Weilin Cong

Random errors when loading OGB datasets

1

### 🐛 Describe the bug Receive random error message `IndexError: index 242823520 is out of bounds for dimension 0 with size 123718280` error when loading OGB-Products using ``` dataset =...

why convert_to_square(dets)?

2

in `gen_hard_example`, convert_to_square is used. Why convert to square is needed since bounding box is rectangle and pnet do not use this func?

where block back propagate?

1

for both positive and negative images, we calculate `cls_prob` and `bbox_pred` loss, however, do not backward update the bbow_pred weigh for negative images by block back propagate. I have read...

P_net only do not use negative dataset

6

When i read your code 'train_P_net.py', I found that you use function 'gt_imdb()'in function 'train_P_net'. This only returns positive + part face, but without negative dataset. However, in Pnet, it...

how do `tracker_init.caffemodel` created?

9

According to your paper, the top fifth layer was initiated on `tracker_init.caffemodel`. How do you create `tracker_init.caffemodel`? Do you copy weigh from `CaffeNet`(which is 230M) to both the two sub-net...

loss layers when training?

1

I want to train the data by myself. My method: input data: four kinds of training data( includes positive, negative, part, landmarks) for different data, only backward specific loss layers.(eg....

Only use Conv and Linear

1

Hi, has anyone tried only to use Conv, and Linear function without BN? I commented BN in the config, and the result gives me random guess ... For 5-ways, the...

Multi-processing error when dataset is large and using distributed node embeddings

5

Hello, does anyone have an idea why this "child fail" error is raised with `num_trainer=1, num_sampler=16`. This issue only occurs when working with a large graph and using distributed node...