Cat
Cat
UNet
Hello, If I use SubMConv to extract features from a sparse point cloud, how should I recover the point cloud using a decoder? I only want to get values of...
I use the newest code and change `mmdet3d/models/vtransforms/base: line 38: add_depth_features=True -> False` to make the [pretrained weight](https://bevfusion.mit.edu/files/pretrained_updated/bevfusion-det.pth) work. The code I used for test is `torchpack dist-run -np 8...
I can generate correct visualizations on validation and testing sets, but the results are wrong on training sets.   The code I use is the stable branch. These two...
Thank you for your great work! I wish to know where I can find code about doing TTA and model ensembling.
Thank you for your great work. Did you provide any tutorial or code on how to do TTA and model ensembling? It seems that these techniques benefit the effectiveness a...
Thank you for your excellent work. It seems that only the base model's weights are released. Would it be possible to release the weights used for the large and e...