from __future__ import print_function import os import argparse import torch import torch.backends.cudnn as cudnn import numpy as np from data import cfg_mnet, cfg_re50 from layers.functions.prior_box import PriorBox from utils.nms.py_cpu_nms import py_cpu_nms import cv2 from utils.box_utils import decode, decode_landm import time import migraphx parser = argparse.ArgumentParser(description='Retinaface') parser.add_argument('-m', '--trained_model', default='./weights/mobilenet0.25_Final.pth', type=str, help='Trained state_dict file path to open') parser.add_argument('--network', default='mobile0.25', help='Backbone network mobile0.25 or resnet50') parser.add_argument('--cpu', action="store_true", default=False, help='Use cpu inference') parser.add_argument('--confidence_threshold', default=0.85, type=float, help='confidence_threshold') parser.add_argument('--top_k', default=5000, type=int, help='top_k') parser.add_argument('--nms_threshold', default=0.4, type=float, help='nms_threshold') parser.add_argument('--keep_top_k', default=750, type=int, help='keep_top_k') parser.add_argument('-s', '--save_image', action="store_true", default=True, help='show detection results') parser.add_argument('--vis_thres', default=0.6, type=float, help='visualization_threshold') args = parser.parse_args() def migraphx_run(model,cpu,data_tensor): # 将输入的tensor数据转换为numpy if cpu: data_numpy=data_tensor.cpu().numpy() device = torch.device("cpu") else: data_numpy=data_tensor.detach().cpu().numpy() device = torch.device("cuda") img_data = np.zeros(data_numpy.shape).astype("float32") for i in range(data_numpy.shape[0]): img_data[i, :, :, :] = data_numpy[i, :, :, :] # 执行推理 result = model.run({model.get_parameter_names()[0]: img_data}) # 将结果转换为tensor result0=torch.from_numpy(np.array(result[0], copy=False)).to(device) result1=torch.from_numpy(np.array(result[1], copy=False)).to(device) result2=torch.from_numpy(np.array(result[2], copy=False)).to(device) return (result0,result1,result2) if __name__ == '__main__': # 加载模型 cfg = None if args.network == "mobile0.25": cfg = cfg_mnet elif args.network == "resnet50": cfg = cfg_re50 device = torch.device("cpu" if args.cpu else "cuda") model = migraphx.parse_onnx("./FaceDetector.onnx") # 获取模型输入/输出节点信息 print("inputs:") inputs = model.get_inputs() for key,value in inputs.items(): print("{}:{}".format(key,value)) print("outputs:") outputs = model.get_outputs() for key,value in outputs.items(): print("{}:{}".format(key,value)) inputName=model.get_parameter_names()[0] inputShape=inputs[inputName].lens() print("inputName:{0} \ninputShape:{1}".format(inputName,inputShape)) # FP16 # migraphx.quantize_fp16(model) # 编译 model.compile(t=migraphx.get_target("gpu"),device_id=0) # device_id: 设置GPU设备，默认为0号设备 resize = 1 # testing begin for i in range(100): # resize到onnx模型输入大小 image_path = "./curve/test.jpg" img_raw = cv2.imread(image_path, cv2.IMREAD_COLOR) img_raw = cv2.resize(img_raw, (640,640)) img = np.float32(img_raw) im_height, im_width, _ = img.shape scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]]) img -= (104, 117, 123) img = img.transpose(2, 0, 1) img = torch.from_numpy(img).unsqueeze(0) img = img.to(device) scale = scale.to(device) tic = time.time() loc, conf, landms = migraphx_run(model,args.cpu,img) # forward pass print('net forward time: {:.4f}'.format(time.time() - tic)) priorbox = PriorBox(cfg, image_size=(im_height, im_width)) priors = priorbox.forward() priors = priors.to(device) prior_data = priors.data boxes = decode(loc.data.squeeze(0), prior_data, cfg['variance']) boxes = boxes * scale / resize boxes = boxes.cpu().numpy() scores = conf.squeeze(0).data.cpu().numpy()[:, 1] landms = decode_landm(landms.data.squeeze(0), prior_data, cfg['variance']) scale1 = torch.Tensor([img.shape[3], img.shape[2], img.shape[3], img.shape[2], img.shape[3], img.shape[2], img.shape[3], img.shape[2], img.shape[3], img.shape[2]]) scale1 = scale1.to(device) landms = landms * scale1 / resize landms = landms.cpu().numpy() # ignore low scores inds = np.where(scores > args.confidence_threshold)[0] boxes = boxes[inds] landms = landms[inds] scores = scores[inds] # keep top-K before NMS order = scores.argsort()[::-1][:args.top_k] boxes = boxes[order] landms = landms[order] scores = scores[order] # do NMS dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False) keep = py_cpu_nms(dets, args.nms_threshold) # keep = nms(dets, args.nms_threshold,force_cpu=args.cpu) dets = dets[keep, :] landms = landms[keep] # keep top-K faster NMS dets = dets[:args.keep_top_k, :] landms = landms[:args.keep_top_k, :] dets = np.concatenate((dets, landms), axis=1) # show image if args.save_image: for b in dets: if b[4] < args.vis_thres: continue text = "{:.4f}".format(b[4]) b = list(map(int, b)) cv2.rectangle(img_raw, (b[0], b[1]), (b[2], b[3]), (0, 0, 255), 2) cx = b[0] cy = b[1] + 12 cv2.putText(img_raw, text, (cx, cy), cv2.FONT_HERSHEY_DUPLEX, 0.5, (255, 255, 255)) # landms cv2.circle(img_raw, (b[5], b[6]), 1, (0, 0, 255), 4) cv2.circle(img_raw, (b[7], b[8]), 1, (0, 255, 255), 4) cv2.circle(img_raw, (b[9], b[10]), 1, (255, 0, 255), 4) cv2.circle(img_raw, (b[11], b[12]), 1, (0, 255, 0), 4) cv2.circle(img_raw, (b[13], b[14]), 1, (255, 0, 0), 4) # save image name = "test.jpg" cv2.imwrite(name, img_raw)