semantic-segmentation-pytorch
semantic-segmentation-pytorch copied to clipboard
CSAILVision
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
when i export the UPerNet like this: traced_script_module = torch.jit.trace(segmentation_module, feed_dict['img_data']) traced_script_module.save("seg.pt") it does not work. then i try export the encoder and decoder seperately, like this: encoder = segmentation_module.get_encoder()...
Hi! Great work here! I'm trying to use the code to create annotation images with my own dataset. However, the code only generates the class segmentation which should be on...
Hi I'm an undergrad student and im using this dataset and code for my final project which is trying to implement CoodConv into this code to do a "location-aware network"....
For the dilated ResNets (resnet50-dilated, resnet101-dilated, etc), the same pretrained weights as the non-dilated ResNets are used. Even though only the last two layers are different (so all earlier layers...
After I ran ./demo_test.sh, returns: `[2020-04-22 20:12:02,131 INFO test.py line 172 28455] Loaded configuration file config/ade20k-resnet50dilated-ppm_deepsup.yaml [2020-04-22 20:12:02,131 INFO test.py line 173 28455] Running with config: DATASET: imgMaxSize: 1000 imgSizes:...
I am trying to convert the models to onnx but the export fails with error UserWarning: ONNX export failed on adaptive_avg_pool2d because output size that are not factor of input...
Dear all, I know this is a very simple question: but isn't validation used to tune hyperparameters rather than giving accuracy and IoU? I learned to evaluate on a test...
Softmax and log-softmax no longer applied in models; they are now applied in the evaluation and training scripts. This was done by using `nn.CrossEntropyLoss` rather than `nn.NLLLoss`. Class predictions are...
Metadata
Owner
Metadata
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset