def extract_boxes(path=DATASETS_DIR / 'coco128'): # from utils.dataloaders import *; extract_boxes() # Convert detection dataset into classification dataset, with one directory per class path = Path(path) # images dir shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None # remove existing files = list(path.rglob('*.*')) n = len(files) # number of files for im_file in tqdm(files, total=n): if im_file.suffix[1:] in IMG_FORMATS: # image im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB h, w = im.shape[:2] # labels lb_file = Path(img2label_paths([str(im_file)])[0]) if Path(lb_file).exists(): with open(lb_file) as f: lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels for j, x in enumerate(lb): c = int(x[0]) # class f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename if not f.parent.is_dir(): f.parent.mkdir(parents=True) b = x[1:] * [w, h, w, h] # box # b[2:] = b[2:].max() # rectangle to square b[2:] = b[2:] * 1.2 + 3 # pad b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int) b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image b[[1, 3]] = np.clip(b[[1, 3]], 0, h) assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
def on_train_end(self, last, best, plots, epoch, results): # Callback runs on training end if plots: plot_results(file=self.save_dir / 'results.csv') # save results.png files = [ 'results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')) ] files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter if self.tb: for f in files: self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') if self.wandb: self.wandb.log({k: v for k, v in zip(self.keys[3:10], results) }) # log best.pt val results self.wandb.log({ "Results": [wandb.Image(str(f), caption=f.name) for f in files] }) # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model if not self.opt.evolve: wandb.log_artifact(str(best if best.exists() else last), type='model', name='run_' + self.wandb.wandb_run.id + '_model', aliases=['latest', 'best', 'stripped']) self.wandb.finish_run()
def load_image(self, i): # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw) im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i], if im is None: # not cached in RAM if fn.exists(): # load npy im = np.load(fn) else: # read image im = cv2.imread(f) # BGR assert im is not None, f'Image Not Found {f}' h0, w0 = im.shape[:2] # orig hw r = self.img_size / max(h0, w0) # ratio if r != 1: # if sizes are not equal interp = cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA im = cv2.resize(im, (int(w0 * r), int(h0 * r)), interpolation=interp) return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized return self.ims[i], self.im_hw0[i], self.im_hw[i] # im, hw_original, hw_resized
def _hub_ops(f, max_dim=1920): # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing f_new = im_dir / Path(f).name # dataset-hub image filename try: # use PIL im = Image.open(f) r = max_dim / max(im.height, im.width) # ratio if r < 1.0: # image too large im = im.resize((int(im.width * r), int(im.height * r))) im.save(f_new, 'JPEG', quality=75, optimize=True) # save except Exception as e: # use OpenCV print(f'WARNING: HUB ops PIL failure {f}: {e}') im = cv2.imread(f) im_height, im_width = im.shape[:2] r = max_dim / max(im_height, im_width) # ratio if r < 1.0: # image too large im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA) cv2.imwrite(str(f_new), im)
def __next__(self): if self.count == self.nf: raise StopIteration path = self.files[self.count] if self.video_flag[self.count]: # Read video self.mode = 'video' ret_val, img0 = self.cap.read() while not ret_val: self.count += 1 self.cap.release() if self.count == self.nf: # last video raise StopIteration else: path = self.files[self.count] self.new_video(path) ret_val, img0 = self.cap.read() self.frame += 1 s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ' else: # Read image self.count += 1 img0 = cv2.imread(path) # BGR assert img0 is not None, f'Image Not Found {path}' s = f'image {self.count}/{self.nf} {path}: ' # Padded resize img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0] # Convert img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB img = np.ascontiguousarray(img) return path, img, img0, self.cap, s
def cache_images_to_disk(self, i): # Saves an image as an *.npy file for faster loading f = self.npy_files[i] if not f.exists(): np.save(f.as_posix(), cv2.imread(self.im_files[i]))
if __name__ == '__main__': model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # model = custom(path='path/to/model.pt') # custom # Verify inference from pathlib import Path import numpy as np from PIL import Image from utils.general import cv2 imgs = [ 'data/images/zidane.jpg', # filename Path('data/images/zidane.jpg'), # Path 'https://ultralytics.com/images/zidane.jpg', # URI cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV Image.open('data/images/bus.jpg'), # PIL np.zeros((320, 640, 3)) ] # numpy results = model(imgs, size=320) # batched inference results.print() results.save()