Great to find your repo, <a class="user-mention notranslate" data-hovercard-type="user

Great to find your repo, <a class="user-mention notranslate" data-hoverca

Very sorry for the late reply: 66 is the number of feature per

Question about feature dimension about video_feature_extractor HOT 2 OPEN

antoine77340 commented on July 3, 2024

Question about feature dimension

from video_feature_extractor.

Comments (2)

h1manshus1ngh commented on July 3, 2024

Great to find your repo, @antoine77340!

I have 3 questions for you to answer:

1. The shape of my .npy file is (66, 2048), 66 is calculated as the total number of frames in the video divided by the batch size right?

2. The output shape I want is (10, 66, 2048), 10 is 10 crops argumentation, can you tell me how to do it?

3. If I want to change the resnet101 model to the resnet50 model, what components do I need to change in your repo?

Thank you so much!

can you provide me csv file you have genrated

from video_feature_extractor.

antoine77340 commented on July 3, 2024

Very sorry for the late reply:

66 is the number of feature per video. Since they are extracted at one feature per second, it should mean your video was 66 seconds right?
The is no implementation of crop augmentation here, so just one single center crop.
Do you mean changing the ResNext 101? you can do it here: https://github.com/antoine77340/video_feature_extractor/blob/master/model.py#L25

from video_feature_extractor.

Recommend Projects