Skip to content

v1.5.0

Compare
Choose a tag to compare
@trevor-m trevor-m released this 10 Nov 21:10
7fb956c

Release 1.5.0 can be used to run models compiled using the release-1.5.0 branch of neo-ai/TVM.

This update enables support for TensorFlow object detection models on GPU. For these particular models, since part of the model runs on CPU while the other part runs on GPU, the model might have to be loaded with dev_type='cpu'. The DeviceType field in the metadata file will now tell you which device type is required. This can be queried using GetDLRDeviceType.

Pre-built wheels can be installed via pip install link-to-wheel. If you don't see your platform in the table, see Installing DLR for instructions to build from source.

Manufacturer Device Name Wheel URL
Acer TV AISage https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/aisage/dlr-1.5.0-py3-none-any.whl
Amazon AWS p2/p3/g4 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/gpu/dlr-1.5.0-py3-none-any.whl
NVIDIA Jetson device with JetPack 4.2 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/jetpack4.2/dlr-1.5.0-py3-none-any.whl
NVIDIA Jetson device with JetPack 4.2.2 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/jetpack4.2.2/dlr-1.5.0-py3-none-any.whl
NVIDIA Jetson device with JetPack 4.3 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/jetpack4.3/dlr-1.5.0-py3-none-any.whl
NVIDIA Jetson device with JetPack 4.4 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/jetpack4.4/dlr-1.5.0-py3-none-any.whl
Raspberry Rasp3b https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/rasp3b/dlr-1.5.0-py3-none-any.whl
Rockchips RK3399 https://neo-ai-dlr-release.s3-us-west-2.amazonaws.com/v1.5.0/rk3399/dlr-1.5.0-py3-none-any.whl