YOLOP

YOLOP copied to clipboard

In the requirements.txt is a duplicate entry of scipy one without version specification one with version higher than 1.4.1 requirement. This pull request sets the requirements `scipy>=1.4.1`, and removes the...

raimannma

研究了一下发现序列化的过程不能有生成器对象，解决方案如下 AutoDriveDataset.py 48行将生成器转为列表 self.mask_list = self.mask_root.iterdir()-----------》 self.mask_list = list(self.mask_root.iterdir()) 同时，bdd.py32行就不用转换了，改完之后就可以正常改变numworkers了 for mask in tqdm(list(self.mask_list))::----------------》for mask in tqdm(self.mask_list):

471742

change batch size

1

After reviewing source code and modified segmentation parts, training raised the following error: `RuntimeError: CUDA out of memory. Tried to allocate 24.00 MiB (GPU 0; 10.89 GiB total capacity; 9.69...

danielzhangau

Perform object detection on segmentation area

1

I want to improve the accuracy of object detection by `yolop`. Is there any way for `yolop` to directly use the segmented road part for the target detection model after...

danielzhangau

Detection and segmentation have different loss function and task，The features that need to be extracted from the backbone network should also be different. why can they use the same parameters...

xxbb0508

我的需求是通过检测获得目标的bbox.然后在bbox内对目标进行分割，请问yoloP能分割多个类别么？例如检测到人，把人分割为头部，身体，手部，腿部。我有mask的掩码标签。

JiangWeiHn

Training time is faster in beginning

3

I train my custom dataset with YOLOP with tesla V100, I found that it training speed is very fast in first but it will get slow after 40 times. May...

JLDDER

problem

1

There is typeError: "cannot pickle 'generator' object" wnen _C.WORKERS=1

seenthestars

Issue while running train.py

4

I have an issue while running train.py The following is the description of the Error : Traceback (most recent call last): File "C:/Users/Wei/torch/YOLOP-main/tools/train.py", line 397, in main() File "C:/Users/Wei/torch/YOLOP-main/tools/train.py", line...

108318139

# of classes in detection

15

How to change it to 13 which BDD100K has? Thanks,

fjremnav