Ronales
Ronales
I think you can use this code to solve error：，I fixed this problem data_item = pd.read_json(open("D:/douban/douban_movie/data/movie_item.json", "r", encoding="utf8"),lines=True)
@MrCuiHao I also encounter this problems, 2020-01-09 18:48:20.593448: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that...
> Warning: in txt-labels class_id = -1 > = classes = 1 in cfg-file, in txt-labels class_id should be [from 0 to 0]. truth.x = -1.000 ........ when run widerface...
@IGnoredBird Sorry, I have no idea to fix this error.
> So the issue is in datasets.py , how would I modify this line: > cls_name = np.where(labels0[:, 0]=='ship',0,1) > for another dataset? hello! I meet this same problem, What...
I have fixed this problem, you should notice this yolo version, the label txt and image put the same folder.
> https://github.com/ultralytics/yolov3 > > ```python > 命名空间（cfg = ' cfg / yolov3-spp.cfg '，conf_thres = 0.5，data_cfg = ' data / coco.data '，images = ' data / samples '，img_size = 416，nms_thres =...
> @kcg2015 , I still don't quite undertand what you mean by the path. Once you know coordinates, you can use OpenCV APIs to to draw the lines? dear author...
> 为了修复psroi_pooling池错误，我回到了CUDA 9.0（从10开始） > ，这需要GCC 6.这些更改得到了运行的基本测试代码。 I fix this problem recently,I change the pytorch version back to 0.4.