From 406ee528f0fb78e6f814b9a53765bc54183f0a0b Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sun, 10 Apr 2022 13:46:07 +0200 Subject: [PATCH] Loss and IoU speed improvements (#7361) * Loss speed improvements * bbox_iou speed improvements * bbox_ioa speed improvements * box_iou speed improvements * box_iou speed improvements --- utils/loss.py | 8 +++---- utils/metrics.py | 54 +++++++++++++++++++++++------------------------- val.py | 4 ++-- 3 files changed, 32 insertions(+), 34 deletions(-) diff --git a/utils/loss.py b/utils/loss.py index fa8095515477..b5d050e46047 100644 --- a/utils/loss.py +++ b/utils/loss.py @@ -138,7 +138,7 @@ def __call__(self, p, targets): # predictions, targets pxy = pxy.sigmoid() * 2 - 0.5 pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i] pbox = torch.cat((pxy, pwh), 1) # predicted box - iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) + iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target) lbox += (1.0 - iou).mean() # iou loss # Objectness @@ -180,7 +180,7 @@ def build_targets(self, p, targets): tcls, tbox, indices, anch = [], [], [], [] gain = torch.ones(7, device=self.device) # normalized to gridspace gain ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) - targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices + targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2) # append anchor indices g = 0.5 # bias off = torch.tensor( @@ -199,10 +199,10 @@ def build_targets(self, p, targets): gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain # Match targets to anchors - t = targets * gain + t = targets * gain # shape(3,n,7) if nt: # Matches - r = t[:, :, 4:6] / anchors[:, None] # wh ratio + r = t[..., 4:6] / anchors[:, None] # wh ratio j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) t = t[j] # filter diff --git a/utils/metrics.py b/utils/metrics.py index 0674beddc0fb..ff43a3073062 100644 --- a/utils/metrics.py +++ b/utils/metrics.py @@ -206,37 +206,36 @@ def print(self): print(' '.join(map(str, self.matrix[i]))) -def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): - # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4 - box2 = box2.T +def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): + # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4) # Get the coordinates of bounding boxes - if x1y1x2y2: # x1, y1, x2, y2 = box1 - b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] - b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] - else: # transform from xywh to xyxy - b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2 - b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2 - b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2 - b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2 + if xywh: # transform from xywh to xyxy + (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, 1), box2.chunk(4, 1) + w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2 + b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_ + b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_ + else: # x1, y1, x2, y2 = box1 + b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, 1) + b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, 1) + w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps + w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps # Intersection area inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \ (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0) # Union Area - w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps - w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps union = w1 * h1 + w2 * h2 - inter + eps + # IoU iou = inter / union if CIoU or DIoU or GIoU: cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared - rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + - (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared + rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center dist ** 2 if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) with torch.no_grad(): @@ -248,6 +247,11 @@ def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps= return iou # IoU +def box_area(box): + # box = xyxy(4,n) + return (box[2] - box[0]) * (box[3] - box[1]) + + def box_iou(box1, box2): # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py """ @@ -261,16 +265,12 @@ def box_iou(box1, box2): IoU values for every element in boxes1 and boxes2 """ - def box_area(box): - # box = 4xn - return (box[2] - box[0]) * (box[3] - box[1]) - - area1 = box_area(box1.T) - area2 = box_area(box2.T) - # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) - inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2) - return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter) + (a1, a2), (b1, b2) = box1[:, None].chunk(2, 2), box2.chunk(2, 1) + inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2) + + # IoU = inter / (area1 + area2 - inter) + return inter / (box_area(box1.T)[:, None] + box_area(box2.T) - inter) def bbox_ioa(box1, box2, eps=1E-7): @@ -280,11 +280,9 @@ def bbox_ioa(box1, box2, eps=1E-7): returns: np.array of shape(n) """ - box2 = box2.transpose() - # Get the coordinates of bounding boxes - b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] - b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] + b1_x1, b1_y1, b1_x2, b1_y2 = box1 + b2_x1, b2_y1, b2_x2, b2_y2 = box2.T # Intersection area inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ diff --git a/val.py b/val.py index 5841437051c2..36f2a6c0284b 100644 --- a/val.py +++ b/val.py @@ -38,10 +38,10 @@ from models.common import DetectMultiBackend from utils.callbacks import Callbacks from utils.datasets import create_dataloader -from utils.general import (LOGGER, box_iou, check_dataset, check_img_size, check_requirements, check_yaml, +from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_yaml, coco80_to_coco91_class, colorstr, increment_path, non_max_suppression, print_args, scale_coords, xywh2xyxy, xyxy2xywh) -from utils.metrics import ConfusionMatrix, ap_per_class +from utils.metrics import ConfusionMatrix, ap_per_class, box_iou from utils.plots import output_to_target, plot_images, plot_val_study from utils.torch_utils import select_device, time_sync