Shanghua Gao

Support receptive field search of CNN models. (TPAMI paper rf-next)

6

## Motivation Merging a general receptive field search method to mmcv and mmdet. (paper: RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks TPAMI 2022 [pdf](http://mftp.mmcheng.net/Papers/22TPAMI-ActionSeg.pdf)) ## Modification The RFSearch...

fatal error: kdt.h: No such file or directory

1

I am having trouble while running tf_pointSIFT_compile.sh. ############ main.cpp:11:17: fatal error: kdt.h: No such file or directory ############ Is this kdt.h a part of kdt-0.3.tar.gz? I tried to install it,...

Thanks for your implementation! The source code of our work "Res2Net: A New Multi-scale Backbone Architecture" is now available at https://mmcheng.net/res2net/ and https://github.com/gasvn/Res2Net. We have implement Res2Net into many tasks...

Extremely slow data load when training on ImageNet

1

Thanks for your excellent work. I found that the data load speed is very slow when training the shuffleNetV2-0.5X. The GPU is basically not working. I use one SSD and...

Thanks for the great work. We have trained a [ControlNet based on the SAM segmentation mask](https://github.com/sail-sg/EditAnything) for fine-grained image generation. This model can help to use SAM for image generation...

ControlNet with SAM mask condition for image generation

1

Thanks for the great work. We have trained a [ControlNet+StableDiffusion based on the SAM segmentation mask](https://github.com/sail-sg/EditAnything) for fine-grained image generation. Replacing the standard inpainting model in your repo with this...

ControlNet with SAM mask condition

7

Thanks for the great ControlNet. We have trained a [ControlNet based on the SAM segmentation mask](https://github.com/sail-sg/EditAnything) for fine-grained image generation. This model can help to use SAM for image generation...

Can you share the cmakelist?

1

Excellent work. I'd love to extend your work with more functions. I notice that you use the SWIG. Can you please share the CmakeList file that compile the swig? Thanks.

Is there a script to reproduce the results of medprompt in the https://arxiv.org/pdf/2311.16452.pdf paper? It seems the current codebase does not support the MedQA dataset.

Bug report in scaled_dot_product_attention

1

In line 80, the train should be is_train for dropout according to the latest doc of jittor.