Omer Sarioglu
Omer Sarioglu
> why the file not exist? `mmfashion/configs/attribute_predict_coarse` use this or `mmfashion/configs/category_attribute_predict`
Can you reinstall `opencv-python` with pip ?
Please check https://github.com/onnx/onnx/issues/2784#issuecomment-633909328, setting `opset_version=10` will solve the issue
I think, since it's working with single value comparison we can just flatten n-dimensional array (N, C, ...) to (N, C, F) which F is flattened axis.
Absolutely @SkafteNicki ``` num_classes=5 preds: (8, 5, 256, 256), dtype=float32, min=0, max=1 => Output softmax target: (8, 256, 256), dtype=int64 => Multi-class labels ```
Hello @luisbergua, Yes actually it would be better to have two correct feature requests. But the second one was a feature I thought of as optional, what we really need...
Any updates @luisbergua ?
Any update ?
@bsekachev changelog entry added
@bsekachev I can update the model without weights, and it will be used as a template for classifier serverless models since there are none. Regarding the `torchvision` usage, I don't...