123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124 |
- #!/usr/bin/env python
- from importlib import import_module
- import os
- from flask import Flask, render_template, Response
- import cv2
- import torch
- from utils.torch_utils import *
- from utils.general import check_img_size, non_max_suppression, scale_coords
- from models.experimental import attempt_load
- from models.yolo import Model
- from utils.datasets import LoadStreams, LoadImages
- import random
- from utils.plots import plot_one_box
- app = Flask(__name__)
- @app.route('/')
- def index():
- """Video streaming home page."""
- return render_template('index.html')
- def stream():
- # WEIGHT = 'runs/train/yolov7-bsw2/weights/best.pt'
- WEIGHT = '/root/Public/model_ssai_fine_20221209/ipark_1208_1305.pt'
- # model = torch.load_state_dict(WEIGHT, map_location=select_device('0'))
- model = attempt_load(WEIGHT, map_location='cuda:0').half()
- # model = TracedModel(model, select_device('0'), img_size=640).half()
- imgsz = 640
- stride = int(model.stride.max()) # model stride
- imgsz = check_img_size(imgsz, s=stride) # check img_size
- device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
- # Run inference
- model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
- # Get names and colors
- names = model.module.names if hasattr(model, 'module') else model.names
- colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
- old_img_w = old_img_h = imgsz
- old_img_b = 1
- """Video streaming generator function."""
- # cap = cv2.VideoCapture('rtsp://astrodom:hdci12@192.168.170.73:554/stream1')
- dataset = LoadStreams('rtsp://astrodom:hdci12@192.168.170.73:554/stream1', img_size=imgsz, stride=stride)
- while True:
- # ret, frame = cap.read()
- # if not ret:
- # print('error')
- # break
- for path, img, im0s, vid_cap in dataset:
- img = torch.from_numpy(img).to(device)
- img = img.half() if True else img.float() # uint8 to fp16/32
- img /= 255.0 # 0 - 255 to 0.0 - 1.0
- if img.ndimension() == 3:
- img = img.unsqueeze(0)
- # Warmup
- if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]):
- old_img_b = img.shape[0]
- old_img_h = img.shape[2]
- old_img_w = img.shape[3]
- for i in range(3):
- model(img, augment=True)[0]
- with torch.no_grad(): # Calculating gradients would cause a GPU memory leak
- pred = model(img, augment=True)[0]
- # print(pred)
- # print('*' * 30)
- # Apply NMS
- pred = non_max_suppression(pred, 0.40, 0.45)
- # Process detections
- for i, det in enumerate(pred): # detections per image
- if True: # batch_size >= 1
- p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
- # else:
- # p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
- p = Path(p) # to Path
- # save_path = str(save_dir / p.name) # img.jpg
- # txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
- # gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
- if len(det):
- # Rescale boxes from img_size to im0 size
- det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
- # Print results
- for c in det[:, -1].unique():
- n = (det[:, -1] == c).sum() # detections per class
- s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
- # Write results
- for *xyxy, conf, cls in reversed(det):
- # if save_txt: # Write to file
- # xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
- # line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format
- # with open(txt_path + '.txt', 'a') as f:
- # f.write(('%g ' * len(line)).rstrip() % line + '\n')
- if True: # Add bbox to image
- label = f'{names[int(cls)]} {conf:.2f}'
- plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1)
- # x = img.permute(0,3,1,2) # (B, W, H, C) --> (B, C, W, H)
- image_bytes = cv2.imencode('.jpg', im0)[1].tobytes()
- yield (b'--frame\r\n'
- b'Content-Type: image/jpeg\r\n\r\n' + image_bytes + b'\r\n')
- @app.route('/video')
- def video():
- """Video streaming route. Put this in the src attribute of an img tag."""
- return Response(stream(), content_type='multipart/x-mixed-replace; boundary=frame')
- if __name__ == '__main__' :
- app.run(host='0.0.0.0', threaded=True, debug=True)
|