ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Mask2Former
Model
NVIDIA
NVIDIA
Mask2Former

Binary instance segmentation model trained on COCO data.

2 Versions
mask2former_swint_trainable_v1.0Selected
08/24/2024 6:29 PM UTC543.33 MBBatch Size: 1GPU: V100
SHA256 digests
KeyValue
experiment.yamlf4216dd8e31ab5c13b81a022f3ea7f81011f078c7176fb017769550f7cfe2c53
mask2former_swint.pth93f7e5a3ed960a9d6723b42e55e3cecc4aca9ef11bd5e96680bef2789fa3c356
TAO Toolkit API
KeyValue
is_backboneFalse
endpoints['mask2former']
format_version0.0.1
model_formatpth
tao_version['>=5.5.0']
trainableTrue
TAO Toolkit UI Metadata
KeyValue
licenseNVAIE EULA
taskinstance segmentation
format_version0.0.1
backbone_typetransformer
domainpretrained
accuracy96%
num_parameters47M
backbone_classswin_tiny
mask2former_swint_deployable_v1.0
08/24/2024 6:29 PM UTC200.67 MBBatch Size: 1GPU: V100
SHA256 digests
KeyValue
experiment.yamlcd95030b9ec9de6cb4f0fceb6afdbb699b8c25779f60202c3011ecfb5f30fe67
mask2former_swint.onnx3f0b9c2478efdab5f0851b828f28c9a7a270e1fa121acf5a5dde9787018dfd1a
TAO Toolkit API
KeyValue
is_backboneFalse
endpoints['mask2former']
format_version0.0.1
model_formatonnx
tao_version['>=5.5.0']
trainableFalse
TAO Toolkit UI Metadata
KeyValue
licenseNVAIE EULA
taskinstance segmentation
format_version0.0.1
backbone_typetransformer
domainpretrained
accuracy96%
num_parameters47M
backbone_classswin_tiny