def extract_boxes(path='../coco128/'): # from utils.datasets import *; extract_boxes('../coco128') # 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, 'r') 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 create_dataset_table(self, dataset, class_to_id, name='dataset'): # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging artifact = wandb.Artifact(name=name, type="dataset") img_files = tqdm([dataset.path]) if isinstance( dataset.path, str) and Path(dataset.path).is_dir() else None img_files = tqdm(dataset.img_files) if not img_files else img_files for img_file in img_files: if Path(img_file).is_dir(): artifact.add_dir(img_file, name='data/images') labels_path = 'labels'.join(dataset.path.rsplit('images', 1)) artifact.add_dir(labels_path, name='data/labels') else: artifact.add_file(img_file, name='data/images/' + Path(img_file).name) label_file = Path(img2label_paths([img_file])[0]) artifact.add_file( str(label_file), name='data/labels/' + label_file.name) if label_file.exists() else None table = wandb.Table(columns=["id", "train_image", "Classes", "name"]) class_set = wandb.Classes([{ 'id': id, 'name': name } for id, name in class_to_id.items()]) for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)): height, width = shapes[0] labels[:, 2:] = (xywh2xyxy(labels[:, 2:].view( -1, 4))) * torch.Tensor([width, height, width, height]) box_data, img_classes = [], {} for cls, *xyxy in labels[:, 1:].tolist(): cls = int(cls) box_data.append({ "position": { "minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3] }, "class_id": cls, "box_caption": "%s" % (class_to_id[cls]), "scores": { "acc": 1 }, "domain": "pixel" }) img_classes[cls] = class_to_id[cls] boxes = { "ground_truth": { "box_data": box_data, "class_labels": class_to_id } } # inference-space table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), json.dumps(img_classes), Path(paths).name) artifact.add(table, name) return artifact
def plot_labels(labels, save_dir=Path(''), loggers=None): # plot dataset labels print('Plotting labels... ') c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes nc = int(c.max() + 1) # number of classes colors = color_list() x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height']) # seaborn correlogram sns.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9)) plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200) plt.close() # matplotlib labels matplotlib.use('svg') # faster ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) ax[0].set_xlabel('classes') sns.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9) sns.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9) # rectangles labels[:, 1:3] = 0.5 # center labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000 img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255) for cls, *box in labels[:1000]: ImageDraw.Draw(img).rectangle(box, width=1, outline=colors[int(cls) % 10]) # plot ax[1].imshow(img) ax[1].axis('off') for a in [0, 1, 2, 3]: for s in ['top', 'right', 'left', 'bottom']: ax[a].spines[s].set_visible(False) plt.savefig(save_dir / 'labels.jpg', dpi=200) matplotlib.use('Agg') plt.close() # loggers for k, v in loggers.items() or {}: if k == 'wandb' and v: v.log( { "Labels": [ v.Image(str(x), caption=x.name) for x in save_dir.glob('*labels*.jpg') ] }, commit=False)
def plot_labels(labels, save_dir=Path(""), loggers=None): # plot dataset labels print("Plotting labels... ") c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes nc = int(c.max() + 1) # number of classes colors = color_list() x = pd.DataFrame(b.transpose(), columns=["x", "y", "width", "height"]) # seaborn correlogram sns.pairplot( x, corner=True, diag_kind="auto", kind="hist", diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9), ) plt.savefig(save_dir / "labels_correlogram.jpg", dpi=200) plt.close() # matplotlib labels matplotlib.use("svg") # faster ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) ax[0].set_xlabel("classes") sns.histplot(x, x="x", y="y", ax=ax[2], bins=50, pmax=0.9) sns.histplot(x, x="width", y="height", ax=ax[3], bins=50, pmax=0.9) # rectangles labels[:, 1:3] = 0.5 # center labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000 img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255) for cls, *box in labels[:1000]: ImageDraw.Draw(img).rectangle(box, width=1, outline=colors[int(cls) % 10]) # plot ax[1].imshow(img) ax[1].axis("off") for a in [0, 1, 2, 3]: for s in ["top", "right", "left", "bottom"]: ax[a].spines[s].set_visible(False) plt.savefig(save_dir / "labels.jpg", dpi=200) matplotlib.use("Agg") plt.close() # loggers for k, v in loggers.items() or {}: if k == "wandb" and v: v.log({ "Labels": [ v.Image(str(x), caption=x.name) for x in save_dir.glob("*labels*.jpg") ] })
def plot_labels(labels, names=(), save_dir=Path('')): # plot dataset labels LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ") c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes nc = int(c.max() + 1) # number of classes x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height']) # seaborn correlogram sn.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9)) plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200) plt.close() # matplotlib labels matplotlib.use('svg') # faster ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) try: # color histogram bars by class [ y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc) ] # known issue #3195 except Exception: pass ax[0].set_ylabel('instances') if 0 < len(names) < 30: ax[0].set_xticks(range(len(names))) ax[0].set_xticklabels(names, rotation=90, fontsize=10) else: ax[0].set_xlabel('classes') sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9) sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9) # rectangles labels[:, 1:3] = 0.5 # center labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000 img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255) for cls, *box in labels[:1000]: ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot ax[1].imshow(img) ax[1].axis('off') for a in [0, 1, 2, 3]: for s in ['top', 'right', 'left', 'bottom']: ax[a].spines[s].set_visible(False) plt.savefig(save_dir / 'labels.jpg', dpi=200) matplotlib.use('Agg') plt.close()
def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True): # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop xyxy = torch.tensor(xyxy).view(-1, 4) b = xyxy2xywh(xyxy) # boxes if square: b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad xyxy = xywh2xyxy(b).long() clip_coords(xyxy, im.shape) crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)] if save: file.parent.mkdir(parents=True, exist_ok=True) # make directory cv2.imwrite(str(increment_path(file).with_suffix('.jpg')), crop) return crop
def forward(self, im, augment=False, visualize=False, val=False): # YOLOv5 MultiBackend inference b, ch, h, w = im.shape # batch, channel, height, width if self.pt or self.jit: # PyTorch y = self.model(im) if self.jit else self.model( im, augment=augment, visualize=visualize) return y if val else y[0] elif self.dnn: # ONNX OpenCV DNN im = im.cpu().numpy() # torch to numpy self.net.setInput(im) y = self.net.forward() elif self.onnx: # ONNX Runtime im = im.cpu().numpy() # torch to numpy y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0] elif self.xml: # OpenVINO im = im.cpu().numpy() # FP32 desc = self.ie.TensorDesc(precision='FP32', dims=im.shape, layout='NCHW') # Tensor Description request = self.executable_network.requests[0] # inference request request.set_blob(blob_name='images', blob=self.ie.Blob( desc, im)) # name=next(iter(request.input_blobs)) request.infer() y = request.output_blobs[ 'output'].buffer # name=next(iter(request.output_blobs)) elif self.engine: # TensorRT assert im.shape == self.bindings['images'].shape, ( im.shape, self.bindings['images'].shape) self.binding_addrs['images'] = int(im.data_ptr()) self.context.execute_v2(list(self.binding_addrs.values())) y = self.bindings['output'].data elif self.coreml: # CoreML im = im.permute( 0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) im = Image.fromarray((im[0] * 255).astype('uint8')) # im = im.resize((192, 320), Image.ANTIALIAS) y = self.model.predict({'image': im}) # coordinates are xywh normalized if 'confidence' in y: box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels conf, cls = y['confidence'].max(1), y['confidence'].argmax( 1).astype(np.float) y = np.concatenate( (box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) else: y = y[sorted(y)[-1]] # last output else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) im = im.permute( 0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) if self.saved_model: # SavedModel y = self.model(im, training=False).numpy() elif self.pb: # GraphDef y = self.frozen_func(x=self.tf.constant(im)).numpy() elif self.tflite: # Lite input, output = self.input_details[0], self.output_details[0] int8 = input[ 'dtype'] == np.uint8 # is TFLite quantized uint8 model if int8: scale, zero_point = input['quantization'] im = (im / scale + zero_point).astype(np.uint8) # de-scale self.interpreter.set_tensor(input['index'], im) self.interpreter.invoke() y = self.interpreter.get_tensor(output['index']) if int8: scale, zero_point = output['quantization'] y = (y.astype(np.float32) - zero_point) * scale # re-scale y[..., :4] *= [w, h, w, h] # xywh normalized to pixels y = torch.tensor(y) if isinstance(y, np.ndarray) else y return (y, []) if val else y
def test_model(self, config, testset): # pylint: disable=unused-argument """The testing loop for YOLOv5. Arguments: config: Configuration parameters as a dictionary. testset: The test dataset. """ assert Config().data.datasource == 'YOLO' test_loader = yolo.DataSource.get_test_loader(config['batch_size'], testset) device = next(self.model.parameters()).device # get model device # Configure self.model.eval() with open(Config().data.data_params) as f: data = yaml.load(f, Loader=yaml.SafeLoader) # model dict check_dataset(data) # check nc = Config().data.num_classes # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() seen = 0 names = { k: v for k, v in enumerate(self.model.names if hasattr( self.model, 'names') else self.module.names) } s = ('%20s' + '%12s' * 6) % \ ('Class', 'Images', 'Targets', 'P', 'R', '[email protected]', '[email protected]:.95') p, r, f1, mp, mr, map50, map, = 0., 0., 0., 0., 0., 0., 0. stats, ap, ap_class = [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(test_loader, desc=s)): img = img.to(device, non_blocking=True).float() img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width with torch.no_grad(): # Run model if Config().algorithm.type == 'mistnet': logits = self.model.forward_to(img) logits = logits.cpu().detach().numpy() logits = unary_encoding.encode(logits) logits = torch.from_numpy(logits.astype('float32')) out, train_out = self.model.forward_from(logits.to(device)) else: out, train_out = self.model(img) # Run NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = [] # for autolabelling out = non_max_suppression(out, conf_thres=0.001, iou_thres=0.6, labels=lb, multi_label=True) # Statistics per image for si, pred in enumerate(out): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class seen += 1 if len(pred) == 0: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Predictions predn = pred.clone() scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1]) # native-space pred # Assign all predictions as incorrect correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device) if nl: detected = [] # target indices tcls_tensor = labels[:, 0] # target boxes tbox = xywh2xyxy(labels[:, 1:5]) scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1]) # native-space labels # Per target class for cls in torch.unique(tcls_tensor): ti = (cls == tcls_tensor).nonzero(as_tuple=False).view( -1) # prediction indices pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view( -1) # target indices # Search for detections if pi.shape[0]: # Prediction to target ious ious, i = box_iou(predn[pi, :4], tbox[ti]).max( 1) # best ious, indices # Append detections detected_set = set() for j in (ious > iouv[0]).nonzero(as_tuple=False): d = ti[i[j]] # detected target if d.item() not in detected_set: detected_set.add(d.item()) detected.append(d) correct[pi[j]] = ious[ j] > iouv # iou_thres is 1xn if len( detected ) == nl: # all targets already located in image break # Append statistics (correct, conf, pcls, tcls) stats.append( (correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, plot=False, save_dir='', names=names) ap50, ap = ap[:, 0], ap.mean(1) # [email protected], [email protected]:0.95 mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%12.3g' * 6 # print format print(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) return map50
def forward(self, im, augment=False, visualize=False, val=False): # YOLOv5 MultiBackend inference b, ch, h, w = im.shape # batch, channel, height, width if self.pt: # PyTorch y = self.model(im) if self.jit else self.model( im, augment=augment, visualize=visualize) return y if val else y[0] elif self.coreml: # CoreML *.mlmodel im = im.permute( 0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) im = Image.fromarray((im[0] * 255).astype('uint8')) # im = im.resize((192, 320), Image.ANTIALIAS) y = self.model.predict({'image': im}) # coordinates are xywh normalized box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels conf, cls = y['confidence'].max(1), y['confidence'].argmax( 1).astype(np.float) y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) elif self.onnx: # ONNX im = im.cpu().numpy() # torch to numpy if self.dnn: # ONNX OpenCV DNN self.net.setInput(im) y = self.net.forward() else: # ONNX Runtime y = self.session.run( [self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0] elif self.engine: # TensorRT assert im.shape == self.bindings['images'].shape, ( im.shape, self.bindings['images'].shape) self.binding_addrs['images'] = int(im.data_ptr()) self.context.execute_v2(list(self.binding_addrs.values())) y = self.bindings['output'].data else: # TensorFlow model (TFLite, pb, saved_model) im = im.permute( 0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) if self.pb: y = self.frozen_func(x=self.tf.constant(im)).numpy() elif self.saved_model: y = self.model(im, training=False).numpy() elif self.tflite: input, output = self.input_details[0], self.output_details[0] int8 = input[ 'dtype'] == np.uint8 # is TFLite quantized uint8 model if int8: scale, zero_point = input['quantization'] im = (im / scale + zero_point).astype(np.uint8) # de-scale self.interpreter.set_tensor(input['index'], im) self.interpreter.invoke() y = self.interpreter.get_tensor(output['index']) if int8: scale, zero_point = output['quantization'] y = (y.astype(np.float32) - zero_point) * scale # re-scale y[..., 0] *= w # x y[..., 1] *= h # y y[..., 2] *= w # w y[..., 3] *= h # h y = torch.tensor(y) if isinstance(y, np.ndarray) else y return (y, []) if val else y
def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, cache_images=False, single_cls=False, stride=32, pad=0.0, rank=-1): try: f = [] # image files for p in path if isinstance(path, list) else [path]: p = str(Path(p)) # os-agnostic parent = str(Path(p).parent) + os.sep if os.path.isfile(p): # file with open(p, 'r') as t: t = t.read().splitlines() f += [ x.replace('./', parent) if x.startswith('./') else x for x in t ] # local to global path elif os.path.isdir(p): # folder f += glob.iglob(p + os.sep + '*.*') else: raise Exception('%s does not exist' % p) self.img_files = sorted([ x.replace('/', os.sep) for x in f if os.path.splitext(x)[-1].lower() in img_formats ]) except Exception as e: raise Exception('Error loading data from %s: %s\nSee %s' % (path, e, help_url)) n = len(self.img_files) assert n > 0, 'No images found in %s. See %s' % (path, help_url) bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index nb = bi[-1] + 1 # number of batches self.n = n # number of images self.batch = bi # batch index of image self.img_size = img_size self.augment = augment self.hyp = hyp self.image_weights = image_weights self.rect = False if image_weights else rect self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) self.mosaic_border = [-img_size // 2, -img_size // 2] self.stride = stride # Define labels self.label_files = [ x.replace('images', 'labels').replace(os.path.splitext(x)[-1], '.txt') for x in self.img_files ] # Check cache cache_path = str(Path( self.label_files[0]).parent) + '.cache' # cached labels if os.path.isfile(cache_path): cache = torch.load(cache_path) # load if cache['hash'] != get_hash(self.label_files + self.img_files): # dataset changed cache = self.cache_labels(cache_path) # re-cache else: cache = self.cache_labels(cache_path) # cache # Get labels labels, shapes = zip(*[cache[x] for x in self.img_files]) self.shapes = np.array(shapes, dtype=np.float64) self.labels = list(labels) # Rectangular Training https://github.com/ultralytics/yolov3/issues/232 if self.rect: # Sort by aspect ratio s = self.shapes # wh ar = s[:, 1] / s[:, 0] # aspect ratio irect = ar.argsort() self.img_files = [self.img_files[i] for i in irect] self.label_files = [self.label_files[i] for i in irect] self.labels = [self.labels[i] for i in irect] self.shapes = s[irect] # wh ar = ar[irect] # Set training image shapes shapes = [[1, 1]] * nb for i in range(nb): ari = ar[bi == i] mini, maxi = ari.min(), ari.max() if maxi < 1: shapes[i] = [maxi, 1] elif mini > 1: shapes[i] = [1, 1 / mini] self.batch_shapes = np.ceil( np.array(shapes) * img_size / stride + pad).astype( np.int) * stride # Cache labels create_datasubset, extract_bounding_boxes, labels_loaded = False, False, False nm, nf, ne, ns, nd = 0, 0, 0, 0, 0 # number missing, found, empty, datasubset, duplicate pbar = enumerate(self.label_files) if rank in [-1, 0]: pbar = tqdm(pbar) for i, file in pbar: l = self.labels[i] # label if l is not None and l.shape[0]: assert l.shape[1] == 5, '> 5 label columns: %s' % file assert (l >= 0).all(), 'negative labels: %s' % file assert (l[:, 1:] <= 1).all( ), 'non-normalized or out of bounds coordinate labels: %s' % file if np.unique(l, axis=0).shape[0] < l.shape[0]: # duplicate rows nd += 1 # print('WARNING: duplicate rows in %s' % self.label_files[i]) # duplicate rows if single_cls: l[:, 0] = 0 # force dataset into single-class mode self.labels[i] = l nf += 1 # file found # Create subdataset (a smaller dataset) if create_datasubset and ns < 1E4: if ns == 0: create_folder(path='./datasubset') os.makedirs('./datasubset/images') exclude_classes = 43 if exclude_classes not in l[:, 0]: ns += 1 # shutil.copy(src=self.img_files[i], dst='./datasubset/images/') # copy image with open('./datasubset/images.txt', 'a') as f: f.write(self.img_files[i] + '\n') # Extract object detection boxes for a second stage classifier if extract_bounding_boxes: p = Path(self.img_files[i]) img = cv2.imread(str(p)) h, w = img.shape[:2] for j, x in enumerate(l): f = '%s%sclassifier%s%g_%g_%s' % ( p.parent.parent, os.sep, os.sep, x[0], j, p.name) if not os.path.exists(Path(f).parent): os.makedirs( Path(f).parent) # make new output folder b = x[1:] * [w, h, w, h] # box b[2:] = b[2:].max() # rectangle to square b[2:] = b[2:] * 1.3 + 30 # 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(f, img[ b[1]:b[3], b[0]:b[2]]), 'Failure extracting classifier boxes' else: ne += 1 # print('empty labels for image %s' % self.img_files[i]) # file empty # os.system("rm '%s' '%s'" % (self.img_files[i], self.label_files[i])) # remove if rank in [-1, 0]: pbar.desc = 'Scanning labels %s (%g found, %g missing, %g empty, %g duplicate, for %g images)' % ( cache_path, nf, nm, ne, nd, n) if nf == 0: s = 'WARNING: No labels found in %s. See %s' % ( os.path.dirname(file) + os.sep, help_url) print(s) assert not augment, '%s. Can not train without labels.' % s # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM) self.imgs = [None] * n if cache_images: gb = 0 # Gigabytes of cached images pbar = tqdm(range(len(self.img_files)), desc='Caching images') self.img_hw0, self.img_hw = [None] * n, [None] * n for i in pbar: # max 10k images self.imgs[i], self.img_hw0[i], self.img_hw[i] = load_image( self, i) # img, hw_original, hw_resized gb += self.imgs[i].nbytes pbar.desc = 'Caching images (%.1fGB)' % (gb / 1E9)
def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=1920, max_subplots=16): # Plot image grid with labels if isinstance(images, torch.Tensor): images = images.cpu().float().numpy() if isinstance(targets, torch.Tensor): targets = targets.cpu().numpy() if np.max(images[0]) <= 1: images *= 255 # de-normalise (optional) bs, _, h, w = images.shape # batch size, _, height, width bs = min(bs, max_subplots) # limit plot images ns = np.ceil(bs**0.5) # number of subplots (square) # Build Image mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init for i, im in enumerate(images): if i == max_subplots: # if last batch has fewer images than we expect break x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin im = im.transpose(1, 2, 0) mosaic[y:y + h, x:x + w, :] = im # Resize (optional) scale = max_size / ns / max(h, w) if scale < 1: h = math.ceil(scale * h) w = math.ceil(scale * w) mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) # Annotate fs = int((h + w) * ns * 0.01) # font size annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) for i in range(i + 1): x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders if paths: annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames if len(targets) > 0: ti = targets[targets[:, 0] == i] # image targets boxes = xywh2xyxy(ti[:, 2:6]).T classes = ti[:, 1].astype('int') labels = ti.shape[1] == 6 # labels if no conf column conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred) if boxes.shape[1]: if boxes.max() <= 1.01: # if normalized with tolerance 0.01 boxes[[0, 2]] *= w # scale to pixels boxes[[1, 3]] *= h elif scale < 1: # absolute coords need scale if image scales boxes *= scale boxes[[0, 2]] += x boxes[[1, 3]] += y for j, box in enumerate(boxes.T.tolist()): cls = classes[j] color = colors(cls) cls = names[cls] if names else cls if labels or conf[j] > 0.25: # 0.25 conf thresh label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}' annotator.box_label(box, label, color=color) annotator.im.save(fname) # save
def run(data, weights=None, # model.pt path(s) batch_size=32, # batch size imgsz=640, # inference size (pixels) conf_thres=0.001, # confidence threshold iou_thres=0.6, # NMS IoU threshold task='val', # train, val, test, speed or study device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu single_cls=False, # treat as single-class dataset augment=False, # augmented inference verbose=False, # verbose output save_txt=False, # save results to *.txt save_hybrid=False, # save label+prediction hybrid results to *.txt save_conf=False, # save confidences in --save-txt labels save_json=False, # save a COCO-JSON results file project=ROOT / 'runs/val', # save to project/name name='exp', # save to project/name exist_ok=False, # existing project/name ok, do not increment half=True, # use FP16 half-precision inference model=None, dataloader=None, save_dir=Path(''), callbacks=Callbacks(), compute_loss=None, ): # Initialize/load model and set device training = model is not None if training: # called by train.py device = next(model.parameters()).device # get model device else: # called directly device = select_device(device, batch_size=batch_size) # 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 check_suffix(weights, '.pt') model = attempt_load(weights, map_location=device) # load FP32 model gs = max(int(model.stride.max()), 32) # grid size (max stride) imgsz = check_img_size(imgsz, s=gs) # check image size # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99 # if device.type != 'cpu' and torch.cuda.device_count() > 1: # model = nn.DataParallel(model) # Data data = check_dataset(data) # check # Half half &= device.type != 'cpu' # half precision only supported on CUDA model.half() if half else model.float() # Configure model.eval() is_coco = isinstance(data.get('val'), str) and data['val'].endswith('coco/val2017.txt') # COCO dataset nc = 1 if single_cls else int(data['nc']) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() # Dataloader if not training: if device.type != 'cpu': model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once pad = 0.0 if task == 'speed' else 0.5 task = task if task in ('train', 'val', 'test') else 'val' # path to train/val/test images dataloader = create_dataloader(data[task], imgsz, batch_size, gs, single_cls, pad=pad, rect=True, prefix=colorstr(f'{task}: '))[0] seen = 0 confusion_matrix = ConfusionMatrix(nc=nc) names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)} class_map = coco80_to_coco91_class() if is_coco else list(range(1000)) s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', '[email protected]', '[email protected]:.95') dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class = [], [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): t1 = time_sync() img = img.to(device, non_blocking=True) img = img.half() if half else img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width t2 = time_sync() dt[0] += t2 - t1 # Run model out, train_out = model(img, augment=augment) # inference and training outputs dt[1] += time_sync() - t2 # Compute loss if compute_loss: loss += compute_loss([x.float() for x in train_out], targets)[1] # box, obj, cls # Run NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling t3 = time_sync() out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) dt[2] += time_sync() - t3 # Statistics per image for si, pred in enumerate(out): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class path, shape = Path(paths[si]), shapes[si][0] seen += 1 if len(pred) == 0: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Predictions if single_cls: pred[:, 5] = 0 predn = pred.clone() scale_coords(img[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred # Evaluate if nl: tbox = xywh2xyxy(labels[:, 1:5]) # target boxes scale_coords(img[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels correct = process_batch(predn, labelsn, iouv) else: correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool) stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # (correct, conf, pcls, tcls) # Save/log if save_txt: save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt')) if save_json: save_one_json(predn, jdict, path, class_map) # append to COCO-JSON dictionary callbacks.run('on_val_image_end', pred, predn, path, names, img[si]) # Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, save_dir=save_dir, names=names) ap50, ap = ap[:, 0], ap.mean(1) # [email protected], [email protected]:0.95 mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format LOGGER.info(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) # Print results per class if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats): for i, c in enumerate(ap_class): LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1E3 for x in dt) # speeds per image if not training: shape = (batch_size, 3, imgsz, imgsz) LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t) # Save JSON if save_json and len(jdict): w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else '' # weights anno_json = str(Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json') # annotations json pred_json = str(save_dir / f"{w}_predictions.json") # predictions json LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...') with open(pred_json, 'w') as f: json.dump(jdict, f) try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb check_requirements(['pycocotools']) from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval anno = COCO(anno_json) # init annotations api pred = anno.loadRes(pred_json) # init predictions api eval = COCOeval(anno, pred, 'bbox') if is_coco: eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files] # image IDs to evaluate eval.evaluate() eval.accumulate() eval.summarize() map, map50 = eval.stats[:2] # update results ([email protected]:0.95, [email protected]) except Exception as e: LOGGER.info(f'pycocotools unable to run: {e}') # Return results model.float() # for training if not training: 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}") maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def test( weights=None, data="yolov5/data/coco128.yaml", batch_size=32, image_size=640, conf_thres=0.001, iou_thres=0.6, # for NMS task="val", device="", single_cls=False, augment=False, verbose=False, save_txt=False, # for auto-labelling save_hybrid=False, # for hybrid auto-labelling save_conf=False, # save auto-label confidences save_json=False, project="runs/test", name="exp", exist_ok=False, model=None, dataloader=None, save_dir=Path(""), # for saving images plots=True, log_imgs=0, # number of logged images ): arguments = locals() # Initialize/load model and set device training = model is not None if training: # called by train.py device = next(model.parameters()).device # get model device else: # called directly set_logging() device = select_device(device, batch_size=batch_size) # Directories save_dir = Path(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 model = attempt_load(weights, map_location=device) # load FP32 model image_size = check_img_size(image_size, s=model.stride.max()) # check img_size # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99 # if device.type != 'cpu' and torch.cuda.device_count() > 1: # model = nn.DataParallel(model) # Half half = device.type != "cpu" # half precision only supported on CUDA if half: model.half() # Configure model.eval() is_coco = data.endswith("coco.yaml") # is COCO dataset with open(data) as f: data = yaml.load(f, Loader=yaml.FullLoader) # model dict check_dataset(data) # check nc = 1 if single_cls else int(data["nc"]) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() # Logging log_imgs, wandb = min(log_imgs, 100), None # ceil try: import wandb # Weights & Biases except ImportError: log_imgs = 0 # Dataloader if not training: img = torch.zeros((1, 3, image_size, image_size), device=device) # init img _ = (model(img.half() if half else img) if device.type != "cpu" else None) # run once path = (data["test"] if task == "test" else data["val"] ) # path to val/test images opt = OptFactory(arguments) dataloader = create_dataloader(path, image_size, batch_size, model.stride.max(), opt, pad=0.5, rect=True)[0] seen = 0 confusion_matrix = ConfusionMatrix(nc=nc) names = { k: v for k, v in enumerate( model.names if hasattr(model, "names") else model.module.names) } coco91class = coco80_to_coco91_class() s = ("%20s" + "%12s" * 6) % ( "Class", "Images", "Targets", "P", "R", "[email protected]", "[email protected]:.95", ) p, r, f1, mp, mr, map50, map, t0, t1 = 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class, wandb_images = [], [], [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): img = img.to(device, non_blocking=True) img = img.half() if half else img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width with torch.no_grad(): # Run model t = time_synchronized() inf_out, train_out = model( img, augment=augment) # inference and training outputs t0 += time_synchronized() - t # Compute loss if training: loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3] # box, obj, cls # Run NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = ([targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] ) # for autolabelling t = time_synchronized() output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb) t1 += time_synchronized() - t # Statistics per image for si, pred in enumerate(output): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class path = Path(paths[si]) seen += 1 if len(pred) == 0: if nl: stats.append(( torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls, )) continue # Predictions predn = pred.clone() scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1]) # native-space pred # Append to text file if save_txt: gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0 ]] # normalization gain whwh for *xyxy, conf, cls in predn.tolist(): 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(save_dir / "labels" / (path.stem + ".txt"), "a") as f: f.write(("%g " * len(line)).rstrip() % line + "\n") # W&B logging if plots and len(wandb_images) < log_imgs: box_data = [{ "position": { "minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3], }, "class_id": int(cls), "box_caption": "%s %.3f" % (names[cls], conf), "scores": { "class_score": conf }, "domain": "pixel", } for *xyxy, conf, cls in pred.tolist()] boxes = { "predictions": { "box_data": box_data, "class_labels": names } } # inference-space wandb_images.append( wandb.Image(img[si], boxes=boxes, caption=path.name)) # Append to pycocotools JSON dictionary if save_json: # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ... image_id = int( path.stem) if path.stem.isnumeric() else path.stem box = xyxy2xywh(predn[:, :4]) # xywh box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner for p, b in zip(pred.tolist(), box.tolist()): jdict.append({ "image_id": image_id, "category_id": coco91class[int(p[5])] if is_coco else int(p[5]), "bbox": [round(x, 3) for x in b], "score": round(p[4], 5), }) # Assign all predictions as incorrect correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device) if nl: detected = [] # target indices tcls_tensor = labels[:, 0] # target boxes tbox = xywh2xyxy(labels[:, 1:5]) scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1]) # native-space labels if plots: confusion_matrix.process_batch( pred, torch.cat((labels[:, 0:1], tbox), 1)) # Per target class for cls in torch.unique(tcls_tensor): ti = ((cls == tcls_tensor).nonzero(as_tuple=False).view(-1) ) # prediction indices pi = ((cls == pred[:, 5]).nonzero(as_tuple=False).view(-1) ) # target indices # Search for detections if pi.shape[0]: # Prediction to target ious ious, i = box_iou(predn[pi, :4], tbox[ti]).max( 1) # best ious, indices # Append detections detected_set = set() for j in (ious > iouv[0]).nonzero(as_tuple=False): d = ti[i[j]] # detected target if d.item() not in detected_set: detected_set.add(d.item()) detected.append(d) correct[ pi[j]] = ious[j] > iouv # iou_thres is 1xn if (len(detected) == nl ): # all targets already located in image break # Append statistics (correct, conf, pcls, tcls) stats.append( (correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # Plot images if plots and batch_i < 3: f = save_dir / f"test_batch{batch_i}_labels.jpg" # labels Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start() f = save_dir / f"test_batch{batch_i}_pred.jpg" # predictions Thread( target=plot_images, args=(img, output_to_target(output), paths, f, names), daemon=True, ).start() # Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names) p, r, ap50, ap = ( p[:, 0], r[:, 0], ap[:, 0], ap.mean(1), ) # [P, R, [email protected], [email protected]:0.95] mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = "%20s" + "%12.3g" * 6 # print format print(pf % ("all", seen, nt.sum(), mp, mr, map50, map)) # Print results per class if verbose and nc > 1 and len(stats): for i, c in enumerate(ap_class): print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1e3 for x in (t0, t1, t0 + t1)) + ( image_size, image_size, batch_size, ) # tuple if not training: print( "Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g" % t) # Plots if plots: confusion_matrix.plot(save_dir=save_dir, names=list(names.values())) if wandb and wandb.run: wandb.log({"Images": wandb_images}) wandb.log({ "Validation": [ wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob("test*.jpg")) ] }) # Save JSON if save_json and len(jdict): w = (Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else "") # weights anno_json = "../coco/annotations/instances_val2017.json" # annotations json pred_json = str(save_dir / f"{w}_predictions.json") # predictions json print("\nEvaluating pycocotools mAP... saving %s..." % pred_json) with open(pred_json, "w") as f: json.dump(jdict, f) try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval anno = COCO(anno_json) # init annotations api pred = anno.loadRes(pred_json) # init predictions api eval = COCOeval(anno, pred, "bbox") if is_coco: eval.params.imgIds = [ int(Path(x).stem) for x in dataloader.dataset.img_files ] # image IDs to evaluate eval.evaluate() eval.accumulate() eval.summarize() map, map50 = eval.stats[: 2] # update results ([email protected]:0.95, [email protected]) except Exception as e: print(f"pycocotools unable to run: {e}") # Return results if not training: 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}") model.float() # for training maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def test(data, weights=None, batch_size=16, imgsz=640, conf_thres=0.001, iou_thres=0.6, # for NMS save_json=False, single_cls=False, augment=False, verbose=False, model=None, dataloader=None, save_dir=Path(''), # for saving images save_txt=False, # for auto-labelling save_conf=False, plots=True): # Initialize/load model and set device training = model is not None if training: # called by train.py device = next(model.parameters()).device # get model device else: # called directly set_logging() device = select_device(opt.device, batch_size=batch_size) save_txt = opt.save_txt # save *.txt labels # Remove previous if os.path.exists(save_dir): shutil.rmtree(save_dir) # delete dir os.makedirs(save_dir) # make new dir if save_txt: out = save_dir / 'autolabels' if os.path.exists(out): shutil.rmtree(out) # delete dir os.makedirs(out) # make new dir # Load model model = attempt_load(weights, map_location=device) # load FP32 model imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99 # if device.type != 'cpu' and torch.cuda.device_count() > 1: # model = nn.DataParallel(model) # Half half = device.type != 'cpu' # half precision only supported on CUDA if half: model.half() # Configure model.eval() with open(data) as f: data = yaml.load(f, Loader=yaml.FullLoader) # model dict check_dataset(data) # check nc = 1 if single_cls else int(data['nc']) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() # Dataloader if not training: img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img _ = model(img.half() if half else img) if device.type != 'cpu' else None # run once path = data['test'] if opt.task == 'test' else data['val'] # path to val/test images dataloader = create_dataloader(path, imgsz, batch_size, model.stride.max(), opt, hyp=None, augment=False, cache=False, pad=0.5, rect=True)[0] seen = 0 names = model.names if hasattr(model, 'names') else model.module.names coco91class = coco80_to_coco91_class() s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Targets', 'P', 'R', '[email protected]', '[email protected]:.95') p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0. loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class = [], [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): img = img.to(device, non_blocking=True) img = img.half() if half else img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width whwh = torch.Tensor([width, height, width, height]).to(device) # Disable gradients with torch.no_grad(): # Run model t = time_synchronized() inf_out, train_out = model(img, augment=augment) # inference and training outputs t0 += time_synchronized() - t # Compute loss if training: # if model has loss hyperparameters loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3] # box, obj, cls # Run NMS t = time_synchronized() output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres) t1 += time_synchronized() - t # Statistics per image for si, pred in enumerate(output): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class seen += 1 if pred is None: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Append to text file if save_txt: gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]] # normalization gain whwh x = pred.clone() x[:, :4] = scale_coords(img[si].shape[1:], x[:, :4], shapes[si][0], shapes[si][1]) # to original for *xyxy, conf, cls in x: xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh line = (cls, conf, *xywh) if save_conf else (cls, *xywh) # label format with open(str(out / Path(paths[si]).stem) + '.txt', 'a') as f: f.write(('%g ' * len(line) + '\n') % line) # Clip boxes to image bounds clip_coords(pred, (height, width)) # Append to pycocotools JSON dictionary if save_json: # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ... image_id = Path(paths[si]).stem box = pred[:, :4].clone() # xyxy scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1]) # to original shape box = xyxy2xywh(box) # xywh box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner for p, b in zip(pred.tolist(), box.tolist()): jdict.append({ 'image_id': int(image_id) if image_id.isnumeric() else image_id, 'category_id': coco91class[int(p[5])], 'bbox': [round(x, 3) for x in b], 'score': round(p[4], 5) }) # Assign all predictions as incorrect correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device) if nl: detected = [] # target indices tcls_tensor = labels[:, 0] # target boxes tbox = xywh2xyxy(labels[:, 1:5]) * whwh # Per target class for cls in torch.unique(tcls_tensor): ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1) # prediction indices pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1) # target indices # Search for detections if pi.shape[0]: # Prediction to target ious ious, i = box_iou(pred[pi, :4], tbox[ti]).max(1) # best ious, indices # Append detections detected_set = set() for j in (ious > iouv[0]).nonzero(as_tuple=False): d = ti[i[j]] # detected target if d.item() not in detected_set: detected_set.add(d.item()) detected.append(d) correct[pi[j]] = ious[j] > iouv # iou_thres is 1xn if len(detected) == nl: # all targets already located in image break # Append statistics (correct, conf, pcls, tcls) stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # Plot images if plots and save_dir and batch_i < 1: f = save_dir / f'test_batch{batch_i}_gt.jpg' # filename plot_images(img, targets, paths, str(f), names) # ground truth f = save_dir / f'test_batch{batch_i}_pred.jpg' plot_images(img, output_to_target(output, width, height), paths, str(f), names) # predictions # Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, fname=os.path.join(save_dir, 'precision-recall_curve.png')) p, r, ap50, ap = p[:, 0], r[:, 0], ap[:, 0], ap.mean(1) # [P, R, [email protected], [email protected]:0.95] mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%12.3g' * 6 # print format print(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) # Print results per class if verbose and nc > 1 and len(stats): for i, c in enumerate(ap_class): print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple if not training: print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t) # Save JSON if save_json and len(jdict): w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else '' # weights file = save_dir / f"detections_val2017_{w}_results.json" # predicted annotations file print('\nCOCO mAP with pycocotools... saving %s...' % file) with open(file, 'w') as f: json.dump(jdict, f) try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files] cocoGt = COCO(glob.glob('../coco/annotations/instances_val*.json')[0]) # initialize COCO ground truth api cocoDt = cocoGt.loadRes(str(file)) # initialize COCO pred api cocoEval = COCOeval(cocoGt, cocoDt, 'bbox') cocoEval.params.imgIds = imgIds # image IDs to evaluate cocoEval.evaluate() cocoEval.accumulate() cocoEval.summarize() map, map50 = cocoEval.stats[:2] # update results ([email protected]:0.95, [email protected]) except Exception as e: print('ERROR: pycocotools unable to run: %s' % e) # Return results model.float() # for training maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def test_model(self, config, testset): # pylint: disable=unused-argument """The testing loop for YOLOv5. Arguments: config: Configuration parameters as a dictionary. testset: The test dataset. """ assert Config().data.datasource == 'YOLO' test_loader = yolo.DataSource.get_test_loader(config['batch_size'], testset) device = next(self.model.parameters()).device # get model device # Configure self.model.eval() with open(Config().data.data_params) as f: data = yaml.load(f, Loader=yaml.SafeLoader) # model dict check_dataset(data) # check nc = Config().data.num_classes # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() seen = 0 names = { k: v for k, v in enumerate(self.model.names if hasattr( self.model, 'names') else self.model.module.names) } s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', '[email protected]', '[email protected]:.95') dt, p, r, __, mp, mr, map50, map = [ 0.0, 0.0, 0.0 ], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 stats, ap = [], [] pbar = tqdm( test_loader, desc=s, ncols=NCOLS, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar for __, (img, targets, paths, shapes) in enumerate(pbar): t1 = time_sync() img = img.to(device, non_blocking=True).float() img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) __, __, height, width = img.shape # batch size, channels, height, width t2 = time_sync() dt[0] += t2 - t1 with torch.no_grad(): # Run model if Config().algorithm.type == 'mistnet': logits = self.model.forward_to(img) logits = logits.cpu().detach().numpy() logits = unary_encoding.encode(logits) logits = torch.from_numpy(logits.astype('float32')) out, __ = self.model.forward_from(logits.to(device)) else: out, __ = self.model(img) # Run NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = [] # for autolabelling out = non_max_suppression(out, conf_thres=0.001, iou_thres=0.6, labels=lb, multi_label=True) # Metrics for si, pred in enumerate(out): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class __, shape = Path(paths[si]), shapes[si][0] seen += 1 if len(pred) == 0: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Predictions predn = pred.clone() scale_coords(img[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred # Evaluate if nl: tbox = xywh2xyxy(labels[:, 1:5]) # target boxes scale_coords(img[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels correct = self.process_batch(predn, labelsn, iouv) else: correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool) stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # (correct, conf, pcls, tcls) # Compute metrics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): __, __, p, r, __, ap, __ = ap_per_class(*stats, plot=False, save_dir='', names=names) ap50, ap = ap[:, 0], ap.mean(1) # [email protected], [email protected]:0.95 mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format print(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) return map50
def test( data, weights=None, # model.pt path(s) batch_size=32, # batch size imgsz=640, # inference size (pixels) conf_thres=0.001, # confidence threshold iou_thres=0.6, # NMS IoU threshold task='val', # train, val, test, speed or study device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu single_cls=False, # treat as single-class dataset augment=False, # augmented inference verbose=False, # verbose output save_txt=False, # save results to *.txt save_hybrid=False, # save label+prediction hybrid results to *.txt save_conf=False, # save confidences in --save-txt labels save_json=False, # save a cocoapi-compatible JSON results file project='runs/test', # save to project/name name='exp', # save to project/name exist_ok=False, # existing project/name ok, do not increment half=True, # use FP16 half-precision inference model=None, dataloader=None, save_dir=Path(''), plots=True, wandb_logger=None, compute_loss=None, ): # Initialize/load model and set device training = model is not None if training: # called by train.py device = next(model.parameters()).device # get model device else: # called directly set_logging() device = select_device(device, batch_size=batch_size) # 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 model = attempt_load(weights, map_location=device) # load FP32 model gs = max(int(model.stride.max()), 32) # grid size (max stride) imgsz = check_img_size(imgsz, s=gs) # check image size # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99 # if device.type != 'cpu' and torch.cuda.device_count() > 1: # model = nn.DataParallel(model) # Half half &= device.type != 'cpu' # half precision only supported on CUDA if half: model.half() # Configure model.eval() if isinstance(data, str): with open(data) as f: data = yaml.safe_load(f) check_dataset(data) # check is_coco = data['val'].endswith('coco/val2017.txt') # COCO dataset nc = 1 if single_cls else int(data['nc']) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() # Logging log_imgs = 0 if wandb_logger and wandb_logger.wandb: log_imgs = min(wandb_logger.log_imgs, 100) # Dataloader if not training: if device.type != 'cpu': model( torch.zeros(1, 3, imgsz, imgsz).to(device).type_as( next(model.parameters()))) # run once task = task if task in ( 'train', 'val', 'test') else 'val' # path to train/val/test images dataloader = create_dataloader(data[task], imgsz, batch_size, gs, single_cls, pad=0.5, rect=True, prefix=colorstr(f'{task}: '))[0] seen = 0 confusion_matrix = ConfusionMatrix(nc=nc) names = { k: v for k, v in enumerate( model.names if hasattr(model, 'names') else model.module.names) } coco91class = coco80_to_coco91_class() s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', '[email protected]', '[email protected]:.95') p, r, f1, mp, mr, map50, map, t0, t1, t2 = 0., 0., 0., 0., 0., 0., 0., 0., 0., 0. loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class, wandb_images = [], [], [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): t_ = time_synchronized() img = img.to(device, non_blocking=True) img = img.half() if half else img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width t = time_synchronized() t0 += t - t_ # Run model out, train_out = model( img, augment=augment) # inference and training outputs t1 += time_synchronized() - t # Compute loss if compute_loss: loss += compute_loss([x.float() for x in train_out], targets)[1][:3] # box, obj, cls # Run NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling t = time_synchronized() out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) t2 += time_synchronized() - t # Statistics per image for si, pred in enumerate(out): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class path = Path(paths[si]) seen += 1 if len(pred) == 0: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Predictions if single_cls: pred[:, 5] = 0 predn = pred.clone() scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1]) # native-space pred # Append to text file if save_txt: gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0 ]] # normalization gain whwh for *xyxy, conf, cls in predn.tolist(): 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(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') # W&B logging - Media Panel plots if len( wandb_images ) < log_imgs and wandb_logger.current_epoch > 0: # Check for test operation if wandb_logger.current_epoch % wandb_logger.bbox_interval == 0: box_data = [{ "position": { "minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3] }, "class_id": int(cls), "box_caption": "%s %.3f" % (names[cls], conf), "scores": { "class_score": conf }, "domain": "pixel" } for *xyxy, conf, cls in pred.tolist()] boxes = { "predictions": { "box_data": box_data, "class_labels": names } } # inference-space wandb_images.append( wandb_logger.wandb.Image(img[si], boxes=boxes, caption=path.name)) wandb_logger.log_training_progress( predn, path, names) if wandb_logger and wandb_logger.wandb_run else None # Append to pycocotools JSON dictionary if save_json: # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ... image_id = int( path.stem) if path.stem.isnumeric() else path.stem box = xyxy2xywh(predn[:, :4]) # xywh box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner for p, b in zip(pred.tolist(), box.tolist()): jdict.append({ 'image_id': image_id, 'category_id': coco91class[int(p[5])] if is_coco else int(p[5]), 'bbox': [round(x, 3) for x in b], 'score': round(p[4], 5) }) # Assign all predictions as incorrect correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device) if nl: detected = [] # target indices tcls_tensor = labels[:, 0] # target boxes tbox = xywh2xyxy(labels[:, 1:5]) scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1]) # native-space labels if plots: confusion_matrix.process_batch( predn, torch.cat((labels[:, 0:1], tbox), 1)) # Per target class for cls in torch.unique(tcls_tensor): ti = (cls == tcls_tensor).nonzero(as_tuple=False).view( -1) # target indices pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view( -1) # prediction indices # Search for detections if pi.shape[0]: # Prediction to target ious ious, i = box_iou(predn[pi, :4], tbox[ti]).max( 1) # best ious, indices # Append detections detected_set = set() for j in (ious > iouv[0]).nonzero(as_tuple=False): d = ti[i[j]] # detected target if d.item() not in detected_set: detected_set.add(d.item()) detected.append(d) correct[ pi[j]] = ious[j] > iouv # iou_thres is 1xn if len( detected ) == nl: # all targets already located in image break # Append statistics (correct, conf, pcls, tcls) stats.append( (correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # Plot images if plots and batch_i < 3: f = save_dir / f'test_batch{batch_i}_labels.jpg' # labels Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start() f = save_dir / f'test_batch{batch_i}_pred.jpg' # predictions Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start() # Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names) ap50, ap = ap[:, 0], ap.mean(1) # [email protected], [email protected]:0.95 mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format print(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) # Print results per class if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats): for i, c in enumerate(ap_class): print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1E3 for x in (t0, t1, t2)) # speeds per image if not training: shape = (batch_size, 3, imgsz, imgsz) print( f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t) # Plots if plots: confusion_matrix.plot(save_dir=save_dir, names=list(names.values())) if wandb_logger and wandb_logger.wandb: val_batches = [ wandb_logger.wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg')) ] wandb_logger.log({"Validation": val_batches}) if wandb_images: wandb_logger.log({"Bounding Box Debugger/Images": wandb_images}) # Save JSON if save_json and len(jdict): w = Path(weights[0] if isinstance(weights, list) else weights ).stem if weights is not None else '' # weights anno_json = '../coco/annotations/instances_val2017.json' # annotations json pred_json = str(save_dir / f"{w}_predictions.json") # predictions json print('\nEvaluating pycocotools mAP... saving %s...' % pred_json) with open(pred_json, 'w') as f: json.dump(jdict, f) try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb check_requirements(['pycocotools']) from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval anno = COCO(anno_json) # init annotations api pred = anno.loadRes(pred_json) # init predictions api eval = COCOeval(anno, pred, 'bbox') if is_coco: eval.params.imgIds = [ int(Path(x).stem) for x in dataloader.dataset.img_files ] # image IDs to evaluate eval.evaluate() eval.accumulate() eval.summarize() map, map50 = eval.stats[: 2] # update results ([email protected]:0.95, [email protected]) except Exception as e: print(f'pycocotools unable to run: {e}') # Return results model.float() # for training if not training: 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}") maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16): # Plot image grid with labels if isinstance(images, torch.Tensor): images = images.cpu().float().numpy() if isinstance(targets, torch.Tensor): targets = targets.cpu().numpy() # un-normalise if np.max(images[0]) <= 1: images *= 255 tl = 3 # line thickness tf = max(tl - 1, 1) # font thickness bs, _, h, w = images.shape # batch size, _, height, width bs = min(bs, max_subplots) # limit plot images ns = np.ceil(bs**0.5) # number of subplots (square) # Check if we should resize scale_factor = max_size / max(h, w) if scale_factor < 1: h = math.ceil(scale_factor * h) w = math.ceil(scale_factor * w) colors = color_list() # list of colors mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init for i, img in enumerate(images): if i == max_subplots: # if last batch has fewer images than we expect break block_x = int(w * (i // ns)) block_y = int(h * (i % ns)) img = img.transpose(1, 2, 0) if scale_factor < 1: img = cv2.resize(img, (w, h)) mosaic[block_y:block_y + h, block_x:block_x + w, :] = img if len(targets) > 0: image_targets = targets[targets[:, 0] == i] boxes = xywh2xyxy(image_targets[:, 2:6]).T classes = image_targets[:, 1].astype('int') labels = image_targets.shape[1] == 6 # labels if no conf column conf = None if labels else image_targets[:, 6] # check for confidence presence (label vs pred) if boxes.shape[1]: if boxes.max() <= 1.01: # if normalized with tolerance 0.01 boxes[[0, 2]] *= w # scale to pixels boxes[[1, 3]] *= h elif scale_factor < 1: # absolute coords need scale if image scales boxes *= scale_factor boxes[[0, 2]] += block_x boxes[[1, 3]] += block_y for j, box in enumerate(boxes.T): cls = int(classes[j]) color = colors[cls % len(colors)] cls = names[cls] if names else cls if labels or conf[j] > 0.25: # 0.25 conf thresh label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j]) plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl) # Draw image filename labels if paths: label = Path(paths[i]).name[:40] # trim to 40 char t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf, lineType=cv2.LINE_AA) # Image border cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3) if fname: r = min(1280. / max(h, w) / ns, 1.0) # ratio to limit image size mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA) # cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB)) # cv2 save Image.fromarray(mosaic).save(fname) # PIL save return mosaic
def evaluate( data: Path, weights: Path, conf_threshold: float = None, batch_size: int = 256, img_size: int = 640, iou_thres: float = 0.6, ) -> None: """Evaluate model on dataset Args: data_dir: Dataset dir path weights: Path to model.pt conf_threshold: Confidence threshold batch_size: Batch size img_size: Inference size (pixels) iou_thres: Non-max supression IoU threshold """ device = select_device(batch_size=batch_size) # cuda | cpu save_dir = config_paths.temp_dir_path / "yolo" / "eval" / str(int(time())) save_dir.mkdir(parents=True) model = DetectMultiBackend(weights, device) model.model.float() model.eval() img_size = check_img_size(img_size, s=model.stride) # type:ignore model.warmup(imgsz=(1, 3, img_size, img_size)) metadata = pd.read_csv(data / "metadata.csv") dataloader = create_dataloader( data, img_size, batch_size, model.stride, single_cls=False, pad=0.5, rect=True, )[0] # Configure iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector 0.5:0.95 seen = 0 stats: List[ImgRes] = [] augmented_res = {} for batch_i, (im, targets, paths, shapes) in enumerate(tqdm(dataloader)): # Preprocess im = im.to(device, non_blocking=True) im = im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 *_, height, width = im.shape # batch size, channels, height, width # [Total targetx x 6] = Tensor[[img_index, class, ...xcycwh-rel]] targets = targets.to(device) # Inference out, _ = model(im, val=True) # inference, loss outputs # NMS # Out format (after NMS), sligthly unclear before NMS... # [Images x Predictions x [...xyxy-abs, conf, class]] # List[Tensor[Tensor[]]] # Looks like bboxes are in xyxy-abs format out = non_max_suppression(prediction=out, conf_thres=0.001, iou_thres=iou_thres) targets[:, 2:] *= torch.Tensor([width, height, width, height]).to( device) # to pixels i.e. Tensor[img_index, class, ...xcycwh-abs] # Metrics # Pred: Tensor[Predictions x [...xyxy-abs, conf class]] for si, pred in enumerate(out): # for each image seen += 1 path = Path(paths[si]) # path to img, shape = shapes[si][0] # original img dimensions # Labels: Each target where image_index matches current index excluding image_index col # i.e. all targets in current image [Targets x [class, ...xcyxcwh-abs]] labels = targets[targets[:, 0] == si, 1:] # target class, one entry for each labeled object labelsn = torch.Tensor() if len(labels): tbox = xywh2xyxy(labels[:, 1:5]) # target boxes [xyxy-abs] scale_coords(im[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels predn = pred.clone() if len(pred): # Predictions # native-space pred # bbox was predicted on rescaled image (i.e. multiple of 32) # now we scale the predicted bbox to match the orignal image shape scale_coords(im[si].shape[1:], predn[:, :4], shape, shapes[si][1]) img_res = evaluate_single_img(labelsn, predn, iouv) if img_res is not None: stats.append(img_res) append_augmented_img_res(augmented_res, path, metadata, labelsn, predn, img_res) # Plot prediction examples if batch_i < 3: plot_batch_predictions(batch_i, save_dir, im, targets, out, paths) augmented_res_df = pd.DataFrame.from_dict(augmented_res, orient="index") augmented_res_df.sort_values(by=["run_id", "frame_index"], inplace=True) augmented_res_df.reset_index(inplace=True, drop=True) augmented_res_df.to_pickle(save_dir / f"{data.stem}-augmented-res.pkl") results_by_slice(augmented_res_df, save_dir, conf_threshold)