sn) TypeError: gendata() got...

how to get epoch99_model1.pt?

1

File Not Found Error: [Errno 2] No such file or directory: './work_dir/recognition/ntu-xsub/AS_GCN/max_hop_4/lamda_05/epoch99_model1.pt'

关于zero-shot测试和few-shot测试的设置问题

3

你好,请问zero-shot的实验是把有seen类别的数据结果当做预训练模型,然后直接把这个预训练的模型拿来直接预测unseen类别么?zero-shot的测试跟一般的测试只是测试集不一样吗?另外few-shot如何划分样本集呢?

accuracy for nw-ucla data is below 97.2%

4

I have run your code according your settings, but I have got the accuracy for NW-UCLA 96.12%.

The linear evaluation is very low

2

I have run your code and the linear evaluation accuracy is only 45.84%. When I set the "param.requires_grad =True" in line 44,49,54 of linear.py, the linear evalution accuracy of NTU60...

Thanks for your sharing and your work is very excellent. I'd like to know how to fine-tune CrosSCLR and have the fine-tuning step been included in your code? What is...