rolandgao / regseg Goto Github PK

What is this license?

Hi, RolandGao, nice to see a good job! I see you've done a lot of experiments on the backbone setting, but I still have some confusion after reading your published paper.

• First, You calculate the fov of 4095 to see the bottom-right pixel when training cityscape (1024x2048), so you have verify the backbone should be exp48 [ (1,1) + (1,2) + 4 * (1, 4) + 7 *(1, 14) ] with fov (3807). But I also find the same backbone when training the CamVid (720x960). Why not use a shallow backbone? I am training my own dataset with image resolution (512 x 512), do I need to modify the backbone architecture? Can you give some advice?
• Second, I test inference time of regseg. I notice that the speed is not better than other real-time archs due to split and dilated conv even if model costs low GFLOPs. In the application, what we are concerned about is the speed, so is there any strategy to improve the speed?

Is there any plan for use tensorrt for accelerate it?

Hello,

Your paper is very interesting.
Can I get a pre-trained model?

Hi, I note that you benchmark the computation of STDC2-Seg75 which is not reported in the CVPR2021 paper. Did you test the speed of STDC-Seg on your own platform? How about the results?

Is there any quantized metric and performance benchmark? Do you plan to release quantized weights for cityscapes ? Thanks.

@RolandGao Hello,I wonder to know whether you will publish the weights file trained on the Camvid dataset.

Thank you for your work. When will you update the code

When training, how did the miou and accuracy calculate? On train dataset or validate dataset?
I think it's calculated on val dataset due to https://github.com/RolandGao/RegSeg/blob/main/train.py#L238.
I trained the base regseg model with config cityscapes_trainval_1000epochs.yam on Cityscapes and got the unbelievable results.

Hi, thank you for sharing the code. Can you provide download link about the pretrained model(exp48_decoder26 and exp53_decoder29) in Cityscapes dataset, Thank you very much!

Hi, Thanks for your excellent work ! I notice that RegSeg can achieve a high accuracy on Cityscapes without pretraining. I also did a lot of ablation studies and I think DDRNet will drop around 3% miou if they do not use ImageNet pretraining. How about trying to train your encoder on ImageNet and see what will happen? I really look forward to your result ! Thanks !

When using seg_transforms.py through your scripts 'camvid_efficientnet_b1_hyperseg-s', there always exsist 'TypeError: resize() got an unexpected keyword argument 'interpolation'' in 174 line. Does this bug only appear in this scripts and should I modify the code when using this scripts?

when I train the model on Cityscapes,I While get "RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED".

I trained with my own dataset but don't know why I keep getting this error？

great job with new update. could you share the new pretrain model with 79.1 miou?

I try show.py.
But I can not.

$ python3 show.py
name= cityscapes
train size: 2975
val size: 500
Traceback (most recent call last):
  File "show.py", line 358, in <module>
    show_cityscapes_model()
  File "show.py", line 337, in show_cityscapes_model
    show(model,val_loader,device,show_cityscapes_mask,num_images=num_images,skip=skip,images_per_line=images_per_line)
  File "show.py", line 134, in show
    outputs = model(images)
  File "/home/sounansu/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/sounansu/RegSeg/model.py", line 76, in forward
    x=self.stem(x)
  File "/home/sounansu/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/sounansu/RegSeg/blocks.py", line 22, in forward
    x = self.conv(x)
  File "/home/sounansu/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/sounansu/.local/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 446, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/sounansu/.local/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 442, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same