search

LZQthePlane / Online-Realtime-Action-Recognition-based-on-OpenPose

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.
Apache License 2.0
685 stars 232 forks source link

This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations: AVX AVX2 #63

Open ncthong opened 4 years ago

ncthong commented 4 years ago

Hi guys, when i run main.py on my laptop with webcam, it's working but low FPS (1,25 ~ 1,75FPS) and it could not identify the action (just ID and Operate) And i tried run with video, this issue: 2020-07-30 16:25:00.278766: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations: AVX AVX2 To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags. 2020-07-30 16:25:00.302019: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance. usage: main.py [-h] test_out/test222.mp4 main.py: error: the following arguments are required: test_out/test222.mp4

Anyone can you help me? Thanks so much

JoeQvQ commented 4 years ago

I met with the same question with you, I guess it may be because the project runs on CPU rather than GPU. If you want to run it with video, you can try to rewrite the function choose_run_mode(args) in utils.py, but it still works with low FPS.