Update the pretrained model file

README.md

@@ -2,10 +2,8 @@
 
 ## News
 
-EMANet-101 gets *79.79* in mIoU on Cityscapes using single-scale inference.
-And *80.99* on the PASCAL VOC dataset (Thanks for Sensetimes' server). 
-So, with a classic backbone(ResNet) instead of some newest ones(WideResNet, HRNet),
-EMANet still achieves the top performance.
+- The bug in loading the pretrained model is now fixed. I have updated the .pth. To use it, download it again.
+- EMANet-101 gets *79.79* in mIoU on Cityscapes using single-scale inference. And *80.99* on the PASCAL VOC dataset (Thanks for Sensetimes' server). So, with a classic backbone(ResNet) instead of some newest ones(WideResNet, HRNet), EMANet still achieves the top performance.
 
 ## Background
 
@@ -54,7 +52,7 @@ For research, I recommand seperatting each experiment with a folder. Each folder
 4. Change the 'DATA_ROOT' in settings.py to where you place the dataset.
 5. Run `sh clean.sh` to clear the models and logs from the last experiment.
 6. Run `python train.py` for training and `sh tensorboard.sh` for visualization on your browser.
-7. Or you can download the [pretraind model](https://drive.google.com/file/d/1vJhzEEpsPzKLLIOb6B9Uro8Vr0A5VXMv/view?usp=sharing), put into the 'models' folder, and skip step 6.
+7. Or you can download the [pretraind model](https://drive.google.com/file/d/11GbUBfpWnt000Hy6FI32tppHc7QxczPO/view?usp=sharing), put into the 'models' folder, and skip step 6.
 8. Run `python eval.py` for validation
 
 ## Ablation Studies