Models Supported by Vitis AI Library v3.5 - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English

Model Support

The following models are supported by this version of the Vitis AI Library.

Table 1. Models Supported by the Vitis AI Library
No. Neural Network VEK280 V70 Application
1 inception_v1_tf Y Y Image Classification
2 inception_v3_tf Y Y
3 inception_v4_2016_09_09_tf Y Y
4 mobilenet_v1_0_25_128_tf Y Y
5 mobilenet_v1_1_0_224_tf Y Y
6 mobilenet_v2_1_0_224_tf Y Y
7 mobilenet_v2_1_4_224_tf Y Y
8 resnet_v1_101_tf Y Y
9 resnet_v1_152_tf Y Y
10 resnet_v1_50_tf Y Y
11 vgg_16_tf Y Y
12 vgg_19_tf Y Y
13 ssd_mobilenet_v1_coco_tf Y Y Object Detection
14 ssd_mobilenet_v2_coco_tf Y Y
15 yolov3_voc_tf Y Y
16 mlperf_ssd_resnet34_tf Y Y
17 resnet50_pt Y Y Image Classification
18 squeezenet_pt Y Y
19 inception_v3_pt Y Y
20 pointpillars_kitti_12000_0_pt


Y Y Point Cloud
21 MLPerf_resnet50_v1.5_tf Y Y Image Classification
22 RefineDet-Medical_EDD_tf Y Y Medical Detection
23 resnet_v2_50_tf Y Y Image Classification
24 resnet_v2_101_tf Y Y
25 resnet_v2_152_tf Y Y
26 resnet50_tf2 Y Y
27 inception_v3_tf2 Y Y
28 efficientNet-edgetpu-S_tf Y Y
29 efficientNet-edgetpu-M_tf Y Y
30 efficientNet-edgetpu-L_tf Y Y
31 pointpillars_nuscenes_40000_64_0_pt


Y Y 3D object detection
32 FADNet_0_pt



N/A N/A Depth Estimation
33 rcan_pruned_tf Y Y Super Resolution
34 efficientnet-b0_tf2 N/A N/A Classification
35 HardNet_MSeg_pt Y Y Polyp Segmentation
36 ofa_resnet50_0_9B_pt Y Y Classification
37 SESR_S_pt Y Y Image Super-Resolution
38 ofa_depthwise_res50_pt Y Y Classification
39 FADNet_pruned_0_pt



N/A N/A Depth Estimation
40 PSMNet_pruned_0_pt



41 mobilenet_v3_small_1_0_tf2 N/A N/A Classification
42 ssr_pt Y Y Spectral Remove
43 chen_color_resnet18_pt Y Y Classification
44 face_mask_detection_pt Y Y Face mask Detection
45 ofa_rcan_latency_pt Y Y Super Resolution
46 vehicle_make_resnet18_pt Y Y Classification
47 vehicle_type_resnet18_pt Y Y Classification
48 ofa_yolo_pt Y Y Object Detection
49 ofa_yolo_pruned_0_30_pt Y Y
50 ofa_yolo_pruned_0_50_pt Y Y
51 efficientdet_d2_tf N/A N/A
52 superpoint_tf Y N/A SLAM
53 hfnet_tf Y N/A SLAM
54 movenet_ntd_pt Y Y Pose Estimation
55 yolov3_coco_416_tf2 Y Y Object Detection
56 yolov4_leaky_416_tf Y Y
57 yolov4_leaky_512_tf Y Y
58 HRNet_pt N/A N/A Segmentation
59 xilinxSR_pt N/A N/A Super Resolution
60 yolov4_csp_pt Y Y Object Detection
61 yolov5_nano_pt Y Y
62 yolov5s6_pt Y Y
63 yolov5_large_pt Y N/A
64 yolox_nano_pt Y Y
65 yolov6_pt Y Y
66 3D-Unet_pt N/A N/A Medical Segmentation
67 FADNet_v2_0_pt



Y Y Depth Estimation
68 FADNet_v2_pruned_0_pt FADNet_v2_pruned_1_pt FADNet_v2_pruned_2_pt Y N/A
69 unet2d_tf2 Y Y Segmentation
70 yolov5l_pt Y N/A Object Detection
71 yolov5m_pt Y Y
72 yolov7_pt Y Y
73 yolov8m_pt Y Y
  1. Networks with the suffix "_tf" or "_tf2" were trained on TensorFlow.
  2. Networks with the suffix "_pt" were trained on PyTorch.