Nick Kao

I am using CRAFT-pytorch(https://github.com/clovaai/CRAFT-pytorch). and want to transfer keras.(pytorch>onnx>keras) Its architecture is VGG-16(backbone). The "Cast" opearator in ONNX(https://github.com/onnx/onnx/blob/master/docs/Operators.md#Cast)

謝謝回覆！ 不過如果因為此問題，那所有類似的目錄都會重新定義， 像我目前跑train.py時，就感覺怪怪的， 似乎沒有 正常依ModelCheckpoint在filepath='/tmp/frcnn-' + config.BASE_NET_NAME + '.{epoch:03d}.h5',在tmp目錄中保存模型？ 這樣有點麻煩，有可以共通的方法嗎？ 不好意思，因為我是python新手，有許多觀念不瞭解。

me too.(same error)

Please refer to the following link as an example. Usually, if you need to connect to the outside through the internal http/https proxy server within the company, you usually need...

The whole process is as follows, the main thing is that it is stuck in HTTP/HTTPS Proxy Client ---> LlitLLM Proxy Server ---> **HTTP/HTTPS Proxy** ---> External Resource (Azure OpenAI...

I found the reason. The router.py program needs to be adjusted. The set_client() method needs to set http/https proxy settings sample code: ```python import os if os.getenv("HTTP_PROXY") is not None...