minhoooo1

A question about train step

1

Excuse me, my training data set has only 1000 pictures, And I found len(AEI_Dataset) = len(self.files) * 5 = 5000 my batch size = 20. So train step should be...

Eclipse 导入 PX4 Firmware 源代码时报错

1

Description Resource Path Location Type Program "g++" not found in PATH Firmware Description Resource Path Location Type Program "gcc" not found in PATH Firmware [Discovery Options] page in project properties...

pre-processed data

1

非常感谢你们的开源工作，非常有趣的是我本科和硕士导师都是来自华工的。回归正题，我无法下载在OneDrive中的预处理数据，不知道你们能提供其他的获取方式吗？比如谷歌云盘，或者麻烦你们发我邮箱[email protected]，感谢了！

Request a preprocessed data set that can run the code！

4

Hello！ everyone! Cound you please send the preprocessed data set that can run the code to my mailbox? Thank you! [email protected]

@allanj Thank you very much for your replication work, but I don't have the microsft READ API. Can I apply to you for the processed data？

Could you please provide the pre-processed data?

https://github.com/Wolfwjs/GANet/blob/7378d7bd34e5d355353de3ac4961accf06b75e94/mmdet/models/dense_heads/ganet_head.py#L240 There are only two heads self.keypts_head and self.offset_head in the paper. Why are there two heads self.centerpts_head and self.reg_head in the code?

Why we need def padr_crop(img) ?

3

https://github.com/Reyhanehne/CVF-SID_PyTorch/blob/c89242a4ef5cc98481404192392a6f76e0fb0ec9/src/trainer/trainer.py#L25