yxchng

Can I know which of the options in `widerface_640` config are toggled during training?

1

Specifically, I am referring to this ``` widerface_640 = { 'num_classes': 2, #'lr_steps': (80000, 100000, 120000), #'max_iter': 120000, 'lr_steps': (40000, 50000, 60000), 'max_iter': 60000, 'feature_maps': [160, 80, 40, 20, 10,...

If the function is smooth, shouldn't it not matter whether it is k or k+1 if it is at the boundary between k and k+1?

Can I know what is the size of the Kinetics 400 dataset used to reproduce the result in this repo?

14

There are many links in Kinetics that have expired. As as result, everyone might not be using the same Kinetics dataset. As a reference, the statistics of the Kinetics dataset...

Can I know how the loss in SSD should look like?

5

Do you still keep your loss info? Currently my loss keep hovers at 20. Can I know what loss value is considered reasonable?

``` Blob sign_0_; // sign_0 = sign(cos_theta) // for DOUBLE type Blob cos_theta_quadratic_; // for TRIPLE type Blob sign_1_; // sign_1 = sign(abs(cos_theta) - 0.5) Blob sign_2_; // sign_2 =...

Accuracy of the released model does not match what you report

8

``` fold ACC ---------------- 1 99.33% 2 99.33% 3 99.00% 4 99.50% 5 98.67% 6 99.33% 7 99.17% 8 99.00% 9 100.00% 10 99.33% ---------------- AVE 99.27% ``` This is...