Add Examples to deploy quantized models (#342)

* Add PaddleOCR Support * Add PaddleOCR Support * Add PaddleOCRv3 Support * Add PaddleOCRv3 Support * Update README.md * Update README.md * Update README.md * Update README.md * Add PaddleOCRv3 Support * Add PaddleOCRv3 Supports * Add PaddleOCRv3 Suport * Fix Rec diff * Remove useless functions * Remove useless comments * Add PaddleOCRv2 Support * Add PaddleOCRv3 & PaddleOCRv2 Support * remove useless parameters * Add utils of sorting det boxes * Fix code naming convention * Fix code naming convention * Fix code naming convention * Fix bug in the Classify process * Imporve OCR Readme * Fix diff in Cls model * Update Model Download Link in Readme * Fix diff in PPOCRv2 * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Fix conflict * Add readme for OCRResult * Improve OCR readme * Add OCRResult readme * Improve OCR readme * Improve OCR readme * Add Model Quantization Demo * Fix Model Quantization Readme * Fix Model Quantization Readme * Add the function to do PTQ quantization * Improve quant tools readme * Improve quant tool readme * Improve quant tool readme * Add PaddleInference-GPU for OCR Rec model * Add QAT method to fastdeploy-quantization tool * Remove examples/slim for now * Move configs folder * Add Quantization Support for Classification Model * Imporve ways of importing preprocess * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Improve Quantization configs and readme * Add support for multi-inputs model * Add backends and params file for YOLOv7 * Add quantized model deployment support for YOLO series * Fix YOLOv5 quantize readme * Fix YOLO quantize readme * Fix YOLO quantize readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Fix bug, change Fronted to ModelFormat * Change Fronted to ModelFormat * Add examples to deploy quantized paddleclas models * Fix readme * Add quantize Readme * Add quantize Readme * Add quantize Readme * Modify readme of quantization tools * Modify readme of quantization tools * Improve quantization tools readme * Improve quantization readme * Improve PaddleClas quantized model deployment readme * Add PPYOLOE-l quantized deployment examples * Improve quantization tools readme
2025-10-05 16:48:03 +08:00 · 2022-10-14 13:35:45 +08:00
parent aac879bf2d
commit b0663209f6
36 changed files with 1465 additions and 87 deletions
--- a/examples/vision/detection/yolov5/quantize/python/infer.py
+++ b/examples/vision/detection/yolov5/quantize/python/infer.py
@@ -0,0 +1,81 @@
+import fastdeploy as fd
+import cv2
+import os
+from fastdeploy import ModelFormat
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model", required=True, help="Path of yolov5 onnx model.")
+    parser.add_argument(
+        "--image", required=True, help="Path of test image file.")
+    parser.add_argument(
+        "--device",
+        type=str,
+        default='cpu',
+        help="Type of inference device, support 'cpu' or 'gpu'.")
+    parser.add_argument(
+        "--backend",
+        type=str,
+        default="default",
+        help="Type of inference backend, support ort/trt/paddle/openvino, default 'openvino' for cpu, 'tensorrt' for gpu"
+    )
+    parser.add_argument(
+        "--device_id",
+        type=int,
+        default=0,
+        help="Define which GPU card used to run model.")
+    parser.add_argument(
+        "--cpu_thread_num",
+        type=int,
+        default=9,
+        help="Number of threads while inference on CPU.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+    if args.device.lower() == "gpu":
+        option.use_gpu(0)
+
+    option.set_cpu_thread_num(args.cpu_thread_num)
+
+    if args.backend.lower() == "trt":
+        assert args.device.lower(
+        ) == "gpu", "TensorRT backend require inference on device GPU."
+        option.use_trt_backend()
+    elif args.backend.lower() == "ort":
+        option.use_ort_backend()
+    elif args.backend.lower() == "paddle":
+        option.use_paddle_backend()
+    elif args.backend.lower() == "openvino":
+        assert args.device.lower(
+        ) == "cpu", "OpenVINO backend require inference on device CPU."
+        option.use_openvino_backend()
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model, "model.pdmodel")
+params_file = os.path.join(args.model, "model.pdiparams")
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.YOLOv5(
+    model_file,
+    params_file,
+    runtime_option=runtime_option,
+    model_format=ModelFormat.PADDLE)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im.copy())
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")