pytorch-segmentation-toolbox

pytorch-segmentation-toolbox copied to clipboard

这里多尺度预测说对于大于原图的采用裁剪的方式，请问是否也采用的滑动窗口预测呢？但是代码里没有采用滑动窗口的代码啊 def predict_multiscale(net, image, tile_size, scales, classes, flip_evaluation, recurrence): """ Predict an image by looking at it with different scales. We choose the "predict_whole_img" for the image with less than...

swjtulinxi

raise ImportError("torch.utils.ffi is deprecated. Please use cpp extensions instead.") ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.

6

I follow the guidance, but pytorch1.0 do not support torch.utils.ffi. I can not run the code

karlcao

boolean index did not match indexed array along dimension 0

1

Hi, thank you for your work. I meet a problem when I run the evaluate.py. I change the input image size into (473,473) and raise the error: 500 images are...

hhhwww123

hi, if I want to use 3090 with CUDA 11， how to change the inplace_abn? some parts of the codes are based on CUDA 9, where to change the code...

chenwang1701

bug， using sliding eval with batch size larger than 1 on each gpu

2

evaluate.py in branch pytorch-1.1 line 134 and line 135 you only use the prediction result of the first image, but treat it as the result of the remaining images in...

fuchangjie

After using the pspnet model, I can only test 76.64 on the test set. What is the maximum amount you can reproduce?

Caius-Lu

The visualization of the segmentation results.

5

I trained the model with 4 GPUs (GTX 2080) with batchsize 4, and the PSPNet achieves the mIOU of 76.42%. But I found the visualization results are not correct. Here...

chenyzh28

IMG_MEAN needs to be changed for CityScapes?

5

Hi @speedinghzl , I see the following has been used for CityScapes (during both training and evaluation)- `IMG_MEAN = np.array((104.00698793,116.66876762,122.67891434), dtype=np.float32)` I did some googling and found out the stats...

aasharma90

Hi ,thanks for your job. And i came across a problem when i multi-times train the model i got the different result .

qqqlz

@speedinghzl hi when i try to extract or viz the cityscapes datasets its like this , how can i extract teh polygon from the semanttic segmentation map 

abhigoku10