ZenNAS is a lighting fast Neural Architecture Searching (NAS) algorithm for automatically designing deep neural networks with high prediction accuracy and high inference speed on GPU and mobile device.

Our paper is available here: arXiv link

Using 1 GPU searching for 12 hours, ZenNAS is able to design networks of ImageNet top-1 accuracy comparable to EfficientNet-B5 (~83.6%) while inference speed 4.9x times faster on V100, 10x times faster on NVIDIA T4, 1.6x times faster on Google Pixel2.

To evaluate the pre-trained model on ImageNet using GPU 0:

python val.py --fp16 --gpu 0 --arch ${zennet_model_name}

where ${zennet_model_name} should be replaced by a valid ZenNet model name. The complete list of model names can be found in 'Pre-trained Models' section.

To evaluate the pre-trained model on CIFAR10 or CIFAR100 using GPU 0:

python val_cifar.py --dataset cifar10 --gpu 0 --arch ${zennet_model_name}

To create a ZenNet in your python code:

gpu=0
model = ZenNet.get_ZenNet(opt.arch, pretrained=True)
torch.cuda.set_device(gpu)
torch.backends.cudnn.benchmark = True
model = model.cuda(gpu)
model = model.half()
model.eval()

• PyTorch >= 1.5, Python >= 3.7
• By default, ImageNet dataset is stored under ~/data/imagenet; CIFAR10/CIFAR100 is stored under ~/data/pytorch_cifar10 or ~/data/pytorch_cifar100
• Pre-trained parameters are cached under ~/.cache/pytorch/checkpoints/zennet_pretrained

We provided pre-trained models on ImageNet and CIFAR10/CIFAR100.

• 'V100' is the inference latency on NVIDIA V100 in milliseconds, benchmarked at batch size 64, float16.
• 'T4' is the inference latency on NVIDIA T4 in milliseconds, benchmarked at batch size 64, TensorRT INT8.
• 'Pixel2' is the inference latency on Google Pixel2 in milliseconds, benchmarked at single image.

• Ming Lin (Home Page, [email protected])
• Pichao Wang ([email protected])
• Zhenhong Sun ([email protected])
• Hesen Chen ([email protected])

Copyright (C) 2010-2021 Alibaba Group Holding Limited.