sithu3

@bamboosdu It is a screenshot with extra white background. Shadow is already included.

The mIoU results are from official papers and pretrained weights from official repo. I haven't tested each of them with my codebase. Though evaluation image size should be 1024x2048 for...

Hello, sorry for late. I will evaluate the model and see if there is an issue with my implementation.

Hi, I am sorry for confusion. TopFormer is not updated in this repo yet. I am updating the whole codebase and will release later.

I suggest to use the pretrained models provided in this repo from [here](https://github.com/sithu31296/semantic-segmentation/blob/main/docs/MODELS.md). Not all of the weights from official repositories are compatible with the modified (simplified) code base in...

Thanks for your details response. About first issue, it is a typing error. Change to `os.environ['LOCAL_RANK']`. To be honest, I don't personally own a multi-gpu machine. So, haven't got many...

Very sorry for the late reply. For the first issue, I don't have a big problem like you said but I will look into it. For the second issue, I...

Take a look at [this](https://github.com/sithu31296/semantic-segmentation/blob/main/docs/BACKBONES.md). All the weights provided there are trained on imagenet.

Yes. BiSeNetv2 doesn't use a separate backbone model. So, no ImageNet weights for it. For custom model creation, please see the sample from [here](https://github.com/sithu31296/semantic-segmentation/blob/main/semseg/models/custom_cnn.py). Basically, you need to know the...

Hi Thanks for your interest in this repo. PyTorch and ONNX are written in channel first format. PyTorch has beta support for NCHW format. Please check [here](https://pytorch.org/tutorials/intermediate/memory_format_tutorial.html). But this will...