NVCaffe Release 19.07
The NVIDIA container image of Caffe, release 19.07, is available on NGC.
Contents of the NVCaffe container
This container image contains the complete source of the version of NVCaffe in /opt/caffe. It is pre-built and installed into the /usr/local/[bin,share,lib] directories in the container image.
The container also includes the following:
- Ubuntu 18.04 including Python 2.7
- NVIDIA CUDA 10.1.168 including cuBLAS 10.2.0.168
- NVIDIA cuDNN 7.6.1
- NVIDIA NCCL 2.4.7 (optimized for NVLink™ )
- MLNX_OFED +3.4
- OpenMPI 3.1.3
- TensorRT 5.1.5
- Jupyter and JupyterLab:
Driver Requirements
Release 19.07 is based on NVIDIA CUDA 10.1.168, which requires NVIDIA Driver release 418.67. However, if you are running on Tesla (Tesla V100, Tesla P4, Tesla P40, or Tesla P100), you may use NVIDIA driver release 384.111+ or 410. The CUDA driver's compatibility package only supports particular drivers. For a complete list of supported drivers, see the CUDA Application Compatibility topic. For more information, see CUDA Compatibility and Upgrades.
GPU Requirements
Release 19.07 supports CUDA compute capability 6.0 and higher. This corresponds to GPUs in the Pascal, Volta, and Turing families. Specifically, for a list of GPUs that this compute capability corresponds to, see CUDA GPUs. For additional support details, see Deep Learning Frameworks Support Matrix.
Key Features and Enhancements
This NVCaffe release includes the following key features and enhancements.
- NVCaffe 0.17.3 container image version 19.07 is based on Caffe Deep Learning Framework by the BVLC.
- Fixed a bug that prevented the usage of batch size = 1 with pictures of different sizes.
- Latest version of NVIDIA cuDNN 7.6.1
- Latest version of MLNX_OFED +3.4
- Latest versions of Jupyter Client 5.3.1, Jupyter Core 4.5.0, JupyterLab 1.0.2 and JupyterLab Server 1.0.0, including Jupyter-TensorBoard integration.
- Latest version of Ubuntu 18.04
Known Issues
There are no known issues in this release.