如何指定PP-OCRv5_server_rec？

[13316090972]

from paddleocr import TextRecognition
model = TextRecognition(model_name="PP-OCRv5_server_rec")
output = model.predict(input="general_ocr_rec_001.png", batch_size=1)
for res in output:
res.print()
res.save_to_img(save_path="./output/")
res.save_to_json(save_path="./output/res.json")

[13316090972]

(paddle) mazz@node63:~/PaddleOCR$ python3 simocr.py
Traceback (most recent call last):
File "simocr.py", line 2, in
model = TextRecognition(model_name="PP-OCRv5_server_rec")
File "/home/mazz/PaddleOCR/paddleocr/_models/text_recognition.py", line 33, in init
super().init(**kwargs)
File "/home/mazz/PaddleOCR/paddleocr/_models/base.py", line 55, in init
self.paddlex_predictor = self._create_paddlex_predictor()
File "/home/mazz/PaddleOCR/paddleocr/_models/base.py", line 81, in _create_paddlex_predictor
return create_predictor(
File "/home/mazz/.local/lib/python3.8/site-packages/paddlex/inference/models/init.py", line 66, in create_predictor
assert (
AssertionError: The model (PP-OCRv5_server_rec) is not supported! Please using directory of local model files or model name supported by PaddleX!

[13316090972]

如果将model_name改成PP-OCRv4_server_rec，可以正常运行。
(paddle) mazz@node63:~/PaddleOCR$ python3 simocr.py
Using official model (PP-OCRv4_server_rec), the model files will be automatically downloaded and saved in /home/mazz/.paddlex/official_models.
Connecting to https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_rec_infer.tar ...
Downloading PP-OCRv4_server_rec_infer.tar ...
[==================================================] 100.00%
Extracting PP-OCRv4_server_rec_infer.tar
[==================================================] 100.00%
{'res': {'input_path': 'general_ocr_rec_001.png', 'page_index': None, 'rec_text': '绿洲仕格维花园公寓', 'rec_score': 0.9943880438804626}}

[13316090972]

删除并重装conda环境，删除并重新clone代码仓库，问题解决。

[wei-ma]

你好怎么按照路径指定
model = TextRecognition(model_name="PP-OCRv5_server_rec")

[wei-ma]

不要再从新下砸， 直接从 model_path读取