semantic-segmentation-pytorch

semantic-segmentation-pytorch copied to clipboard

Ask for the ImageNet pretrained ResNet-152 or ResNext-101/ResNext-152

1

@hangzhaomit Really great work! We find that the provided pretrained models all replace the 7x7 convolutions with three 3x3 convolutions and achieve really good performance. I just have tried to...

PkuRainBow

Standard methods from documentation [https://pytorch.org/tutorials/recipes/script_optimized.html] don't work.

DianaGumar

Hi, I'm running the google colab provided in README, and I want to subtitude the model to HRNetv2. I download the weights file for encoder and decoder from the link...

yamiefun

[Question] Piping video into the test model?

1

Hi thank you for making a great scene segmentation repo, Was just wondering if I were to try and pipe a video file/camera output into the model, which config file...

Trinity-Actual

Customizing your dataset

6

I wrote [a help page](https://hackmd.io/wNGlmMq2RC-lY3l8JhO4SA?view) for anyone is planning to implement this repo in ones own project/data. Note that the page is still ongoing and _not official_, also it might...

RicoSuaveGuapo

Does your code base suppose custom dataset

2

- can I train with custom dataset - load custom classes (categories)

pankaja0285

HRNet + OCR ?

1

Hi, Thank you for the great repo. Extremely helpful. I was wondering if you have any plans on adding the HRNet +OCR model to your repo as well.

Mary-h86

How to use other models for other projects??

2

The notebook demo contains the following part: ------------------------------------------------------------------------------------ net_encoder = ModelBuilder.build_encoder( arch='resnet50dilated', fc_dim=2048, weights='ckpt/ade20k-resnet50dilated-ppm_deepsup/encoder_epoch_20.pth') net_decoder = ModelBuilder.build_decoder( arch='ppm_deepsup', fc_dim=2048, num_class=150, weights='ckpt/ade20k-resnet50dilated-ppm_deepsup/decoder_epoch_20.pth', use_softmax=True) ------------------------------------------------------------------------------------ I'm wondering how I can use other...

Uehwan

error when export to a onnx model

6

Hello CSAILVision team, Thanks for sharing this work. I trained a model with 'resnet18dilated' and 'ppm_deepsup'. Trying to export this model to a onnx model and get errors (I can...

bigsheep2012

[https://github.com/CSAILVision/semantic-segmentation-pytorch/blob/master/test.py](url) 82 line pred = as_numpy(pred.squeeze(0).cpu()) .cpu()is very slow

GuoxingYan