Update app.py

app.py

@@ -1,156 +1,244 @@
 import os
 import sys
-import time
 import argparse
+import time
 from pathlib import Path
-import random
+import pandas as pd
 
+import gradio as gr
 import cv2
-import torch
-import numpy as np
-import pandas as pd
 from PIL import Image
-import gradio as gr
+import torch
 import torch.backends.cudnn as cudnn
+from numpy import random
+import numpy as np
 
-# ==== CONSTANTS ====
 BASE_DIR = "/home/user/app"
-INPUT_DIR = f"{BASE_DIR}/input"
-YOLOV7_PATH = f"{BASE_DIR}/yolov7"
-
-# ==== SETUP ====
-os.makedirs(INPUT_DIR, exist_ok=True)
 os.chdir(BASE_DIR)
-sys.path.append(YOLOV7_PATH)
+os.makedirs(f"{BASE_DIR}/input",exist_ok=True)
+# os.system(f"git clone https://github.com/WongKinYiu/yolov7.git {BASE_DIR}/yolov7")
+sys.path.append(f'{BASE_DIR}/yolov7')
 os.system("pip install yolov7-package==0.0.12")
 
-# ==== UTILS ====
 def plot_one_box(x, img, color=None, label=None, line_thickness=3):
-    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1
+    # Plots one bounding box on image img
+    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
     color = color or [random.randint(0, 255) for _ in range(3)]
     c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
     cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
-
     if label:
-        tf = max(tl - 1, 1)
+        tf = max(tl - 1, 1)  # font thickness
         t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
-        label_bg = c1[0] + t_size[0], c1[1] - t_size[1] - 3
-        cv2.rectangle(img, c1, label_bg, color, -1, cv2.LINE_AA)
+        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
+        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
         cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
 
-# ==== MAIN DETECTION FUNCTION ====
-def detect(opt):
+
+def detect(opt, save_img=False):    
+#     from models.experimental import attempt_load
+#     from utils.datasets import LoadStreams, LoadImages
+#     from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+#         scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+#     from utils.plots import plot_one_box
+#     from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
+
     from yolov7_package import Yolov7Detector
     from yolov7_package.models.experimental import attempt_load
-    from yolov7_package.utils.general import (
-        check_img_size, non_max_suppression, apply_classifier,
-        scale_coords, xyxy2xywh, set_logging, increment_path, check_imshow
-    )
-    from yolov7_package.utils.torch_utils import (
-        select_device, load_classifier, time_synchronized, TracedModel
-    )
+    from yolov7_package.utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+        scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+    from yolov7_package.utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
     from yolov7_package.utils.datasets import LoadStreams, LoadImages
-
+    
     bbox = {}
-    save_img = not opt.nosave and not opt.source.endswith('.txt')
-    webcam = opt.source.isnumeric() or opt.source.endswith('.txt') or opt.source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
+    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
+    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
+        ('rtsp://', 'rtmp://', 'http://', 'https://'))
 
     # Directories
-    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
-    (save_dir / 'labels' if opt.save_txt else save_dir).mkdir(parents=True, exist_ok=True)
+    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
 
     # Initialize
     set_logging()
     device = select_device(opt.device)
-    half = device.type != 'cpu'
+    half = device.type != 'cpu'  # half precision only supported on CUDA
 
     # Load model
-    model = attempt_load(opt.weights, map_location=device)
-    stride = int(model.stride.max())
-    imgsz = check_img_size(opt.img_size, s=stride)
+    det = Yolov7Detector(weights=weights, traced=False)
+    model = attempt_load(weights, map_location=device)  # load FP32 model
+    stride = int(model.stride.max())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check img_size
 
-    if opt.no_trace is False:
-        model = TracedModel(model, device, imgsz)
+    if trace:
+        model = TracedModel(model, device, opt.img_size)
 
     if half:
-        model.half()
+        model.half()  # to FP16
+
+    # Second-stage classifier
+    classify = False
+    if classify:
+        modelc = load_classifier(name='resnet101', n=2)  # initialize
+        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
 
-    # Dataloader
+    # Set Dataloader
+    vid_path, vid_writer = None, None
     if webcam:
-        cudnn.benchmark = True
         view_img = check_imshow()
-        dataset = LoadStreams(opt.source, img_size=imgsz, stride=stride)
+        cudnn.benchmark = True  # set True to speed up constant image size inference
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
     else:
-        dataset = LoadImages(opt.source, img_size=imgsz, stride=stride)
+        dataset = LoadImages(source, img_size=imgsz, stride=stride)
 
-    # Labels/colors
+    # 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]
 
-    # Warmup
+    # Run inference
     if device.type != 'cpu':
-        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))
+        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+    old_img_w = old_img_h = imgsz
+    old_img_b = 1
 
+    t0 = time.time()
     for path, img, im0s, vid_cap in dataset:
-        img = torch.from_numpy(img).to(device).half() if half else torch.from_numpy(img).float().to(device)
-        img /= 255.0
-        img = img.unsqueeze(0) if img.ndimension() == 3 else img
+        img = torch.from_numpy(img).to(device)
+        img = img.half() if half 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=opt.augment)[0]
 
         # Inference
         t1 = time_synchronized()
-        with torch.no_grad():
+        with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
             pred = model(img, augment=opt.augment)[0]
         t2 = time_synchronized()
 
-        # NMS
-        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms)
+        # Apply NMS
+        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
         t3 = time_synchronized()
 
-        # Process detections
-        for i, det in enumerate(pred):
-            im0 = im0s[i] if webcam else im0s
-            p = Path(path)
-            txt_path = str(save_dir / 'labels' / p.stem) + (f'_{dataset.frame}' if hasattr(dataset, 'frame') else '')
-            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]
+        # Apply Classifier
+        if classify:
+            pred = apply_classifier(pred, modelc, img, im0s)
 
+        # Process detections
+        for i, det in enumerate(pred):  # detections per image
+            if webcam:  # 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()
-                bbox[p.name] = det[:, :4].cpu().numpy()
+#                 print(f"BOXES ---->>>> {det[:, :4]}")
+                bbox[f"{txt_path.split('/')[4]}"]=(det[:, :4]).numpy()
+
+               # 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 opt.save_txt:
-                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
-                        label_line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)
+                    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(('%.6f ' * len(label_line)).strip() % label_line + '\n')
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
 
-                    if save_img or opt.view_img:
+                    if save_img or view_img:  # 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)
 
-            print(f'Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')
-
-    return bbox
-
-# ==== Example usage (can be wired into a Gradio UI or CLI entry point) ====
-# if __name__ == '__main__':
-#     parser = argparse.ArgumentParser()
-#     parser.add_argument('--weights', type=str, default='yolov7.pt', help='model.pt path')
-#     parser.add_argument('--source', type=str, default='data/images', help='source')
-#     parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
-#     parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
-#     parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
-#     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-#     parser.add_argument('--view-img', action='store_true', help='display results')
-#     parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
-#     parser.add_argument('--save-conf', action='store_true', help='save confidences in txt labels')
-#     parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
-#     parser.add_argument('--classes', nargs='+', type=int, help='filter by class')
-#     parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
-#     parser.add_argument('--augment', action='store_true', help='augmented inference')
-#     parser.add_argument('--no-trace', action='store_true', help='don’t trace model')
-#     parser.add_argument('--project', default='runs/detect', help='save to project/name')
-#     parser.add_argument('--name', default='exp', help='save to project/name')
-#     parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
-#     opt = parser.parse_args()
-#     detect(opt)
+            # Print time (inference + NMS)
+            print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')
+
+            # Stream results
+            # if view_img:
+            #     cv2.imshow(str(p), im0)
+            #     cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    # Image.fromarray(im0).show()
+                    cv2.imwrite(save_path, im0) 
+                    print(f" The image with the result is saved in: {save_path}")
+                # else:  # 'video' or 'stream'
+                #     if vid_path != save_path:  # new video
+                #         vid_path = save_path
+                #         if isinstance(vid_writer, cv2.VideoWriter):
+                #             vid_writer.release()  # release previous video writer
+                #         if vid_cap:  # video
+                #             fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                #             w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                #             h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                #         else:  # stream
+                #             fps, w, h = 30, im0.shape[1], im0.shape[0]
+                #             save_path += '.mp4'
+                #         vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                #     vid_writer.write(im0)
+
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        #print(f"Results saved to {save_dir}{s}")
+
+    print(f'Done. ({time.time() - t0:.3f}s)')
+    return bbox,save_path
+
+class options:
+    def __init__(self, weights, source, img_size=640, conf_thres=0.1, iou_thres=0.45, device='', 
+                 view_img=False, save_txt=False, save_conf=False, nosave=False, classes=None, 
+                 agnostic_nms=False, augment=False, update=False, project='runs/detect', name='exp', 
+                 exist_ok=False, no_trace=False):
+        self.weights=weights
+        self.source=source
+        self.img_size=img_size
+        self.conf_thres=conf_thres
+        self.iou_thres=iou_thres
+        self.device=device
+        self.view_img=view_img
+        self.save_txt=save_txt
+        self.save_conf=save_conf
+        self.nosave=nosave
+        self.classes=classes
+        self.agnostic_nms=agnostic_nms
+        self.augment=augment
+        self.update=update
+        self.project=project
+        self.name=name
+        self.exist_ok=exist_ok
+        self.no_trace=no_trace
+
+def get_output(input_image):
+    ### Numpy -> PIL
+    input_image = Image.fromarray(input_image).convert('RGB')
+    input_image.save(f"{BASE_DIR}/input/image.jpg")
+    source = f"{BASE_DIR}/input"
+    opt = options(weights='logo_detection.pt',source=source)
+    bbox = None
+    with torch.no_grad():
+        bbox,output_path = detect(opt)
+    if os.path.exists(output_path):
+        return Image.open(output_path)
+    else:
+        return input_image
+
+
+demo = gr.Interface(fn=get_output, inputs="image", outputs="image")
+demo.launch(debug=True)