Hao Ren
Hao Ren
I have installed your library and use `PWC` conda env, but it will throw `pytorch CUDNN_STATUS_MAPPING_ERROR` and `CUDA error: invalid texture reference` errors, I run this code on RTX 3090...
I found that the code will only processing one video on each GPU, and used about 2.5G memory, the memory usage is slow for GPUs which have lager memory. I...
These two lines should not add 1 for compute areas: https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling/blob/ea630d41e2fc92d523257524690cc6de921e4773/utils.py#L101 https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling/blob/ea630d41e2fc92d523257524690cc6de921e4773/utils.py#L111 Reference the implement of temporal nms in `mmaction2` https://mmaction2.readthedocs.io/en/latest/api.html#id26
Can you explain the workflow of proposal? @Pilhyeon https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling/blob/ea630d41e2fc92d523257524690cc6de921e4773/utils.py#L19 How to decide these four values: `_lambda=0.25`, `gamma=0.2`, `feature_fps = 24`, `scale = 24`
There is a bug about `normalize(self, buffer)` function in `dataset.py`, it has not normalize data to [0, 1], which we usually do this in Deep Learning training process with PyTorch....
@szagoruyko Thanks for your repository, I have studied how to use CuPy to write my own CUDA Kernel function and call it with PyTorch, but I found if I used...
There are one image named `34.jpg` is missing on `real` data of your provided Google Driver download link. According to your paper, there should have 110 images, but the downloaded...
In paper, it said the `total iters` is 8k for activitynet1.2 dataset, and `batch size` is 128, but in the code is 100K iters and 256 batch size: https://github.com/zhang-can/CoLA/blob/314c8d7b548f6740eece6124dac3bca75d712281/core/config.py#L14 https://github.com/zhang-can/CoLA/blob/314c8d7b548f6740eece6124dac3bca75d712281/core/config.py#L19
According to your code, the input image is in `RGB` format: https://github.com/hustvl/SparseInst/blob/fd6fb385b152d232988542aae3072a8fe5d545ae/configs/Base-SparseInst.yaml#L33 and the given `mean` and `std` is also in `RGB` format: https://github.com/hustvl/SparseInst/blob/fd6fb385b152d232988542aae3072a8fe5d545ae/configs/Base-SparseInst.yaml#L4-L5 In `demo.py`, the image is read...