import argparse import os import platform import sys import streamlit as st import torch import torch.backends.cudnn as cudnn import numpy as np from pathlib import Path from PIL import Image from torchvision import transforms, models FILE = Path(__file__).resolve() ROOT = FILE.parents[0] # YOLOv5 root directory if str(ROOT) not in sys.path: sys.path.append(str(ROOT)) # add ROOT to PATH ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import select_device, time_sync weights="appledd-yolov5s-800.pb" device = torch.device("cuda" if torch.cuda.is_available() else "cpu") #### Class for classification model import torch.nn as nn import torch.nn.functional as F class NaturalSceneClassification(nn.Module): def __init__(self): super().__init__() self.network = torch.hub.load('pytorch/vision:v0.10.0', 'mobilenet_v2', pretrained=True) self.network.fc = nn.Sequential(nn.Linear(2048, 512), nn.ReLU(), nn.Dropout(0.2), nn.Linear(512, 10), nn.Softmax(dim=1)) def forward(self, xb): return self.network(xb) def training_step(self, batch): images, labels = batch images, labels = images.to(device), labels.to(device) out = self(images) # Generate predictions loss = F.cross_entropy(out, labels) # Calculate loss return loss def validation_step(self, batch): images, labels = batch images, labels = images.to(device), labels.to(device) out = self(images) # Generate predictions loss = F.cross_entropy(out, labels) # Calculate loss acc = accuracy(out, labels) # Calculate accuracy return {'val_loss': loss.detach(), 'val_acc': acc} def validation_epoch_end(self, outputs): batch_losses = [x['val_loss'] for x in outputs] epoch_loss = torch.stack(batch_losses).mean() # Combine losses batch_accs = [x['val_acc'] for x in outputs] epoch_acc = torch.stack(batch_accs).mean() # Combine accuracies return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()} def epoch_end(self, epoch, result): print("Epoch [{}], train_loss: {:.4f}, val_loss: {:.4f}, val_acc: {:.4f}".format( epoch, result['train_loss'], result['val_loss'], result['val_acc'])) def increase_contrast(image): if isinstance(image, Image.Image): # Convert the PIL image to a numpy array image = np.array(image) if not isinstance(image, np.ndarray): raise ValueError("Input must be a valid numpy array") # Convert the image to grayscale if it's in color if len(image.shape) == 3: image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # Calculate min and max values min_val = image.min() max_val = image.max() if min_val == max_val: return image # Avoid division by zero # Apply contrast stretching contrast_stretched = cv2.convertScaleAbs(image, alpha=255.0 / (max_val - min_val), beta=-min_val) return contrast_stretched def reduce_noise(image, kernel_size=(3, 3)): # Apply Gaussian blur to reduce noise blurred = cv2.GaussianBlur(image, kernel_size, 0) return blurred @torch.no_grad() def run( weights=ROOT / 'yolov5s.pt', # model.pt path(s) source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam data=ROOT / 'data.yaml', # dataset.yaml path imgsz=(640, 640), # inference size (height, width) conf_thres=0.25, # confidence threshold iou_thres=0.45, # NMS IOU threshold max_det=1000, # maximum detections per image device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu view_img=False, # show results save_txt=False, # save results to *.txt save_conf=False, # save confidences in --save-txt labels save_crop=False, # save cropped prediction boxes nosave=False, # do not save images/videos classes=None, # filter by class: --class 0, or --class 0 2 3 agnostic_nms=False, # class-agnostic NMS augment=False, # augmented inference visualize=False, # visualize features update=False, # update all models project=ROOT / 'runs/detect', # save results to project/name name='exp', # save results to project/name exist_ok=True, # existing project/name ok, do not increment line_thickness=2, # bounding box thickness (pixels) hide_labels=False, # hide labels hide_conf=False, # hide confidences half=False, # use FP16 half-precision inference dnn=False, # use OpenCV DNN for ONNX inference upl_image: np.ndarray=None, #return_type: list=["Image", "Labels"] ): source = str(source) save_img = not nosave and not source.endswith('.txt') # save inference images is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file) if is_url and is_file: source = check_file(source) # download # Directories save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir # Load model device = select_device(device) model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half) stride, names, pt = model.stride, model.names, model.pt imgsz = check_img_size(imgsz, s=stride) # check image size # Dataloader 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, auto=pt) bs = len(dataset) # batch_size else: dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt) bs = 1 # batch_size vid_path, vid_writer = [None] * bs, [None] * bs # Run inference model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup seen, windows, dt = 0, [], [0.0, 0.0, 0.0] for path, im, im0s, vid_cap, s in dataset: t1 = time_sync() #im=upl_image im = torch.from_numpy(im).to(device) im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 if len(im.shape) == 3: im = im[None] # expand for batch dim t2 = time_sync() dt[0] += t2 - t1 # Contrast enhancement # im = increase_contrast(im) # # Noise reduction # im = reduce_noise(im) # Inference visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred = model(im, augment=augment, visualize=visualize) t3 = time_sync() dt[1] += t3 - t2 # NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) dt[2] += time_sync() - t3 # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Process predictions for i, det in enumerate(pred): # per image seen += 1 if webcam: # batch_size >= 1 p, im0, frame = path[i], im0s[i].copy(), dataset.count s += f'{i}: ' else: p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) p = Path(p) # to Path save_path = str(save_dir / p.name) # im.jpg txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt s += '%gx%g ' % im.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, example=str(names)) if len(det): # Rescale boxes from img_size to im0 size det[:, :4] = scale_coords(im.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 save_conf else (cls, *xywh) # label format with open(f'{txt_path}.txt', 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') if save_img or save_crop or view_img: # Add bbox to image c = int(cls) # integer class label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}') annotator.box_label(xyxy, label, color=colors(c, True)) if save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) # Stream results im0 = annotator.result() if view_img: if platform.system() == 'Linux' and p not in windows: windows.append(p) cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0]) 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) print("Save") else: # 'video' or 'stream' if vid_path[i] != save_path: # new video vid_path[i] = save_path if isinstance(vid_writer[i], cv2.VideoWriter): vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) # Print time (inference-only) LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)') # Print results t = tuple(x / seen * 1E3 for x in dt) # speeds per image LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) 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 '' LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning) im0 = cv2.cvtColor(im0, cv2.COLOR_BGR2RGB) return im0 def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)') parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam') parser.add_argument('--data', type=str, default=ROOT / 'data.yaml', help='(optional) dataset.yaml path') parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[800], help='inference size h,w') parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold') parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold') parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image') 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='show 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('--save-crop', action='store_true', help='save cropped prediction boxes') parser.add_argument('--nosave', action='store_true', help='do not save images/videos') parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features') parser.add_argument('--update', action='store_true', help='update all models') parser.add_argument('--project', default=ROOT / '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('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)') parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels') parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences') parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference') parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference') opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(vars(opt)) return opt def classify(model,img): img = img.to(device) prediction = model(img) sc, preds = torch.max(prediction, dim = 1) return sc[0].item(),preds[0].item() def main(opt,model,labels): #check_requirements(exclude=('tensorboard', 'thop')) #run(**vars(opt)) st.image("logo.jpg", caption="") st.title("#Welcome to Deep Diagnosis") # st.write("By: Dr. Asif Iqbal Khan") st.markdown( """ This app allows you to detect different apple diseases from leaf images. 1) Scab 2) Alternaria 3) MLB 4) Mossaic 5) Powdery Mildew 6) Necrosis """ ) url="https://www.sciencedirect.com/science/article/abs/pii/S0168169922004100" st.write("Link to the research paper: [link] (%s)" %url) st.write("This app allows you to provide an image, and one of the most advanced Object Detection algorithms available will try to classify it for you. Upload your data to get started!") with st.sidebar: # st.image("logo.jpg", caption="") uploaded_file = st.file_uploader("Choose an Image", type=["png","jpg","jpeg"]) return_types = st.multiselect("Select Return Type", ["Image", "Labels"], ["Image", "Labels"]) if not uploaded_file: file_name = "sample.jpg" st.write("Upload apple leaf image to detect diseases") st.image("sample.jpg", caption='Sample Image',width=400) else: file_name = uploaded_file.name #image = np.array(Image.open(image_file_buffer)) #Saving upload file_details = {"filename":uploaded_file.name, "filetype":uploaded_file.type,"filesize":uploaded_file.size} #st.write(file_details) with open(file_name,"wb") as f: f.write((uploaded_file).getbuffer()) img = Image.open(uploaded_file) if img.format.lower() != "jpeg" or img.format.lower() !="jpg" : # Convert the image to RGB format (JPEG-compatible) and save as a temporary JPEG file img = img.convert("RGB") temp_jpeg_file = "temp_image.jpg" img.save(temp_jpeg_file, "JPEG") img.close() # Load the temporary JPEG file for processing img = Image.open(temp_jpeg_file) img = transforms.Resize((360,360))(img) img = transforms.ToTensor()(img) img = img.unsqueeze(0).to(device) res=classify(model,img) lb=labels[res[1]] sc=res[0] st.write(lb+" "+str(sc)) if(lb=="noleaf"): st.write("Invalid image! Try Some other image") elif(lb=="healthy"): st.write("Looks healthy to me") elif(lb=="demaged"): st.write("No recognizable disease found") else: if(sc>7): final_result = run(weights,file_name) st.image(final_result, caption='Diseases Detected', width=400) else: st.write("No disease detected") #final_result = run(weights,file_name) #st.image(final_result, caption='Diseases Detected') os.remove(file_name) #Remove the temporary JPEG file after processing os.remove(temp_jpeg_file) if __name__ == "__main__": opt = parse_opt() model=NaturalSceneClassification() model=torch.load("mobilenetv2-apple-10-class-pytorch.pth",map_location=device ) model.eval() labels=[] with open("labels.txt") as file: for line in file: line = line.strip() #or some other preprocessing labels.append(line) #st main(opt,model,labels)