bubbliiiing / mask-rcnn-tf2

这是一个mask-rcnn-tf2的库,可以用于训练自己的模型。
MIT License
64 stars 9 forks source link

求问博主帮我看看跑maskrcnn时出现的错误,已知环境按照tf2.4配置在windows30显卡系列下运行出现的错误 #41

Open jcy8 opened 1 year ago

jcy8 commented 1 year ago

Errors may have originated from an input operation. Input Source operations connected to node mask_rcnn/ROI/GatherV2_5: mask_rcnn/ROI/strided_slice_12 (defined at mask-rcnn-tf2-master\nets\layers.py:12)

Function call stack: train_function

: W tensorflow/core/kernels/data/generator_dataset_op.cc:107] Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process may be terminated. [[{{node PyFunc}}]] 博主你好,请问出现这种错误是什么问题呢,我的环境是没问题的,可以跑通其他模型

bubbliiiing commented 1 year ago

貌似还是环境的问题,cuda和 cudnn是什么

jcy8 commented 1 year ago

cuda和cudnn我又按照你的博文重新配置了一遍,但是跑train.py的时候又出现了新的问题, 2023-08-25 10:37:43.181280: I tensorflow/core/platform/windows/subprocess.cc:308] SubProcess ended with return code: 4294967295 出现上述问题,但是不影响模型训练,并且排除了环境变量、路径以及版本匹配等问题 还请博主再帮我指点一二

bubbliiiing commented 1 year ago

0 0这个好像在环境配置最开始说了0 0

jcy8 commented 1 year ago

找到了!谢谢老师!!!