shape_templates icon indicating copy to clipboard operation
shape_templates copied to clipboard
verified publisher icon lschmidtke

Number of training images

Open unofgithub opened this issue 3 years ago • 3 comments

Hello,

I just have a quick clarification about the number of images you used in training. You mentioned using about 600K images for training. Could you please let me know if that means it was trained with 300K pairs (frame 1, frame 2) or that 600K pairs were used for training? Thank you so much!

unofgithub avatar Apr 18 '23 15:04 unofgithub

Hi, it's 600k training images in total, but with random frame pairs.

lschmidtke avatar Apr 25 '23 20:04 lschmidtke

Hello. Thank you. Could you please let me know how many random frame pairs were sampled?

unofgithub avatar May 02 '23 04:05 unofgithub

Okay, so I counted the number of possible pairs in each bounding box bucket for each subject and each activity. Number of possible pairs would be (num_frames choose 2). I end up with 800 million possible pairings. However, since the model is trained for a limited amount (around 30 epochs), there are roughly 30 epochs * 600k pairs seen during training. Keep in mind though that since it's video data, frame pairs that are close to each other in terms of timestamp have very little pixel-wise difference.

Hope that helps!

lschmidtke avatar May 06 '23 10:05 lschmidtke