phelan

SAR model with batching error

1

Thanks for your bug report. We appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md)...

Export texdet models to onnx failed

3

Thanks for your bug report. We appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md)...

Deploy Nuclio into GKE

9

When I tried with kubectl apply -f https://raw.githubusercontent.com/nuclio/nuclio/master/hack/gke/resources/nuclio.yaml => Got error: unable to recognize "https://raw.githubusercontent.com/nuclio/nuclio/master/hack/gke/resources/nuclio.yaml": no matches for kind "Deployment" in version "apps/v1beta1" Could we update nuclio.yaml to apps/v1? btw,...

GPU on GCP issue

1

[run GPU on GCP issue] I installed nuclio on Kubenetes Engine of GCP and could run CPU node successfully but GPU not working. My cluster have GPU pool with 1...

Github private repo

1

How we install private github repo from dashboard UI on k8s? I think need add secrets k8s to yaml file but do know how to do from dashboard Any suggestion?

Inference with pretrained checkpoint

2

I tried: - download pretrain checkpoint D0 and D7 - save model: `python model_inspect.py --runmode=saved_model --model_name=efficientdet-d0 --ckpt_path=efficientdet-d0 --saved_model_dir=/tmp/saved_model_0` - inference with image: `python model_inspect.py --runmode=saved_model_infer --saved_model_dir=/tmp/saved_model_0 --model_name=efficientdet-d0 --input_image=/tmp/train_all/00053190460d56c53cc3e57321387478.jpg --output_image_dir=out `...

loss plot

1

I tried and get weird lr by finding  Could you help me explain why it is

Python backend cannot import Tensor

6

**Description** Python backend model import Tensor `from triton_python_backend_utils import Tensor` Got error: UNAVAILABLE: Internal: ImportError: cannot import name 'Tensor' from 'triton_python_backend_utils' (/opt/tritonserver/backends/python/triton_python_backend_utils.py Triton inference server version 22.05 still work well...

Get shm memory status

2

**Is your feature request related to a problem? Please describe.** When deploy many Python backend models, triton inference server run out of `shm` memory **Describe the solution you'd like** I...

Local deployment (Docker, not Kubernetes/MiniKube)

2

I am new with modelmesh but so interested in this project. Could we deploy modelmesh using Docker only without k8s cluster? Thanks