NVIDIA today announced the latest updates to its GPU-accelerated deep learning software that will double deep learning training performance. With the latest software, it will empower data scientists and researchers to supercharge their deep learning projects and product development work by producing more accurate neural networks through faster model training and more sophisticated model design.
The NVIDIA DIGITS Deep Learning GPU Training System version 2 (DIGITS 2) and NVIDIA CUDA Deep Neural Network library version 3 (cuDNN 3) provide significant performance enhancements and new capabilities. Apart from that, data scientist can use DIGITS 2 to deliver automatic scaling of neural network training across multiple high-performance GPUs that will double the speed of deep neural network training for image classification compared to a single GPU.
For deep learning researchers, codeine 3 features optimized data stored in GPU memory for the training of larger, more sophisticated neural network and it also provides higher performance than cuDNN 2 by enabling researchers to train neural networks up to two times faster on a single GPU. Apart from that, the new cuDNN 3 libraries will be expected to integrate into forthcoming versions of the deep learning frameworks Caffe, Minerva, Theano and Torch, which are widely used to train deep neural networks.
The all new automatic multi-GPU scaling capability in DIGITS 2 maximizes the available GPU resources by automatically distributing the deep learning training workload across all of the GPUs in the system. By using DIGITS 2, NVIDIA engineers trained the well-known AlexNet neural network model more than two times faster on four NVIDIA Maxwell architecture-based GPUs, compared to a single GPU and initial results from early customers are demonstrating better results.
The DIGITS 2 preview release is already available today as a free download for NVIDIA registered developers and to learn more or download, visit the DIGITS website. The cuDNN 3 libraries are expected to be available in major deep learning frameworks in the coming months.
The DIGITS 2 Preview release is available today as a free download for NVIDIA registered developers. To learn more or download, visit the DIGITS website. The cuDNN 3 libraries are expected to be available in major deep learning frameworks in the coming months. To learn more, visit the cuDNN website.
