首页 Paddle框架 帖子详情
跑模型遇到问题
收藏
快速回复
Paddle框架 问答深度学习 637 1
跑模型遇到问题
收藏
快速回复
Paddle框架 问答深度学习 637 1

(paddle) bjjx@bjjx-Z690-GAMING-X-DDR4:~/paddlex_webapi$ python3 predict_paddlex.batch1.py -m ./models/yolo3_0321/ -i /home/bjjx/nfsjx_dir/Bin_blue -o /media/bjjx/dataset/batch_results -t infer -n 1000 -s 800
2022-11-07 14:31:33,174-WARNING: type object 'QuantizationTransformPass' has no attribute '_supported_quantizable_op_type'
2022-11-07 14:31:33,174-WARNING: If you want to use training-aware and post-training quantization, please use Paddle >= 1.8.4 or develop version
/home/bjjx/anaconda3/envs/paddle/lib/python3.7/site-packages/paddlex/ppcls/data/preprocess/ops/timm_autoaugment.py:38: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
_RANDOM_INTERPOLATION = (Image.BILINEAR, Image.BICUBIC)
/home/bjjx/anaconda3/envs/paddle/lib/python3.7/site-packages/paddlex/ppcls/data/preprocess/ops/timm_autoaugment.py:38: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
_RANDOM_INTERPOLATION = (Image.BILINEAR, Image.BICUBIC)
2022-11-07 14:31:34,188 - INFO - predict_paddlex.batch1.py:292 - ####################
2022-11-07 14:31:34,188 - INFO - predict_paddlex.batch1.py:293 - predict_paddlex.batch1.py -m ./models/yolo3_0321/ -i /home/bjjx/nfsjx_dir/Bin_blue -o /media/bjjx/dataset/batch_results -t infer -n 1000 -s 800
2022-11-07 14:31:34,188 - INFO - predict_paddlex.batch1.py:294 - handling [/media/bjjx/dataset/batch_results]
Traceback (most recent call last):
File "predict_paddlex.batch1.py", line 474, in
main()
File "predict_paddlex.batch1.py", line 278, in main
batch_handle(args, image_dir, output_dir)
File "predict_paddlex.batch1.py", line 282, in batch_handle
predict(args, image_dir, output_dir)
File "predict_paddlex.batch1.py", line 320, in predict
model_name=model_name, threshold=args.threshold, use_gpu=True, gpu_id=args.gpu_id)
File "/home/bjjx/paddlex_webapi/paddlex_predictor.py", line 85, in __init__
self.model = pdx.deploy.Predictor(self.model_path, use_gpu=use_gpu, gpu_id=gpu_id)
File "/home/bjjx/anaconda3/envs/paddle/lib/python3.7/site-packages/paddlex/deploy.py", line 52, in __init__
self._model = load_model(model_dir, with_net=False)
File "/home/bjjx/anaconda3/envs/paddle/lib/python3.7/site-packages/paddlex/cv/models/load_model.py", line 68, in load_model
format(paddlex.__version__, version))
Exception: Current version is 2.1.0, a model trained by PaddleX=1.2.8 cannot be load.

 

帮忙看看是什么问题

0
收藏
回复
全部评论(1)
时间顺序
L
Linq1呀
#2 回复于2022-11

最后一行写了呀,你的PaddleX版本太高了,而预训练是低版本训练出来的,你需要降低PaddleX版本

0
回复
需求/bug反馈?一键提issue告诉我们
发现bug?如果您知道修复办法,欢迎提pr直接参与建设飞桨~
在@后输入用户全名并按空格结束,可艾特全站任一用户