-
Dear author, I want to use the [table tennis temporal location project](https://aistudio.baidu.com/aistudio/competition/detail/127/0/task-definition) for my job, however, the input feature is extracte…
-
PPTSM目前是否支持实时视频流的输入呢？如果不支持，是否考虑在以后会支持呢？
-
When running
`python recognition_web_service.py -n PPTSM -c configs/PP-TSM.yaml`
Nothing happens and the code just exits.
Then I changed
`uci_service = VideoService(name="video")`
` uci_s…
-
加载从
https://bj.bcebos.com/acg-algo/PaddleVideo_application/VideoQualityAssessment/ppTSM.pdparams
下载的预训练模型推理时，报
OSError: {weight_path} is not a checkpoint file
错误，该如何解决？
-
Traceback (most recent call last):
File "/home/wangnan/anaconda3/envs/action-py3.7/bin/paddle2onnx", line 8, in
sys.exit(main())
File "/home/wangnan/anaconda3/envs/action-py3.7/lib/python3.7/site-p…
-
直接lstm？或者图像有比较特别的方案？
-
环境配置如下：
机器：v100
cuda10.1+cudnn7.6+gcc8.2
opencv：4.2.0
TensorRT-6.0.1.5
paddle_inference.tgz 选用的是适配环境的manylinux_cuda10.1_cudnn7.6_avx_mkl_trt6_gcc8.2
按照服务器端C++预测中的readme编译成功了所有部分
运行命令：
./buil…
-
请问百度大佬如何将PP-TSMv2改造成像SlowFast那样可以给出多目标检测框并实现对每个目标的动作识别么？谢谢~
-
Hello,
I'm trying to use LEVIATHAN and require the barcode indices from LRez. Introduced a step in my workflow that uses `samtools view` to filter reads on mapping quality, and it seems that doing …
-
*Thanks for such a great work! When I run the code , problems occur: how to generate the features(such as VGGish or ResNet) used by MultimodalVideoTag? This part seems not to be implemented in the rep…