I also encountered similar situations Problem with:
Username: $oauthtoken
Password:
Error response from daemon: login attempt to https://nvcr.io/v2/ failed with status: 502 Bad Gateway
@spolisetty
Thanks, it seem that I used implicit quantization with batch size = 1. When running inference, I used execute_async_v2() and it did not work.
@spolisetty
Method execute_async() work, but output of engine model is seem not correct.
I debug my inference code and recognize that output values is very small. Output has length 4, predictions[3] is class index of my model (from 0 to 79), but 4.2e-42 is obtained. This values seem allocated values from system.
Are you still facing the above issue?
If you still face the issue, please open a new post with complete error logs and minimal issue repro (ONNX model and scripts) for better debugging.