cannot read datasets correctly during the training

[yanfei96]

Thanks for your project. I have tested it successfully, but I have something wrong during the training. The information is as follows. Can you give some suggestions? python train.py Namespace(accumulate=1, backend='nccl', batch_size=16, cfg='cfg/yolov3-spp.cfg', data_cfg='data/coco.data', dist_url='tcp://127.0.0.1:9999', epochs=273, evolve=False, img_size=416, multi_scale=False, nosave=False, notest=False, num_workers=4, rank=0, resume=False, transfer=False, var=0, world_size=1) Using CUDA device0 _CudaDeviceProperties(name='GeForce GTX TITAN X', total_memory=12209MB)

Traceback (most recent call last): File "train.py", line 338, in multi_scale=opt.multi_scale, File "train.py", line 141, in train dataset = LoadImagesAndLabels(train_path, img_size, batch_size, augment=True, rect=True, image_weights=True) File "/home/ubuntu/yolov3/utils/datasets.py", line 134, in init with open(path, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: '../coco/trainvalno5k.txt'

[yanfei96]

I put the directory "coco" and the directory "yolov3" in the same directory then I solved the problem

[glenn-jocher]

@yanfei96 yes exactly, the two must be in the same parent directory.