Validate all backends for detection models and add demo code & docs (#94)

* Validate all backends for detection models and add demo code and doc

* Delete .README.md.swp

examples/vision/detection/paddledetection/python/README.md

@@ -0,0 +1,72 @@
+# PaddleDetection Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/quick_start/requirements.md)  
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/quick_start/install.md)
+
+本目录下提供`infer_xxx.py`快速完成PPYOLOE/PicoDet等模型在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```
+#下载PPYOLOE模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+tar xvf ppyoloe_crn_l_300e_coco.tgz
+
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vison/detection/paddledetection/python/
+
+# CPU推理
+python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device cpu
+# GPU推理
+python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device gpu
+# GPU上使用TensorRT推理 （注意：TensorRT推理第一次运行，有序列化模型的操作，有一定耗时，需要耐心等待）
+python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+## PaddleDetection Python接口
+
+```
+fastdeploy.vision.detection.PPYOLOE(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+fastdeploy.vision.detection.PicoDet(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+fastdeploy.vision.detection.PaddleYOLOX(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+fastdeploy.vision.detection.YOLOv3(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+fastdeploy.vision.detection.PPYOLO(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+fastdeploy.vision.detection.FasterRCNN(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
+```
+
+PaddleDetection模型加载和初始化，其中model_file， params_file为导出的Paddle部署模型格式, config_file为PaddleDetection同时导出的部署配置yaml文件
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径
+> * **config_file**(str): 推理配置yaml文件路径
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(Frontend): 模型格式，默认为Paddle
+
+### predict函数
+
+PaddleDetection中各个模型，包括PPYOLOE/PicoDet/PaddleYOLOX/YOLOv3/PPYOLO/FasterRCNN，均提供如下同样的成员函数用于进去图像的检测
+> ```
+> PPYOLOE.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+## 其它文档
+
+- [PaddleDetection 模型介绍](..)
+- [PaddleDetection C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)

examples/vision/detection/paddledetection/python/infer_faster_rcnn.py

@@ -0,0 +1,61 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 640, 640])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.FasterRCNN(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")

examples/vision/detection/paddledetection/python/infer_picodet.py

@@ -0,0 +1,61 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 320, 320])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.PicoDet(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")

examples/vision/detection/paddledetection/python/infer_ppyolo.py

@@ -0,0 +1,62 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 640, 640])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.PPYOLO(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(
+    im, result, score_threshold=0.5, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")

examples/vision/detection/paddledetection/python/infer_ppyoloe.py

@@ -0,0 +1,61 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 640, 640])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.PPYOLOE(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")

examples/vision/detection/paddledetection/python/infer_yolov3.py

@@ -0,0 +1,62 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 608, 608])
+        option.set_trt_input_shape("im_shape", [1, 2])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.YOLOv3(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")

examples/vision/detection/paddledetection/python/infer_yolox.py

@@ -0,0 +1,61 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_dir",
+        required=True,
+        help="Path of PaddleDetection model directory")
+    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(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("image", [1, 3, 640, 640])
+        option.set_trt_input_shape("scale_factor", [1, 2])
+    return option
+
+
+args = parse_arguments()
+
+model_file = os.path.join(args.model_dir, "model.pdmodel")
+params_file = os.path.join(args.model_dir, "model.pdiparams")
+config_file = os.path.join(args.model_dir, "infer_cfg.yml")
+
+# 配置runtime，加载模型
+runtime_option = build_option(args)
+model = fd.vision.detection.PaddleYOLOX(
+    model_file, params_file, config_file, runtime_option=runtime_option)
+
+# 预测图片检测结果
+im = cv2.imread(args.image)
+result = model.predict(im)
+print(result)
+
+# 预测结果可视化
+vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")