XuLU

[inference_model_picodet_esnet_l.zip](https://github.com/PaddlePaddle/PaddleX/files/8219838/inference_model_picodet_esnet_l.zip) 模型文件已上传

@JingyuanZhang 麻烦有空的时候看看 谢谢

可能是 while 循环的问题？ 

【队名】：一只菜鸟 【序号】：58 【状态】：报名 【链接】：[luxu1220/PaddleScience](https://github.com/luxu1220/PaddleScience)

@w5688414 同样的项目，macos 下也有报错，报错信息如下，麻烦请问该如何解决呢，谢谢 ``` ❯ python web_service.py config use_encryption model here None config use_encryption model here None Traceback (most recent call last): File "", line 1, in File "/Users/luxu/.pyenv/versions/3.8.12/lib/python3.8/multiprocessing/spawn.py", line...

将 is_thread_op 改为 true 后 ``` # op资源类型, True, 为线程模型；False，为进程模型 is_thread_op: True ``` 报错变为 ``` ❯ python web_service.py config use_encryption model here None [DAG] Succ init E0629 11:19:20.553887 302106112 analysis_config.cc:95]...

onnx 转 pb 报错，请问有遇到过吗？谢谢 RuntimeError: Node name is not unique in your model. Please recreate your model with unique node name.

uninstall and reinstall may help. maybe you install rocketmq-client-python before librocketmq. you need to reinstall rocketmq-client-python after install librocketmq

@qiano 是 picodet吗，我也遇到同样的问题，现在模型转换前后的精度对齐了，但是同一张图片输出的预测值还有有偏差，在js里面bbox画出来的预测框和 paddledetection预测的位置大致一致，但是明显边界上差很多，你有遇到吗

same error here ~/work/.localenv/lib/python3.5/site-packages/Augmentor/Pipeline.py in keras_generator(self, batch_size, scaled, image_data_format) 538 539 if scaled: --> 540 X = X.astype('float32') 541 X /= 255. # PR #126 542 ValueError: setting an array...