AS-GCN
AS-GCN copied to clipboard
limaosen0
The model architecture of AS-GCN (for human action recognition)
Since I didn't find the code you used to package the data, I used the ntu rgb-d dataset directly when training [st-gcn](https://github.com/yysijie/st-gcn), but this input doesn't seem to fit your...
Can you explain the AIM's loss function? I can understand it. Thank you vert much！
rel_rec = self.rel_rec.cuda(gpu_id) rel_send = self.rel_send.cuda(gpu_id) self.logits = self.encoder(x, rel_rec, rel_send) The dim of rel_rec and rel_send is 【600，25】,but I can not understand what they mean about human skeleton. AIM...
Like the samples_with_missing_skeletons.txt you provided for NTU-RGB+D,I would appreciate it if you could show me the same way to get the file for NTU-RGB+D120.
I did the warmup pretraining for 9 epochs (instead of your 10 epochs) and that worked okay, and wanted to continue with the `train` part but hit that error then...
Hi, Do you happen to have the `kinetics` config available to share so that your results are easier to reproduce as your repo seemed to contain only the `NTU-RGBD` configs?...
`class Model(nn.Module): ······ def forward(self, x, x_target, x_last, A_act, lamda_act): print("A_act.shape = {}, lamda_act = {}".format(A_act.shape) >>> A_act.shape=2,2,25,25 What's the A_act?
