Sreeragh comments

Results 6 comments of


                                            Sreeragh

shape of input image in cityscapes dataset

@coderzbx > why the input image size of cityscapes is 1025 x 2049? > Shouldn't be 1024 x 2048? The original image size is 1024 x 2048 in cityscapes dataset....

Where is the saved data

I just modified **train.py** to save a predicted image. ![image](https://user-images.githubusercontent.com/19902556/102689271-cec0df80-4222-11eb-8aa9-1f31a3a90c34.png) Inserted this code as in the image. ``` for each_pred in pred: rgb_img = decode_segmap(each_pred, 'cityscapes') rgb_img = Image.fromarray((rgb_img *...

Low mIoU on Cityscapes

@jfzhang95 > Hi, all > > I just noticed an [issue](https://github.com/sacmehta/ESPNet/issues/9#issuecomment-392057816) in [ESPNet](https://github.com/sacmehta/ESPNet/). It seems like Cityscapes dataset script uses weighted mIoU. So maybe you can evaluate mIoU using the...

Getting very low mIoU on Cityscapes

@speedinghzl An update. I just modified **evaluation** script to use `predict_whole()` function instead of `predict_sliding()` and I obtained mIoU of **57.09%** mIoU with the same model. I also tried downloading...

Getting very low mIoU on Cityscapes

@speedinghzl Thanks for the explanation. I have one more query. Downloaded official **CCNet trained model** and evaluated with **official [cityscapesScripts](https://github.com/mcordts/cityscapesScripts)**. But unable to reproduce the expected result. * Used **single-scale...

Could not run the code

One possibility can be that you have less number of visible/available GPUs than the configured number of GPUs to use. i.e In the run_local.sh file (in branch pytorch-1.1) `--nproc_per_node=4 `...