Closed PRAYALANKAR closed 3 years ago
I give my implementation, i.e., MPADA/blob/master/AVA_info/ava2012.py, which I used through my experiments on AVA dataset. Some necessary files, e.g., the training file list and the test file list, can be found in MPADA/tree/master/AVA_info.
And of course, due to the different environment (e.g., the version of CUDA or cv2), you need to change some code lines to make it work in your environment.
Hello, have you solved your problem? I have the same problem. What does that mean? "You need to put the ava2012. Py in AVA_info in the folder of tensorpack. dataflow. dataset." can give me more details on that?
AttributeError: module 'tensorpack.dataflow.dataset' has no attribute 'AVA2012'