ActionDetection-AFSD

ActionDetection-AFSD copied to clipboard

In the version of supporting multi-GPU, I notice the code in GAF/thumos14/train.py has been modified from `output_dict = net(clips, proposals=targets, ssl=ssl)` to `output_dict = net.module(clips, proposals=targets, ssl=ssl, mode='clf')`. Can anyone...

syj2908

ADstudyer

C:\Users\Administrator\.conda\envs\AFSD-pl\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/functional/embedding.h(115): note: see reference to function template instantiation 'std::string torch::enumtype::get_enum_name(V)' being compiled with [ V=torch::nn::EmbeddingBagMode ] C:\Users\Administrator\.conda\envs\AFSD-pl\lib\site-packages\torch\include\ATen/core/ivalue_inl.h(624): note: see reference to class template instantiation 'c10::ArrayRef' being compiled error: command 'C:\\Program...

a907251064

based on the paper，should i use the code “python3 AFSD/anet/train_init.py configs/anet.yaml --lw=1 --cw=1 --piou=0.5” to train the net. The lw=1 is right? Why does my loss increase when I train?

hj611

setup.py in 3090

3

你好，我在我自己的电脑上（cuda11.2）可以进行setup.py并运行后续程序，但是在3090的服务器中（cuda11.1 cuda11.4）进行训练时，在boundary_max_pooling_cuda处总是会报错 cuda runtime error（209）:no kernel image is available foe execution on the device. 我调整了好多torch和cuda版本，但好像并不是版本不匹配的问题 能帮帮我吗 谢谢你

neauniko

Prepare the pre-processed RGB data. How to pre-process RGB data?

NuaaLuWei

你好，请问，这个框架应用于自定义的数据，该如何构建数据格式，比如一个视频是一个动作从start到end的视频

ljl02521

about activitynet1.3

1

@linchuming 您好我在运行python3 AFSD/anet_data/video2npy.py THREAD_NUM生成 RGB npy 输入数据时，遇到一个问题，当采样视频的总时长超过1分钟时，ret, frame = cap.read()，ret为false，count = cap.get(cv2.CAP_PROP_FRAME_COUNT)为770。但是同样的count为770，但是采样视频总时长不超过1分钟时，ret是为true。我不知道这是什么问题，您能帮帮我吗？还有一个神奇的现象是，我把不能正确读帧的视频下载到我本地笔记本电脑上时，这些都可以读取。

menghuaa

menghuaa

video2npy.py for activitynet cannot read video frames.

1

I am trying to extract RGB frames by following ActivityNet Readme. However, when I run video2npy.py, it cannot read frames for some videos . In detail, VideoCapture.read() returns False while...

prote376