@@ -90,33 +90,33 @@ The export script called `aot_optimize_and_infer.py` allows users to export deep
9090 Examples: ` CPU ` , ` GPU `
9191
9292
93- ### ** Examples**
93+ #### ** Examples**
9494
95- #### Export a TIMM VGG16 model for the CPU
95+ ##### Export a TIMM VGG16 model for the CPU
9696``` bash
9797python aot_optimize_and_infer.py --export --suite timm --model vgg16 --input_shape [1, 3, 224, 224] --device CPU
9898```
9999
100- #### Export a Torchvision ResNet50 model for the GPU
100+ ##### Export a Torchvision ResNet50 model for the GPU
101101``` bash
102102python aot_optimize_and_infer.py --export --suite torchvision --model resnet50 --input_shape " (1, 3, 256, 256)" --device GPU
103103```
104104
105- #### Export a Hugging Face BERT model for the CPU
105+ ##### Export a Hugging Face BERT model for the CPU
106106``` bash
107107python aot_optimize_and_infer.py --export --suite huggingface --model bert-base-uncased --input_shape " (1, 512)" --device CPU
108108```
109- #### Export and validate TIMM Resnet50d model for the CPU
109+ ##### Export and validate TIMM Resnet50d model for the CPU
110110``` bash
111111python aot_optimize_and_infer.py --export --suite timm --model vgg16 --input_shape [1, 3, 224, 224] --device CPU --validate --dataset /path/to/dataset
112112```
113113
114- #### Export, quantize and validate TIMM Resnet50d model for the CPU
114+ ##### Export, quantize and validate TIMM Resnet50d model for the CPU
115115``` bash
116116python aot_optimize_and_infer.py --export --suite timm --model vgg16 --input_shape [1, 3, 224, 224] --device CPU --validate --dataset /path/to/dataset --quantize
117117```
118118
119- #### Execute Inference with Torchvision Inception V3 model for the CPU
119+ ##### Execute Inference with Torchvision Inception V3 model for the CPU
120120``` bash
121121python aot_optimize_and_infer.py --suite torchvision --model inception_v3 --infer --warmup_iter 10 --num_iter 100 --input_shape " (1, 3, 256, 256)" --device CPU
122122```
0 commit comments