Muhammad Maaz

Hi @YunYang1994, Any plan to add Yolov3-tiny implementation in near future?

Instructions to Run Inference on Mobile Devices

1

Hi, Thank you for the great work. I would request you to share the detailed instructions to run inference and calculate latency on mobile devices (Table. 3 of the paper)....

Hi, Thank you for the great work. I have a question related to the `update_scales()` function in `VariableBatchSamplerDDP` class. I see by default the code is not updating scales during...

Support for Training Negative Samples

1

Hi, Is this repository allow considering negative images as well for training? For example, while training a cat detector, one may have some images containing cats (+ve images) and some...

This pull request adds the support to train a person detector using only person images of VOC2007 dataset. One can pass `-s=voc2007-person` argument to `train.py` to train a peson detector...

Cuda out of Memory Error

1

Hi, It looks like pytorch by default keeping a lot of GPU memory and there isn't any memory available for the data to fit. I tried to train on two...

Reproduce the results in the paper

1

In the paper, on CUB they mentioned 87.8% accuracy on CUB, but I can only get 86.9% using this repository.

How can I generate the activation maps shown in the paper? Thanks

Reproduce the Paper Results

3

Hi Authors, I wonder if you can provide the detailed instructions (and pretrained models as well ideally) to reproduce the results reported in the paper (0.918 avg. dice score). Thanks...

Hi, EdgeNeXt-B model is released. It achieves 82.5% top-1 ImageNet-1K accuracy with 18.51M parameters and 3.84G MAdds. Further, using USI training recipe, the same model achieves 83.7% accuracy. Let's see...