-
Hi, I think I have some problem with my code, so I can not reproduce the result of densenet161 with pytorch.
I use the pretrained Densenet161 to train on CUB200, with standard SGD, linear-decay of le…
-
I change the network to resnet50 in the pytorch version HashNet, and i can not produce acceptable map on CUB dataset. I have tried some fine tuning, and the best map i can get is arount 40 with 64 bit…
-
Hi, I have evaluated the code with another image normalization parameters, the performance is much better. But still, I'm not sure whether it's correct or not. Could u pls tell me where the pretrained…
-
My Graphic card is GTX1080. So the batch size in my experiment cannot be set as large as 100. Will it decrease the accuracy?
-
I delete the metric learning part of the code and run the CIFAR100 experiment, so all the model is the Pretrain model at test time.
It seems like I get the result as good as when running the code wit…
-
-
Hi @ehcalabres @melkilin can you please guide how to train model on a custom data which is similar to cub-100 data format , folders of classes format.,
-
Hi authors, thanks for the amazing work! I used the following command (just adding -batch_size_base 128 and -gpu '0,1' to your default command), to train SAVC on CUB on 2 GPUs with batch size as 128:
…
-
Hello,
Could you please explain what's the purpose of the "grayscale_cam" and "weights_gradcam" variables in main.py (line 148) ?
These variables are never used, but they are probably important …
-
As there is no "/data" directory, would you mind sharing this part or the data preprocessing process? Thanks!