The problem about self.rel_rec and self.rel_send

limaosen0 / AS-GCN

The model architecture of AS-GCN (for human action recognition)

BSD 2-Clause "Simplified" License

290 stars 71 forks source link

The problem about self.rel_rec and self.rel_send #17

Open 1zgh opened 5 years ago

1zgh commented 5 years ago

            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 network is a little hard to understand. I would appreciate it if you could elaborate on your ideas. Thanks!!

czhaneva commented 5 years ago

I have read the code too, it's difficult to understanding the encoder-decoder as well.

Liu0114 commented 5 years ago

Hello,Are you understand the network of AIM?