From ce9a79203f88e9a3956f12163f70ce45f6df7eef Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Tue, 29 Jun 2021 13:13:40 +0200 Subject: [PATCH] Move IoU functions to metrics.py --- utils/general.py | 80 +--------------------------------------------- utils/loss.py | 2 +- utils/metrics.py | 83 ++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 82 insertions(+), 83 deletions(-) diff --git a/utils/general.py b/utils/general.py index 83eb95744678..4606a8ec54f5 100755 --- a/utils/general.py +++ b/utils/general.py @@ -25,7 +25,7 @@ import yaml from utils.google_utils import gsutil_getsize -from utils.metrics import fitness +from utils.metrics import box_iou, fitness from utils.torch_utils import init_torch_seeds # Settings @@ -469,84 +469,6 @@ def clip_coords(boxes, img_shape): boxes[:, 3].clip(0, img_shape[0], out=boxes[:, 3]) # y2 -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 - - # 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 - - # 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 = inter / union - if GIoU or DIoU or CIoU: - 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 - if DIoU: - return iou - rho2 / c2 # DIoU - elif 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(): - alpha = v / (v - iou + (1 + eps)) - return iou - (rho2 / c2 + v * alpha) # CIoU - else: # GIoU https://arxiv.org/pdf/1902.09630.pdf - c_area = cw * ch + eps # convex area - return iou - (c_area - union) / c_area # GIoU - else: - return iou # IoU - - -def box_iou(box1, box2): - # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py - """ - Return intersection-over-union (Jaccard index) of boxes. - Both sets of boxes are expected to be in (x1, y1, x2, y2) format. - Arguments: - box1 (Tensor[N, 4]) - box2 (Tensor[M, 4]) - Returns: - iou (Tensor[N, M]): the NxM matrix containing the pairwise - 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) - - -def wh_iou(wh1, wh2): - # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 - wh1 = wh1[:, None] # [N,1,2] - wh2 = wh2[None] # [1,M,2] - inter = torch.min(wh1, wh2).prod(2) # [N,M] - return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter) - - def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False, labels=(), max_det=300): """Runs Non-Maximum Suppression (NMS) on inference results diff --git a/utils/loss.py b/utils/loss.py index d4c261a5cc97..88f57693307c 100644 --- a/utils/loss.py +++ b/utils/loss.py @@ -3,7 +3,7 @@ import torch import torch.nn as nn -from utils.general import bbox_iou +from utils.metrics import bbox_iou from utils.torch_utils import is_parallel diff --git a/utils/metrics.py b/utils/metrics.py index 8512197956e7..4f001c046285 100644 --- a/utils/metrics.py +++ b/utils/metrics.py @@ -1,5 +1,6 @@ # Model validation metrics +import math import warnings from pathlib import Path @@ -7,8 +8,6 @@ import numpy as np import torch -from . import general - def fitness(x): # Model fitness as a weighted combination of metrics @@ -128,7 +127,7 @@ def process_batch(self, detections, labels): detections = detections[detections[:, 4] > self.conf] gt_classes = labels[:, 0].int() detection_classes = detections[:, 5].int() - iou = general.box_iou(labels[:, 1:], detections[:, :4]) + iou = box_iou(labels[:, 1:], detections[:, :4]) x = torch.where(iou > self.iou_thres) if x[0].shape[0]: @@ -184,6 +183,84 @@ 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 + + # 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 + + # 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 = inter / union + if GIoU or DIoU or CIoU: + 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 + if DIoU: + return iou - rho2 / c2 # DIoU + elif 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(): + alpha = v / (v - iou + (1 + eps)) + return iou - (rho2 / c2 + v * alpha) # CIoU + else: # GIoU https://arxiv.org/pdf/1902.09630.pdf + c_area = cw * ch + eps # convex area + return iou - (c_area - union) / c_area # GIoU + else: + return iou # IoU + + +def box_iou(box1, box2): + # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py + """ + Return intersection-over-union (Jaccard index) of boxes. + Both sets of boxes are expected to be in (x1, y1, x2, y2) format. + Arguments: + box1 (Tensor[N, 4]) + box2 (Tensor[M, 4]) + Returns: + iou (Tensor[N, M]): the NxM matrix containing the pairwise + 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) + + +def wh_iou(wh1, wh2): + # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 + wh1 = wh1[:, None] # [N,1,2] + wh2 = wh2[None] # [1,M,2] + inter = torch.min(wh1, wh2).prod(2) # [N,M] + return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter) + + # Plots ---------------------------------------------------------------------------------------------------------------- def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):