pytorch-semseg
pytorch-semseg copied to clipboard
meetps
Semantic Segmentation Architectures Implemented in PyTorch
Hi, icnet returned a tuple when training.... but when calculating loss, it directly get size from tuple and got this error: ``` Traceback (most recent call last): File "train.py", line...
I train segnet using SBD and pascal voc 2012, but my loss is so large such as 578002. And when i eval my model on val, i get iou of...
Howdy folks relatively new to Python, numpy, PyTorch (come from C++ and Matlab). I am using CUDA 9.1, Python 3.6, Torch 0.3.0.post4, running on Ubuntu 16.04 LTS and I am...
This is a proposition to solve issue #188 When training on pascal VOC, even if sbd_path is provided in the config, it does not get forwarded to the constructor of...
Does anyone have the pre-trained model that we can use directly now? thanks
In [here](https://github.com/meetshah1995/pytorch-semseg/blob/master/ptsemseg/models/pspnet.py#L333), we should average the overlapping prediction instead of replacing it with new psub Should replace ` pred[:, :, sx:ex, sy:ey] = psub ` with ` pred[:, :, sx:ex,...
Hi, thank you for your efforts! In cross_entropy2d function in loss.py I noticed there are these reshaping lines: input = input.transpose(1, 2).transpose(2, 3).contiguous().view(-1, c) target = target.view(-1) Before passing into...
I want to train pspnet with pascal 2012 and reproduce the results, but i don't know how to set the config.yml Can anyone help me? Thank you so much.
I have trouble when test.py command I want solve that this problem This is test.py command python test.py --model_path ./runs/fcn16s_cityscapes_best_model.pkl --img_path ~/dataset/cityscape/leftImg8bit/test/berlin/berlin_000197_000019_leftImg8bit.png --out_path ./out/ error File "test.py", line 157, in...
