-
-
from transformers import VisionEncoderDecoderModel
model = VisionEncoderDecoderModel.from_pretrained('./model/hand-write/')
模型目录包含pytorch_model.bin和config文件
换成mindnlp.transformers后，没有VisionEncode…
-
Tesseract was trained on documents. Passing entire 1920x1080 screenshot will yield dubious performance.
Screenshots should be split into 3:4 aspect ratio images, ran in batches through tesseract, t…
-
Make tests for models that will use appropriate validation data set (e.g., SQUAD, hellaswag) to run model and compare output to expected outputs from data set.
This tests should be organized in a simi…
-
Hi, I am using TrOCR to transcribe historical (18th century) handwritten French data.
I am feeding in text-line images which are segmented using doc-ufcn. However, due to the nature of the document…
-
I was trying to train a VisionEncoderDecoderModel and I got the below error. For decoder I'm using bert-base-multilingual-cased and encoder is google/vit-base-patch16-224. How to solve this error? Tha…
-
请问如果我想要修改训练的预处理size为其他值，我该怎么改呢
-
Hi, after reading the code, it seems that the pretrained weights need to be used in conjunction with a tokenizer and some other libraries:
```py
x = self._preprocess(img)
x = self.model.generate(…
-
I tried to convert TrOCR in onnx format to tf lite, but convert.py throw such a strange mistake
feff2 updated
4 months ago
-
# Export Error Summary Dashboard ##
- This report is generated from branch of https://github.com/huggingface/optimum/pull/1712
- Produced by `RUN_SLOW=1 pytest tests/exporters/onnx -k "test_export…