search

Tianxiaomo / pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4
Apache License 2.0
4.48k stars 1.49k forks source link

How to prepare 'val.txt' on our own dataset? #266

Open jayhung97724 opened 4 years ago

jayhung97724 commented 4 years ago

Hello there, I've tried to train on my own dataset, and I have created training image and 'train.txt' well. But then when I tried to train I got this:

train.py[line:611] INFO: Using device cuda
convalution havn't activate linear
convalution havn't activate linear
convalution havn't activate linear
Traceback (most recent call last):
  File "train.py", line 626, in <module>
    device=device, )
  File "train.py", line 293, in train
    val_dataset = Yolo_dataset(config.val_label, config, train=False)
  File "D:\Code\yolo\pytorch-YOLOv4\dataset.py", line 256, in __init__
    f = open(lable_path, 'r', encoding='utf-8')
FileNotFoundError: [Errno 2] No such file or directory: 'pytorch-YOLOv4\\data\\val.txt'

Can someone provide more info of training own dataset?

xielu6 commented 4 years ago

I also encountered the same problem, did you solve it?

zxj11838 commented 4 years ago

You can refer to this file (Use_yolov4_to_train_your_own_data.md）in the project.