semantic-segmentation-pytorch

semantic-segmentation-pytorch copied to clipboard

Preparation of the dataset

8

Hello, I decreased the number of classes to 11 and retaining the network on my dataset. But ended with the ERROR- "RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED". I think this is because...

yashagarwal9

Is there anyone convert the .pth models to .pb models?

2

Is there anyone convert the .pth models to .pb models? With some reasons, Pytorch is not in use while Tensorflow is... Help!!

Jason-xin

train my own data, the results is mussy

1

I used this project to train human segmentation data, change the num_class and .odgt file, but the results is mussy. Are there any other changes that need to be made

guanyonglai

Error while inferencing binary classification trained model (hrnet+c1)

1

 Hi Team, Greetings..!! This is in regards to an inference error. I have trained the model as a binary classifier (object and non-object). I have made changes to unm_class...

Akash-Bhiwgade

Could you plz guide how to print the confidence of per pixel

1

Could you plz guide how to print the confidence of per pixel

leyuan-sun

fix random_flip setting

3

parser.add_argument('--random_flip', default=True, type=bool, help='if horizontally flip images when training') random_flip will always be True, although we run 'python train.py --random_flip False'

mathfinder

Adding mixed precision training support

8

This PR adds mixed precision training support using APEX. https://github.com/NVIDIA/apex Automatic mixed precision training makes use of both FP32 and FP16 precisions where appropriate. FP16 operations can leverage the Tensor...

vinhngx

Add window size to AverageMeter. In this way, we compute the average value in a window size instead of global value history, which may more meaningful.

xingyuanbu

Dear all, I am trying to the Section "Quick start: Test on an image using our trained model". [2020-06-09 12:28:55,641 INFO test.py line 172 138659] Loaded configuration file config/ade20k-resnet50dilated-ppm_deepsup.yaml [2020-06-09...

thomashsia

You can use encoder and decoder in http://sceneparsing.csail.mit.edu/model/pytorch/baseline-resnet50-upernet/ and edit opts as python -u test.py --model_path C:\Coding\Python\segmentation\baseline-resnet50_dilated8-ppm_bilinear_deepsup --test_img ADE_val_00001519.jpg --arch_encoder resnet50 --arch_decoder upernet --fc_dim 2048 --result C:\Coding\Python\segmentation\result to run the...

prajwal98