The Classification library is used to classify images. Such neural networks are trained on ImageNet for ILSVRC and they can identify the objects from a thousand classes. The Vitis AI Library integrates networks including, but not limited to, ResNet18, ResNet50, Inception_v1, Inception_v2, Inception_v3, Inception_v4, VGG, mobilenet_v1, mobilenet_v2, and Squeezenet into Xilinx libraries. The input is a picture with an object and the output is the top-K most probable category.
Figure 1. Classification Example
The following table lists the classification models supported by the Vitis AI library.
| No | Model Name | Framework |
|---|---|---|
| 1 | inception_resnet_v2_tf | TensorFlow |
| 2 | inception_v1_tf | |
| 3 | inception_v3_tf | |
| 4 | inception_v4_2016_09_09_tf | |
| 5 | mobilenet_v1_0_25_128_tf | |
| 6 | mobilenet_v1_0_5_160_tf | |
| 7 | mobilenet_v1_1_0_224_tf | |
| 8 | mobilenet_v2_1_0_224_tf | |
| 9 | mobilenet_v2_1_4_224_tf | |
| 10 | resnet_v1_101_tf | |
| 11 | resnet_v1_152_tf | |
| 12 | resnet_v1_50_tf | |
| 13 | vgg_16_tf | |
| 14 | vgg_19_tf | |
| 15 | mobilenet_edge_1_0_tf | |
| 16 | mobilenet_edge_0_75_tf | |
| 17 | inception_v2_tf | |
| 18 | MLPerf_resnet50_v1.5_tf | |
| 19 | resnet50_tf2 | |
| 20 | mobilenet_1_0_224_tf2 | |
| 21 | inception_v3_tf2 | |
| 22 | resnet_v2_50_tf | |
| 23 | resnet_v2_101_tf | |
| 24 | resnet_v2_152_tf | |
| 25 | efficientnet-b0_tf2 | |
| 26 | efficientNet-edgetpu-S_tf | |
| 27 | efficientNet-edgetpu-M_tf | |
| 28 | efficientNet-edgetpu-L_tf | |
| 29 | mobilenet_v3_small_1_0_tf2 | |
| 30 | resnet50 | Caffe |
| 31 | resnet18 | |
| 32 | inception_v1 | |
| 33 | inception_v2 | |
| 34 | inception_v3 | |
| 35 | inception_v4 | |
| 36 | mobilenet_v2 | |
| 37 | squeezenet | |
| 38 | resnet50_pt | PyTorch |
| 39 | squeezenet_pt | |
| 40 | inception_v3_pt | |
| 41 | ofa_resnet50_0_9B_pt | |
| 42 | person-orientation_pruned_558m_pt | |
| 43 | ofa_depthwise_res50_pt |