THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
Performance
Performance Boost with Intel MKL-DNN backend from various models
Category | Model | Latency batchsize=1 (ms, small is better) | Throughput batchsize=128 (fps, big is better) | ||||
| w/o MKL-DNN | w/ MKL-DNN | speedup | w/o MKL-DNN | w/ MKL-DNN | speedup | ||
CNN/classification | ResNet-50 v1 | ||||||
| ResNet-50 v2 | |||||||
| Inception v3 | |||||||
| Inception v4 | |||||||
| DenseNet | |||||||
| MobileNet | |||||||
| VGG16 | |||||||
| AlexNet | |||||||
| inception-resnet v2 | |||||||
CNN/object detection | Faster R-CNN | ||||||
| SSD-VGG16 | |||||||
| SSD-MobileNet | |||||||
RNN | GNMT | ||||||
| GAN | DCGAN | ||||||
Inference Accuracy
| topology | top1 | top1 | ||
| CPU w/o Intel MKL-DNN | CPU w/ Intel MKL-DNN | CPU w/o Intel MKL-DNN | CPU w/ Intel MKL-DNN | |
| alexnet | ||||
| resnet50_v1 | ||||
| resnet50_v2 | ||||
| vgg16 | ||||
| densenet121 | ||||
| squeezenet1.1 | ||||
| mobilenet1.0 | ||||
| inceptionv3 | ||||