Hello,
I am running an AWS EC2 instance which is running the Clara Train SDK. I have successfully set up the Clara Train Server, and have been able to load 2 models onto it using the following syntax:
curl -X PUT "http://127.0.0.1:5000/admin/model/clara_pt_brain_mri_segmentation_t1c" -H "accept: application/json" -H "Content-Type: application/json" -d '{"path":"nvidia/med/clara_pt_brain_mri_segmentation_t1c", "version":"1”}’
When I run curl http://$AIAA_URL:LOCAL_PORT/v1/models
I recieve the following output:
[
{
"name": "clara_pt_brain_mri_annotation_t1c",
"labels": [
"brain tumor core"
],
"description": "A pre-trained model for volumetric (3D) segmentation of the tumor from MRI T1C image using DEXtr3D",
"version": "1",
"type": "annotation"
},
{
"name": "clara_pt_spleen_ct_segmentation",
"labels": [
"spleen"
],
"description": "A pre-trained model for volumetric (3D) segmentation of the spleen from CT image",
"version": "1",
"type": "segmentation"
}
]
Everything is looking normal. But when I try to load the DeepGrow 3D model found here clara_pt_deepgrow_3d_annotation | NVIDIA NGC using the following syntax
curl -X PUT "http://127.0.0.1:5000/admin/model/clara_pt_deepgrow_3d_annotation" -H "accept: application/json" -H "Content-Type: application/json" -d '{"path":"nvidia/med/clara_pt_deepgrow_3d_annotation", "version":"1”}’
My request hangs for 20+ minutes. I have no idea why. Can someone please help me debug this issue.
Thanks,
Shane