Luis Unzueta

Thanks @willyd. With your changes and suggestions now I can compile the "leveldb" project correctly, both in Debug and Release. However, this time I'm getting other two errors; one linking...

@willyd Yes, you're right. I tried that "trick", but without success, so it wasn't a good idea. Just in case, I've removed that file again and I've restarted the whole...

I just wanted the same thing. In the code, you'll see this function: keypoints_from_heatmaps(). it is for that. I hope it helps...

Hi @ktak199 I just did the same thing today and I also saw that the error was much higher than in the case of FLIC. I guess we should check...

Hi @ktak199. I've tested this time with MPII and the default parameters. The tests have less error in general than in the case of LSP, but they still are quite...

@ktak199 The dropout is already considered in the implementation, with the same value mentioned in the paper: `h = F.dropout(F.relu(self.fc6(h)), train=self.train, ratio=0.6)` `h = F.dropout(F.relu(self.fc7(h)), train=self.train, ratio=0.6)` Now, I'm training...

Hi @ktak199. Yes, you are right about σ, I said it wrong. I've continued doing some more tests changing the parameters (crop vs no-crop, local contrast vs no-local-contrast, etc), but...

Thanks for sharing this @yutuofish2. I see you are training for more than 600 epochs. I wonder how many should be a good number, but I see that your training...

This time I trained a model with LSP, just changing the optimizer to 'MomentumSGD', and maintaining the rest of parameters the same way. I got the following results, which still...

@ktak199 I was also doing the same thing, but I still was at Epoch 200, and I'm getting a similar graphic:  So, what do you think it might be...