YanjunChen

icon location SH,CHINA icon location work harder and harder~

Results 7 comments of YanjunChen

RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/torch/lib/THC/generated/../THCReduceAll.cuh:339 terminate called after throwing an instance of 'std::runtime_error' what(): cuda runtime error (59) : device-side assert triggered at /pytorch/torch/lib/THC/generic/THCStorage.c:184

It seems get_labels module in hmdb51_json will produce a null string as a class. Change the module as follows will work. `def get_labels(csv_dir_path): labels = [] for file_path in csv_dir_path.iterdir():...

Details

> 感谢作者大大非常好的工作~我有一些疑问 > > 1. 请问在NTU-60和NTU-120上的各个单串流的准确率是多少？ > > 2. 我发现config文件中关于ntu数据集的模型设置与论文中所描述的有所不一样，它没有使用“时间注意力”，请问这是推荐的设置？还是重现过程中的一个小错误~ > > 3. 推荐的batch_size * GPUs 参数是多少？对于不同的数据集需要多少个GPU > > 4. 怎么deouple数据，论文中的spatial-temporal是指原始joint数据么？spatial指的是bone数据么？具体改怎么修改来decouple？ > > > 再次非常感谢~ 你好，我对于decouple的理解和你是一样的，请问你有在spatial数据上跑结果吗？我在NTU和SHREC上跑的结果，spatial比spatial-temporal低好多~

ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn'

you can set line 249 as self.global_step = 0 since initial command is to load the epoch number of the model when it has one.

Error Loading pretrained weights

> For the first issue, try to change the name of self.down to self.conv_res in > > https://github.com/lshiwjx/2s-AGCN/blob/d4880e1cfc0822cc86beb2c9dd7463f904dd40ea/model/agcn.py#L72 > > For the second issue, try to change the name of...

Error Loading pretrained weights

`[ Sun Oct 25 02:03:25 2020 ] Load weights from ./runs/ntu_cv_agcn_joint-49-29400.pt. [ Sun Oct 25 02:03:25 2020 ] using warm up, epoch: 0 [ Sun Oct 25 02:03:25 2020 ]...

Error Loading pretrained weights

> `[ Sun Oct 25 02:03:25 2020 ] Load weights from ./runs/ntu_cv_agcn_joint-49-29400.pt. [ Sun Oct 25 02:03:25 2020 ] using warm up, epoch: 0 [ Sun Oct 25 02:03:25 2020...

Auxiliary losses implementations

> Hi, Guadalupe is right that it was cross entropy loss for link pred loss. The reason is that since the assignment prediction contains values between [0,1], cross entropy is...