Xiaolin Zhang
Xiaolin Zhang
Sorry for the later response. @heyPooPy is right. Btw, I have updated the oneshot/__init__.py file. Thanks!
The python version I used for running this code was python2.7. PyTorch version was 0.4.1. `# This file may be used to create an environment using: # $ conda create...
The checkpoint is not correctly loaded. Place the checkpoint at the right location or change the path to the checkpoint.
You have two choices 1) `mkdir -p snapshots/inception_imagenet_full_spg` `cp ***.pth.zip snapshots/inception_imagenet_full_spg/` The script of `utils/Restore.py` will automatically load the least saved model according to the save date. You can also...
@Rahul-Venugopal If you want to test on a new dataset without largely changing this code, a feasible solution I suggest is to generate a testing list file like `datalist/test_list.txt`. But...
Hi @Rahul-Venugopal , Sorry for the late reply. The demo scripts have been uploaded. Please refer to the [setup_demo.txt](setup_demo.txt) for more guidance.
@FzuLJ Sorry for the late reply. The trained model on CUB dataset has been uploaded at https://drive.google.com/open?id=1WfrELBlEoq5WO7gKUv-MLTQ8QHY-2wiX
@Rahul-Venugopal You got to change to `onehot=False` if your images do not have multiclasses.
I used ILSVRC 2016. You may need to register on this website （http://image-net.org/download）, and then download the dataset after getting granted.
@xiaopingzeng Exactly!