Update app.py

app.py

@@ -1,194 +1,60 @@
 import gradio as gr
-import os
-
-import argparse
-import time
-from pathlib import Path
-
-import cv2
 import torch
-import torch.backends.cudnn as cudnn
-from numpy import random
-
-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
- 
-from huggingface_hub import hf_hub_download
-
-
-def load_model():
-    model_path = hf_hub_download(repo_id=f"StarAtNyte1/yolov7_custom", filename=f"best.pt")
-
-    return model_path
-
-
-
-
-models = {'best': load_model()}
-
-
-def detect(img,model):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', nargs='+', type=str, default=models[model], help='model.pt path(s)')
-    parser.add_argument('--source', type=str, default='Inference/', help='source')  # file/folder, 0 for webcam
-    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 --save-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: --class 0, or --class 0 2 3')
-    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('--update', action='store_true', help='update all models')
-    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
-    parser.add_argument('--name', default='exp', help='save results to project/name')
-    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
-    parser.add_argument('--trace', action='store_true', help='trace 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
-    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
-    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
-
-    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
-    vid_path, vid_writer = None, None
-    if webcam:
-        view_img = check_imshow()
-        cudnn.benchmark = True  # set True to speed up constant image size inference
-        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
-    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
-        if img.ndimension() == 3:
-            img = img.unsqueeze(0)
-
-        # Inference
-        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
-                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
-            s += '%gx%g ' % img.shape[2:]  # print string
-            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 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=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
-
-            # 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
-                        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 Image.fromarray(im0[:,:,::-1])
-
-   
-gr.Interface(detect,[gr.Image(type="pil"),gr.Dropdown(choices='yolov7')], gr.Image(type="pil"),title="Yolov7").launch()
-
+import yolov7
+
+
+
+def yolov7_inference(
+    image: gr.inputs.Image = None,
+    model_path: gr.inputs.Dropdown = None,
+    image_size: gr.inputs.Slider = 640,
+    conf_threshold: gr.inputs.Slider = 0.25,
+    iou_threshold: gr.inputs.Slider = 0.45,
+):
+    """
+    YOLOv7 inference function
+    Args:
+        image: Input image
+        model_path: Path to the model
+        image_size: Image size
+        conf_threshold: Confidence threshold
+        iou_threshold: IOU threshold
+    Returns:
+        Rendered image
+    """
+
+    model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
+    model.conf = conf_threshold
+    model.iou = iou_threshold
+    results = model([image], size=image_size)
+    return results.render()[0]
+        
+
+inputs = [
+    gr.inputs.Image(type="pil", label="Input Image"),
+    gr.inputs.Dropdown(
+        choices=[
+            "StarAtNyte1/yolov7_custom",
+        ],
+        default="StarAtNyte1/yolov7_custom",
+        label="Model",
+    ),
+    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
+    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
+    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"),
+]
+
+outputs = gr.outputs.Image(type="filepath", label="Output Image")
+#title = "Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"
+
+examples = [['small-vehicles1.jpeg', 'kadirnar/yolov7-tiny-v0.1', 640, 0.25, 0.45], ['zidane.jpg', 'kadirnar/yolov7-v0.1', 640, 0.25, 0.45]]
+demo_app = gr.Interface(
+    fn=yolov7_inference,
+    inputs=inputs,
+    outputs=outputs,
+    title=title,
+    examples=examples,
+    cache_examples=True,
+    theme='huggingface',
+)
+demo_app.launch(debug=True, enable_queue=True)