Hello, sorry to disturb you~ here are some questions when running the projects:
1) When I run the test.py on ucf101 mixed 1, i got only 0.6756 accuracy while rgb model is 0.89, and flow model is 0.95.
2) Also I found that test.py #196, "input_label=np.array([label]).reshape(-1)", the input_label sometimes is not matched to the video when testing, e.g. v_ApplyEyeMakeup_g07_c07, prediction and video name are 'ApplyEyeMakeup', but input_label changed to ApplyLipstick's index.
so I change the code
video_label = rgb_data.Videos[i].label
video_label = flow_data.Videos[i].label
input_label=np.array([video_label]).reshape(-1)
Hello, sorry to disturb you~ here are some questions when running the projects: 1) When I run the test.py on ucf101 mixed 1, i got only 0.6756 accuracy while rgb model is 0.89, and flow model is 0.95.
2) Also I found that test.py #196, "input_label=np.array([label]).reshape(-1)", the input_label sometimes is not matched to the video when testing, e.g. v_ApplyEyeMakeup_g07_c07, prediction and video name are 'ApplyEyeMakeup', but input_label changed to ApplyLipstick's index. so I change the code video_label = rgb_data.Videos[i].label video_label = flow_data.Videos[i].label input_label=np.array([video_label]).reshape(-1)
but the accuracy is not improved.