Jing Li

Questions about the numerical_gradients_2d function

2

Thanks for sharing your work! It seems a bug here: > https://github.com/nv-tlabs/GSCNN/blob/64f84878c6d4aabbf74d7e74fe27f38aa408c7ec/my_functionals/custom_functional.py#L38-L52 The numerical_gradients_2d function call this function that return the input directly and the input is only processed by...

Experiment result is not consistent with the result reported on the paper

3

Hi, thanks a lot for sharing your work! I download your full approach model pretrained on the panoContext dataset and use it to predict on the test set of the...

Question about your loss function

3

Since the input of your loss function is the network output without sigmoid function, I find it difficult to understand your code. What are 'max val' and 'log weight' here?...

I tried to use torch.compile but failed with SAT. The reason is that self.transformer.hooks.clear() in base_model.py also clear the hooks of torch.compile?

Hi, I have a question in your work and the former PlaneRCNN. In your code and PlaneRCNN: https://github.com/yi-ming-qian/interplane/blob/f0713e4d97c03221b29769b2679eb69031469312/predict_all.py#L110 Only 100 images are tested. I wonder is this true?

[Feature] throw Turbomind error to python

4

### Motivation Cannot catch and continue running when Turbomind throws an error. ### Related resources _No response_ ### Additional context _No response_