ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
SegIC
Model
NVIDIA
NVIDIA
SegIC

In-context segmentation model trained on commercial data.

2 Versions
segic_deployable_v1.0Selected
08/23/2024 1:07 AM UTC1.15 GBBatch Size: 1GPU: V100
SHA256 digests
KeyValue
segic_deployable_v1.0.onnx62e560ff2aaa63a23ac2977634c8247e1b903b2e1ebe9fde57e0b5687dc34fe3
TAO Toolkit API
KeyValue
is_backboneFalse
endpoints['segic']
format_version0.0.1
model_formatonnx
tao_version['>=5.5.0']
trainableFalse
TAO Toolkit UI Metadata
KeyValue
licenseNVAIE EULA
taskobject segmentation
format_version0.0.1
backbone_typetransformer
domainpretrained
accuracy90.4%
num_parameters432.8M
backbone_classvit_large
prompt_feature_extract_deployable_v1.0
08/23/2024 1:06 AM UTC1.55 GBBatch Size: 1GPU: V100
SHA256 digests
KeyValue
prompt_feature_extract_deployable_v1.0.onnx30dff0b2e9c331ec8442a95600cc1d278ec74e17e61fcca88ce2693f75b93eca
TAO Toolkit API
KeyValue
is_backboneTrue
endpoints['segic']
format_version0.0.1
model_formatonnx
tao_version['>=5.5.0']
trainableFalse
TAO Toolkit UI Metadata
KeyValue
licenseNVAIE EULA
taskobject segmentation
format_version0.0.1
backbone_typetransformer
domainpretrained
accuracy90.4%
num_parameters432.8M
backbone_classvit_large + vit_base