SemanticSegmentation
SemanticSegmentation copied to clipboard
WillBrennan
A framework for training segmentation models in pytorch on labelme annotations with pretrained examples of skin, cat, and pizza topping segmentation
I need Semantic Segmentation to show a black and white skin mask so I can feed it to Gimp as a layer mask for skin. How do I do this?...
Could you please share the training data (images and labels) for the model training in skin segmentation? (150 images from coco)
Hello @WillBrennan , I tried to train using my own data / annotation files, but received the following error: ``` python train.py --train /home/yoda/Development/sportModel/Training --val /home/yoda/Development/sportModel/Validation --model-tag segmentation_sport --model-type FCNResNet101...
Hi! when i convert pytorch model to onnx ( for coreml onversion), I get unpickling error while loading ".pth" weights file. Can you help converting pytorch model to onnx form.
@WillBrennan Do you have experience using coremltools to convert pytorch models to coreml? I created a script to convert the "model_segmentation_skin_30.pth" model to coreml format, but have encountered issues. The...
https://github.com/WillBrennan/SemanticSegmentation/blob/7646661aa0e05f5c5b087f2aeda3faff42c34e00/train.py#L83 If I see it correctly, you have also solved semantic segmentations for multiple classes and not only binary decisions like skin vs. background with this source code, for example,...
Metadata
Owner
Metadata
A framework for training segmentation models in pytorch on labelme annotations with pretrained examples of skin, cat, and pizza topping segmentation