search

chineseocr / trocr-chinese

transformers ocr for chinese
338 stars 53 forks source link

请问与训练模型是哪个？官方的 #23

Open cqray1990 opened 1 year ago

cqray1990 commented 1 year ago

；训练出现以下错误 ./aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [71,0,0] Assertion srcIndex < srcSelectDimSize failed. ../aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [72,0,0] Assertion srcIndex < srcSelectDimSize failed. ../aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [73,0,0] Assertion srcIndex < srcSelectDimSize failed. ../aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [74,0,0] Assertion srcIndex < srcSelectDimSize failed. ../aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [75,0,0] Assertion srcIndex < srcSelectDimSize failed. ../aten/src/ATen/native/cuda/Indexing.cu:703: indexSelectLargeIndex: block: [40,0,0], thread: [76,0,0] Assertion srcIndex < srcSelectDimSize failed.

SWHL commented 1 year ago
wayy13 commented 1 year ago
  • 训练模型应该是仓库作者自己训练的
  • 报这个错误是因为你的vocab与模型的vocab大小不一导致的

您好 想请教一下自己的训练数据vocab与模型的vocab大小不一导致的 该如何修改呢

SWHL commented 1 year ago

如果想用作者的训练模型，就需要找模型对应的vocab了