jeong-tae

md5sum chn_syn.json: `7ec90c2482c259c5727e56a4dabac955` I can read now with your new link! After that, I got this error  I am using this script: `SWINTS-swin-chn_pretrain.yaml`

hm.... I will figure it out soon. @mxin262 Can you provide other labels as well? which linked to baidu. I checked other labels which I downloaded from official site and...

@mxin262 Thank you! Everything goes well! Btw, I tried to visualize the result with Chinese characters,  but I can't see any Chinese characters from demo visualization. How to change...

@Ostnie i think we use the points to crop the current batch. the points are about current image. so it must be. i am not sure where are you confusing...

following the paper, we should repeat two times. The losses are not backpropagated togather. rank loss is for APN, entropy loss for conv/classifier. As authors said, it should calculated in...

Yes it is. you can use the output of the softmax layer. `rank_loss = (pred[i]-pred[i+1] + 0.05).clamp(min = 0)` i calculated the loss like this. Why can't we use the...

The rank loss is the gap between VGG1 and VGG2. You can easily imagine the meta-learning that teach the difference between two networks(in this cage VGG1 and VGG2). And the...

oh, you mean backpropagation for APN? i actually implement the backward code following the caffe code, which is in attention crop layer. i will finish the code work so soon...

@Ostnie oh, very nice! thx!

@Ostnie i publish the code and need some helps. If you still interested in implementation with other framework. come to here https://github.com/jeong-tae/RACNN-pytorch and work together.