Update app.py

app.py

@@ -1,34 +1,27 @@
-import gradio as gr
 import os
-
-os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt")
-os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt")
-os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt")
-
-import argparse
-import time
-from pathlib import Path
-
 import cv2
+import time
 import torch
-import torch.backends.cudnn as cudnn
+import argparse
+import gradio as gr
+from PIL import Image
 from numpy import random
-
+from pathlib import Path
+import torch.backends.cudnn as cudnn
 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 PIL import Image
+os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt")
+os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt")
  
-
-
-
 def detect_Custom(img,model):
     parser = argparse.ArgumentParser()
     parser.add_argument('--weights', nargs='+', type=str, default=model+".pt", help='model.pt path(s)')
-    parser.add_argument('--source', type=str, default='Inference/', help='source')  # file/folder, 0 for webcam
+    parser.add_argument('--source', type=str, default='Inference/', 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')
@@ -48,57 +41,37 @@ def detect_Custom(img,model):
     opt = parser.parse_args()
     img.save("Inference/test.jpg")
     source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, opt.trace
-    save_img = True  # save inference images
+    save_img = True 
     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))  # increment run
-    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
-
-    # Initialize
+    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) 
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  
     set_logging()
     device = select_device(opt.device)
-    half = device.type != 'cpu'  # half precision only supported on CUDA
-
-    # Load model
-    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
-
+    half = device.type != 'cpu' 
+    model = attempt_load(weights, map_location=device) 
+    stride = int(model.stride.max())  
+    imgsz = check_img_size(imgsz, s=stride)
     if trace:
         model = TracedModel(model, device, opt.img_size)
-
     if 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()
-
-    # Set Dataloader
+        model.half() 
     vid_path, vid_writer = None, None
     if webcam:
         view_img = check_imshow()
-        cudnn.benchmark = True  # set True to speed up constant image size inference
+        cudnn.benchmark = True 
         dataset = LoadStreams(source, img_size=imgsz, stride=stride)
     else:
         dataset = LoadImages(source, img_size=imgsz, stride=stride)
-
-    # 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]
-
-    # Run inference
     if device.type != 'cpu':
-        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) 
     t0 = time.time()
     for path, img, im0s, vid_cap in dataset:
         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
+        img = img.half() if half else img.float() 
+        img /= 255.0  
         if img.ndimension() == 3:
             img = img.unsqueeze(0)
 
@@ -106,69 +79,60 @@ def detect_Custom(img,model):
         t1 = time_synchronized()
         pred = model(img, augment=opt.augment)[0]
 
-        # Apply NMS
+
         pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
         t2 = time_synchronized()
 
-        # 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
+        for i, det in enumerate(pred): 
+            if webcam: 
                 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
+            p = Path(p)  
+            save_path = str(save_dir / p.name)
             txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
-            s += '%gx%g ' % img.shape[2:]  # print string
-            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            s += '%gx%g ' % img.shape[2:]  
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  
             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
+                    n = (det[:, -1] == c).sum()  
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  
 
-                # 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
+                    if save_txt:  
+                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() 
+                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) 
                         with open(txt_path + '.txt', 'a') as f:
                             f.write(('%g ' * len(line)).rstrip() % line + '\n')
 
-                    if save_img or view_img:  # Add bbox to image
+                    if save_img or view_img:
                         label = f'{names[int(cls)]} {conf:.2f}'
                         plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
-
-            # Print time (inference + NMS)
-            #print(f'{s}Done. ({t2 - t1:.3f}s)')
-
-            # Stream results
             if view_img:
                 cv2.imshow(str(p), im0)
-                cv2.waitKey(1)  # 1 millisecond
+                cv2.waitKey(1)  
 
-            # Save results (image with detections)
             if save_img:
                 if dataset.mode == 'image':
                     cv2.imwrite(save_path, im0)
-                else:  # 'video' or 'stream'
-                    if vid_path != save_path:  # new video
+                else: 
+                    if vid_path != save_path: 
                         vid_path = save_path
                         if isinstance(vid_writer, cv2.VideoWriter):
-                            vid_writer.release()  # release previous video writer
-                        if vid_cap:  # video
+                            vid_writer.release()
+                        if vid_cap: 
                             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
+                        else: 
                             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))
@@ -176,7 +140,6 @@ def detect_Custom(img,model):
 
     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)')
 
@@ -184,10 +147,10 @@ def detect_Custom(img,model):
 
    
 
-description="Custom Training Performed on Kaggle <a href='https://www.kaggle.com/code/owaiskhan9654/training-yolov7-on-kaggle-on-custom-dataset/notebook' style='text-decoration: underline' target='_blank'>Link</a> <br> Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors  <br> Also Please use <b>Images with .jpeg</b> because Yolo V7 Model is trained on GPU and while inferencing default CPU has been implemented"
+description="<center>Custom Training Performed on Kaggle <a href='https://www.kaggle.com/code/owaiskhan9654/training-yolov7-on-kaggle-on-custom-dataset/notebook' style='text-decoration: underline' target='_blank'>Link</a> </center><br> <center>Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors </center> <br> <center>Also Please use <b>Images with .jpeg</b> because Yolo V7 Model is trained on GPU and while inferencing default CPU has been implemented</center>"
 
 text1 = (
-    "<center> Custom Model Trained by: Owais Ahmad Data Scientist at <b> Thoucentric </b> <a href=\"https://www.linkedin.com/in/owaiskhan9654/\">Visit Profile</a> <br></center>"
+    "<center>Model Trained by: Owais Ahmad Data Scientist at <b> Thoucentric </b> <a href=\"https://www.linkedin.com/in/owaiskhan9654/\">Visit Profile</a> <br></center>"
     
     "<center> Model Trained Kaggle Kernel <a href=\"https://www.kaggle.com/code/owaiskhan9654/training-yolov7-on-kaggle-on-custom-dataset/notebook\">Link</a> <br></center>"
         
@@ -198,4 +161,6 @@ text1 = (
 
 examples1=[["Image1.jpeg", "Yolo_v7_Custom_trained_By_Owais"],["Image2.jpeg", "Yolo_v7_Custom_trained_By_Owais"],["Image3.jpeg", "Yolo_v7_Custom_trained_By_Owais",],["Image4.jpeg", "Yolo_v7_Custom_trained_By_Owais"],["Image5.jpeg", "Yolo_v7_Custom_trained_By_Owais"],["Image6.jpeg", "Yolo_v7_Custom_trained_By_Owais"],["horses.jpeg", "yolov7"],["horses.jpeg", "yolov7-e6"]]
 
-gr.Interface(detect_Custom,[gr.Image(type="pil"),gr.Dropdown(default="Yolo_v7_Custom_trained_By_Owais",choices=["best","yolov7","yolov7-e6"])],gr.Image(type="pil"),title="Yolov7 Custom Trained by <a href='https://www.linkedin.com/in/owaiskhan9654/' style='text-decoration: underline' target='_blank'>Owais Ahmad</a> ",examples=examples1,description=description,article=text1,cache_examples=False).launch()
+Title="<center>Yolov7 Custom Trained by <a href='https://www.linkedin.com/in/owaiskhan9654/' style='text-decoration: underline' target='_blank'>Owais Ahmad</center></a>"
+
+gr.Interface(detect_Custom,[gr.Image(type="pil"),gr.Dropdown(default="Yolo_v7_Custom_trained_By_Owais",choices=["Yolo_v7_Custom_trained_By_Owais","yolov7","yolov7-e6"])],gr.Image(type="pil"),title=,examples=examples1,description=description,article=text1,cache_examples=False).launch()