c38b7d4377
* Fix links in readme * Fix links in readme * Update PPOCRv2/v3 examples * Update auto compression configs * Add neww quantization support for paddleclas model * Update quantized Yolov6s model download link * Improve PPOCR comments * Add English doc for quantization * Fix PPOCR rec model bug * Add new paddleseg quantization support * Add new paddleseg quantization support * Add new paddleseg quantization support * Add new paddleseg quantization support * Add Ascend model list * Add ascend model list * Add ascend model list * Add ascend model list * Add ascend model list * Add ascend model list * Add ascend model list * Support DirectML in onnxruntime * Support onnxruntime DirectML * Support onnxruntime DirectML * Support onnxruntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Support OnnxRuntime DirectML * Remove DirectML vision model example * Imporve OnnxRuntime DirectML * Imporve OnnxRuntime DirectML * fix opencv cmake in Windows * recheck codestyle
English | 简体中文
PaddleClas Model Deployment
Model Description
Now FastDeploy supports the deployment of the following models
- PP-LCNet Models
- PP-LCNetV2 Models
- EfficientNet Models
- GhostNet Models
- MobileNet Models(including v1,v2,v3)
- ShuffleNet Models
- SqueezeNet Models
- Inception Models
- PP-HGNet Models
- ResNet Models（including vd series）
Prepare PaddleClas Deployment Model
For PaddleClas model export, refer to Model Export.
Attention：The model exported by PaddleClas contains two files, including inference.pdmodel and inference.pdiparams. However, it is necessary to prepare the generic inference_cls.yaml file provided by PaddleClas to meet the requirements of deployment. FastDeploy will obtain from the yaml file the preprocessing information required during inference. FastDeploy will get the preprocessing information needed by the model from the yaml file. Developers can directly download this file. But they need to modify the configuration parameters in the yaml file based on personalized needs. Refer to the configuration information in the infer section of the PaddleClas model training config.
Download Pre-trained Model
For developers' testing, some models exported by PaddleClas (including the inference_cls.yaml file) are provided below. Developers can download them directly.
| Model | Parameter File Size | Input Shape | Top1 | Top5 |
|---|---|---|---|---|
| PPLCNet_x1_0 | 12MB | 224x224 | 71.32% | 90.03% |
| PPLCNetV2_base | 26MB | 224x224 | 77.04% | 93.27% |
| EfficientNetB7 | 255MB | 600x600 | 84.3% | 96.9% |
| EfficientNetB0_small | 18MB | 224x224 | 75.8% | 75.8% |
| GhostNet_x1_3_ssld | 29MB | 224x224 | 75.7% | 92.5% |
| GhostNet_x0_5 | 10MB | 224x224 | 66.8% | 86.9% |
| MobileNetV1_x0_25 | 1.9MB | 224x224 | 51.4% | 75.5% |
| MobileNetV1_ssld | 17MB | 224x224 | 77.9% | 93.9% |
| MobileNetV2_x0_25 | 5.9MB | 224x224 | 53.2% | 76.5% |
| MobileNetV2_ssld | 14MB | 224x224 | 76.74% | 93.39% |
| MobileNetV3_small_x0_35_ssld | 6.4MB | 224x224 | 55.55% | 77.71% |
| MobileNetV3_large_x1_0_ssld | 22MB | 224x224 | 78.96% | 94.48% |
| ShuffleNetV2_x0_25 | 2.4MB | 224x224 | 49.9% | 73.79% |
| ShuffleNetV2_x2_0 | 29MB | 224x224 | 73.15% | 91.2% |
| SqueezeNet1_1 | 4.8MB | 224x224 | 60.1% | 81.9% |
| InceptionV3 | 92MB | 299x299 | 79.14% | 94.59% |
| PPHGNet_tiny_ssld | 57MB | 224x224 | 81.95% | 96.12% |
| PPHGNet_base_ssld | 274MB | 224x224 | 85.0% | 97.35% |
| ResNet50_vd | 98MB | 224x224 | 79.12% | 94.44% |