peternara

Hi! I appreciate you(@nashory) releasing the code. I am very curious about the way you evaluated the benchmark set. Could you explain to me in detail? And, if you have...

Is there a special training strategy(include pre-processing)?

1

@bgshih Hi, I have implemented it using tensorflow based on your thesis and source . I've been doing a lot of testing and debugging, and I've even tried to increase...

Hi, @filipradenovic When training with the GL18 dataset, what is the whitening dataset? Did you ever use "retrieval-SfM-120k-whiten.pkl" from the sfm-120k dataset? When whitening, it's not clear, but in your...

tf 초보입니다. 다름이 아니라, 학습과정에서 saver를 이용하여, cnn_study.ckpt-\* 이름으로 checkpoint cnn_study.ckpt-0 cnn_study.ckpt-0.meta cnn_study.ckpt-1 cnn_study.ckpt-1.meta cnn_study.ckpt-2 cnn_study.ckpt-2.meta cnn_study.ckpt-3 cnn_study.ckpt-3.meta cnn_study.ckpt-4 cnn_study.ckpt-4.meta 이렇게 생성하였습니다. 단독 파일(.py)에서 학습이 아닌, 생성된 모델을 이용하여, 로드한후,...

Existing in caffe general way should I do?? Or, Do you have a special way for metric learning(triplet loss)? thank you

refer paper?

1

hi, i see your code. but, i find not related paper. i wonder related paper about your code.

Can you update how to use imagenet21k_R50+ViT-L_32.npz?

3

Hi, @jeonsworld The imagenet21k_R50+ViT-L_32.npz model has been released. Can you update how to use imagenet21k_R50+ViT-L_32.npz? I tried it on current your source, but I kept having problems. thanks

fine-tuning training prolem

4

@MhLiao hi, i have a problem during training. First, I learned with SynthText data. I learned by changing two learning rates with reference to your paper. so, see logs.. (examples)...