TI Deep Learning Library User Guide
Pre-trained CNN Models for TIDL

Both Import and inference configuration files for all the below models are part of TIDL software release package

Caffe Models

Num Network Architecture Source Comments
1 JacintoNet11v2 Link
2 squeezeNet1.1 Link
3 ResNet 10 Link
4 MobileNetv1 1.0 Link
5 ResNet 50 Proto Link
Model Link 		Refer Note 1
6 ShuffleNet Link
7 VGGNet 16 Link Not Validated on TIDL Yet, Only for Performance simulator. Refer Note 2
8 DenseNet121 Link
9 resnext50-32x4d Link
10 JdetNet512x512 Link Refer Note 3
11 Pelee Pascal VOC 304x304 Link Refer Note 3
12 JsegNet21v2 102x512 link

Tensorflow Models

Num Network Architecture Source Comments
1 MobileNet v1 Frozen Graph Link
More models can be found mobilenet_v1.md 		Optimize the graph for inference. Refer Note 4
2 InceptionNet v1 (googleNet) Checkpoint Link Generate Frozen Graph and Optimize it for inference. Refer Note 5
3 MobileNet v2 Frozen Graph Link
More models can be found here 		Optimize the graph for inference. Refer Note 4
4 Resnet 50 V1 Checkpoint Link Generate Frozen Graph and Optimize it for inference. Refer Note 5
5 Resnet 50 V2 Checkpoint Link Generate Frozen Graph and Optimize it for inference. Refer Note 5
6 ssd_mobilenet_v1_0.75 SSD Link Generate Frozen Graph and Optimize it for inference. Refer Note 6
7 ssd_mobilenet_v1 1.0 SSD Link Generate Frozen Graph and Optimize it for inference. Refer Note 6
8 ssd_mobilenet_v2 SSD Link Generate Frozen Graph and Optimize it for inference. Refer Note 6

ONNX Models

Num Network Architecture Source Comments
1 MobileNet v2 Link
2 SqueezeNet 1.1 Link
3 Resnet 18 v1 Link
4 Resnet 18 v2 Link
5 ShuffleNet Link
6 VGG 16 Link

Notes

1. Download and Convert the "ResNet_mean.binaryproto" to simple raw float file Modify Below layer in ResNet-50-deploy.prototxt, replace kernel_size: 7 with global_pooling: true 

layer {
  bottom: "res5c"
  top: "pool5"
  name: "pool5"
  type: "Pooling"
  pooling_param { 
  kernel_size: 7
  stride: 1
  pool: AVE
  }
}

2.

  • Use below commands to Upgrade prototext and Model
    • $CAFFE_ROOT/build/tools/upgrade_net_proto_text deploy_old.prototx deploy.prototxt
    • $CAFFE_ROOT/build/tools/upgrade_net_proto_binary deploy_old.caffemodel deploy.caffemodel

3.

  • SSD based Object detection network trained on PASCAL VOC data set
  • Update "confidence_threshold: 0.01" to confidence_threshold: 0.4

4.

  • Optimize Frozen Graph for inference using below tensorflow tool
    python "tensorflow\python\tools\optimize_for_inference.py" --input=mobilenet_v1_1.0_224_frozen.pb --output=mobilenet_v1_1.0_224_final.pb --input_names=input --output_names="MobilenetV1/Predictions/Softmax"

5.

6.