import gradio as gr import argparse import time from pathlib import Path 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, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, set_logging, increment_path, ) from utils.plots import plot_one_box from utils.torch_utils import ( select_device, load_classifier, TracedModel, ) from PIL import Image from huggingface_hub import hf_hub_download def load_model(model_name): model_path = hf_hub_download( repo_id=f"Yolov7/{model_name}", filename=f"{model_name}.pt" ) return model_path loaded_model = load_model("yolov7") def detect(img): parser = argparse.ArgumentParser() parser.add_argument( "--weights", nargs="+", type=str, default=loaded_model, help="model.pt path(s)" ) 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" ) 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 # 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 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 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, ) # Apply Classifier if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process detections for i, det in enumerate(pred): # detections per image p, s, im0, frame = path, "", im0s, getattr(dataset, "frame", 0) p = Path(p) # to Path 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 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(f"Done. ({time.time() - t0:.3f}s)") return [Image.fromarray(im0[:, :, ::-1]), s] css_code = ".border{border-width: 0;}.gr-button-primary{--tw-gradient-stops: rgb(11 143 235 / 70%), rgb(192 53 208 / 80%);color:black;border-color:black;}.gr-button-secondary{color:black;border-color:black;--tw-gradient-stops: white;}.gr-panel{background-color: white;}.gr-text-input{border-width: 0;padding: 0;text-align: center;margin-left: -8px;font-size: 28px;color: black;margin-top: -12px;}.font-semibold,.shadow-sm,.h-5,.text-xl{display:none;}.gr-box{box-shadow:none;border-radius:0;}.object-contain{background-color: white;}" gr.Interface( fn=detect, title="Anything Counter", inputs=gr.Image(type="pil"), outputs=[gr.Image(label="detection", type="pil"), gr.Textbox(label="")], css=css_code, ).launch(debug=True)