Module heyvi.model.yolov5.utils.general
Expand source code Browse git
# General utils
import glob
import logging
import os
import platform
import random
import re
import subprocess
import time
from pathlib import Path
#import cv2
import math
import numpy as np
import torch
import torchvision
import yaml
from heyvi.model.yolov5.utils.google_utils import gsutil_getsize
from heyvi.model.yolov5.utils.metrics import fitness
from heyvi.model.yolov5.utils.torch_utils import init_torch_seeds
# Settings
#torch.set_printoptions(linewidth=320, precision=5, profile='long')
#np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
#cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
def set_logging(rank=-1):
logging.basicConfig(
format="%(message)s",
level=logging.INFO if rank in [-1, 0] else logging.WARN)
def init_seeds(seed=0):
random.seed(seed)
np.random.seed(seed)
init_torch_seeds(seed)
def get_latest_run(search_dir='.'):
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
return max(last_list, key=os.path.getctime) if last_list else ''
def check_git_status():
# Suggest 'git pull' if repo is out of date
if platform.system() in ['Linux', 'Darwin'] and not os.path.isfile('/.dockerenv'):
s = subprocess.check_output('if [ -d .git ]; then git fetch && git status -uno; fi', shell=True).decode('utf-8')
if 'Your branch is behind' in s:
print(s[s.find('Your branch is behind'):s.find('\n\n')] + '\n')
def check_img_size(img_size, s=32):
# Verify img_size is a multiple of stride s
new_size = make_divisible(img_size, int(s)) # ceil gs-multiple
if new_size != img_size:
print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
return new_size
def check_file(file):
# Search for file if not found
if os.path.isfile(file) or file == '':
return file
else:
files = glob.glob('./**/' + file, recursive=True) # find file
assert len(files), 'File Not Found: %s' % file # assert file was found
assert len(files) == 1, "Multiple files match '%s', specify exact path: %s" % (file, files) # assert unique
return files[0] # return file
def check_dataset(dict):
# Download dataset if not found locally
val, s = dict.get('val'), dict.get('download')
if val and len(val):
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
if not all(x.exists() for x in val):
print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
if s and len(s): # download script
print('Downloading %s ...' % s)
if s.startswith('http') and s.endswith('.zip'): # URL
f = Path(s).name # filename
torch.hub.download_url_to_file(s, f)
r = os.system('unzip -q %s -d ../ && rm %s' % (f, f)) # unzip
else: # bash script
r = os.system(s)
print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure')) # analyze return value
else:
raise Exception('Dataset not found.')
def make_divisible(x, divisor):
# Returns x evenly divisible by divisor
return math.ceil(x / divisor) * divisor
def labels_to_class_weights(labels, nc=80):
# Get class weights (inverse frequency) from training labels
if labels[0] is None: # no labels loaded
return torch.Tensor()
labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
classes = labels[:, 0].astype(np.int) # labels = [class xywh]
weights = np.bincount(classes, minlength=nc) # occurrences per class
# Prepend gridpoint count (for uCE training)
# gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image
# weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start
weights[weights == 0] = 1 # replace empty bins with 1
weights = 1 / weights # number of targets per class
weights /= weights.sum() # normalize
return torch.from_numpy(weights)
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
# Produces image weights based on class_weights and image contents
class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
# index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
return image_weights
def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper)
# https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
# a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
# b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
# x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
# x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
return x
def xyxy2xywh(x):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
y[:, 2] = x[:, 2] - x[:, 0] # width
y[:, 3] = x[:, 3] - x[:, 1] # height
return y
def xywh2xyxy(x):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
return y
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
# Rescale coords (xyxy) from img1_shape to img0_shape
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
coords[:, [0, 2]] -= pad[0] # x padding
coords[:, [1, 3]] -= pad[1] # y padding
coords[:, :4] /= gain
clip_coords(coords, img0_shape)
return coords
def clip_coords(boxes, img_shape):
# Clip bounding xyxy bounding boxes to image shape (height, width)
boxes[:, 0].clamp_(0, img_shape[1]) # x1
boxes[:, 1].clamp_(0, img_shape[0]) # y1
boxes[:, 2].clamp_(0, img_shape[1]) # x2
boxes[:, 3].clamp_(0, img_shape[0]) # y2
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-9):
# 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 / ((1 + eps) - iou + v)
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=0.1, iou_thres=0.6, classes=None, agnostic=False, labels=()):
"""Performs Non-Maximum Suppression (NMS) on inference results
Returns:
detections with shape: nx6 (x1, y1, x2, y2, conf, cls)
"""
nc = prediction[0].shape[1] - 5 # number of classes
xc = prediction[..., 4] > conf_thres # candidates
# Settings
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
max_det = 300 # maximum number of detections per image
time_limit = 10.0 # seconds to quit after
redundant = True # require redundant detections
multi_label = nc > 1 # multiple labels per box (adds 0.5ms/img)
merge = False # use merge-NMS
t = time.time()
output = [torch.zeros(0, 6)] * prediction.shape[0]
for xi, x in enumerate(prediction): # image index, image inference
# Apply constraints
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
x = x[xc[xi]] # confidence
# Cat apriori labels if autolabelling
if labels and len(labels[xi]):
l = labels[xi]
v = torch.zeros((len(l), nc + 5), device=x.device)
v[:, :4] = l[:, 1:5] # box
v[:, 4] = 1.0 # conf
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
x = torch.cat((x, v), 0)
# If none remain process next image
if not x.shape[0]:
continue
# Compute conf
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
box = xywh2xyxy(x[:, :4])
# Detections matrix nx6 (xyxy, conf, cls)
if multi_label:
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
else: # best class only
conf, j = x[:, 5:].max(1, keepdim=True)
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
# Filter by class
if classes:
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
# Apply finite constraint
# if not torch.isfinite(x).all():
# x = x[torch.isfinite(x).all(1)]
# If none remain process next image
n = x.shape[0] # number of boxes
if not n:
continue
# Sort by confidence
# x = x[x[:, 4].argsort(descending=True)]
# Batched NMS
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
if i.shape[0] > max_det: # limit detections
i = i[:max_det]
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
weights = iou * scores[None] # box weights
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
if redundant:
i = i[iou.sum(1) > 1] # require redundancy
output[xi] = x[i]
if (time.time() - t) > time_limit:
break # time limit exceeded
return output
def strip_optimizer(f='weights/best.pt', s=''): # from utils.general import *; strip_optimizer()
# Strip optimizer from 'f' to finalize training, optionally save as 's'
x = torch.load(f, map_location=torch.device('cpu'))
x['optimizer'] = None
x['training_results'] = None
x['epoch'] = -1
x['model'].half() # to FP16
for p in x['model'].parameters():
p.requires_grad = False
torch.save(x, s or f)
mb = os.path.getsize(s or f) / 1E6 # filesize
print('Optimizer stripped from %s,%s %.1fMB' % (f, (' saved as %s,' % s) if s else '', mb))
def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
# Print mutation results to evolve.txt (for use with train.py --evolve)
a = '%10s' * len(hyp) % tuple(hyp.keys()) # hyperparam keys
b = '%10.3g' * len(hyp) % tuple(hyp.values()) # hyperparam values
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c))
if bucket:
url = 'gs://%s/evolve.txt' % bucket
if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0):
os.system('gsutil cp %s .' % url) # download evolve.txt if larger than local
with open('evolve.txt', 'a') as f: # append result
f.write(c + b + '\n')
x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0) # load unique rows
x = x[np.argsort(-fitness(x))] # sort
np.savetxt('evolve.txt', x, '%10.3g') # save sort by fitness
# Save yaml
for i, k in enumerate(hyp.keys()):
hyp[k] = float(x[0, i + 7])
with open(yaml_file, 'w') as f:
results = tuple(x[0, :7])
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
yaml.dump(hyp, f, sort_keys=False)
if bucket:
os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket)) # upload
def apply_classifier(x, model, img, im0):
import cv2
# applies a second stage classifier to yolo outputs
im0 = [im0] if isinstance(im0, np.ndarray) else im0
for i, d in enumerate(x): # per image
if d is not None and len(d):
d = d.clone()
# Reshape and pad cutouts
b = xyxy2xywh(d[:, :4]) # boxes
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square
b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad
d[:, :4] = xywh2xyxy(b).long()
# Rescale boxes from img_size to im0 size
scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
# Classes
pred_cls1 = d[:, 5].long()
ims = []
for j, a in enumerate(d): # per item
cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
im = cv2.resize(cutout, (224, 224)) # BGR
# cv2.imwrite('test%i.jpg' % j, cutout)
im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
im /= 255.0 # 0 - 255 to 0.0 - 1.0
ims.append(im)
pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections
return x
def increment_path(path, exist_ok=True, sep=''):
# Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc.
path = Path(path) # os-agnostic
if (path.exists() and exist_ok) or (not path.exists()):
return str(path)
else:
dirs = glob.glob(f"{path}{sep}*") # similar paths
matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
i = [int(m.groups()[0]) for m in matches if m] # indices
n = max(i) + 1 if i else 2 # increment number
return f"{path}{sep}{n}" # update path
Functions
def apply_classifier(x, model, img, im0)
-
Expand source code Browse git
def apply_classifier(x, model, img, im0): import cv2 # applies a second stage classifier to yolo outputs im0 = [im0] if isinstance(im0, np.ndarray) else im0 for i, d in enumerate(x): # per image if d is not None and len(d): d = d.clone() # Reshape and pad cutouts b = xyxy2xywh(d[:, :4]) # boxes b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad d[:, :4] = xywh2xyxy(b).long() # Rescale boxes from img_size to im0 size scale_coords(img.shape[2:], d[:, :4], im0[i].shape) # Classes pred_cls1 = d[:, 5].long() ims = [] for j, a in enumerate(d): # per item cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])] im = cv2.resize(cutout, (224, 224)) # BGR # cv2.imwrite('test%i.jpg' % j, cutout) im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32 im /= 255.0 # 0 - 255 to 0.0 - 1.0 ims.append(im) pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections return x
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-09)
-
Expand source code Browse git
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-9): # 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 / ((1 + eps) - iou + v) 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)
-
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
Expand source code Browse git
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 check_dataset(dict)
-
Expand source code Browse git
def check_dataset(dict): # Download dataset if not found locally val, s = dict.get('val'), dict.get('download') if val and len(val): val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path if not all(x.exists() for x in val): print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()]) if s and len(s): # download script print('Downloading %s ...' % s) if s.startswith('http') and s.endswith('.zip'): # URL f = Path(s).name # filename torch.hub.download_url_to_file(s, f) r = os.system('unzip -q %s -d ../ && rm %s' % (f, f)) # unzip else: # bash script r = os.system(s) print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure')) # analyze return value else: raise Exception('Dataset not found.')
def check_file(file)
-
Expand source code Browse git
def check_file(file): # Search for file if not found if os.path.isfile(file) or file == '': return file else: files = glob.glob('./**/' + file, recursive=True) # find file assert len(files), 'File Not Found: %s' % file # assert file was found assert len(files) == 1, "Multiple files match '%s', specify exact path: %s" % (file, files) # assert unique return files[0] # return file
def check_git_status()
-
Expand source code Browse git
def check_git_status(): # Suggest 'git pull' if repo is out of date if platform.system() in ['Linux', 'Darwin'] and not os.path.isfile('/.dockerenv'): s = subprocess.check_output('if [ -d .git ]; then git fetch && git status -uno; fi', shell=True).decode('utf-8') if 'Your branch is behind' in s: print(s[s.find('Your branch is behind'):s.find('\n\n')] + '\n')
def check_img_size(img_size, s=32)
-
Expand source code Browse git
def check_img_size(img_size, s=32): # Verify img_size is a multiple of stride s new_size = make_divisible(img_size, int(s)) # ceil gs-multiple if new_size != img_size: print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size)) return new_size
def clip_coords(boxes, img_shape)
-
Expand source code Browse git
def clip_coords(boxes, img_shape): # Clip bounding xyxy bounding boxes to image shape (height, width) boxes[:, 0].clamp_(0, img_shape[1]) # x1 boxes[:, 1].clamp_(0, img_shape[0]) # y1 boxes[:, 2].clamp_(0, img_shape[1]) # x2 boxes[:, 3].clamp_(0, img_shape[0]) # y2
def coco80_to_coco91_class()
-
Expand source code Browse git
def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper) # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/ # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n') # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n') # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90] return x
def get_latest_run(search_dir='.')
-
Expand source code Browse git
def get_latest_run(search_dir='.'): # Return path to most recent 'last.pt' in /runs (i.e. to --resume from) last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True) return max(last_list, key=os.path.getctime) if last_list else ''
def increment_path(path, exist_ok=True, sep='')
-
Expand source code Browse git
def increment_path(path, exist_ok=True, sep=''): # Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc. path = Path(path) # os-agnostic if (path.exists() and exist_ok) or (not path.exists()): return str(path) else: dirs = glob.glob(f"{path}{sep}*") # similar paths matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs] i = [int(m.groups()[0]) for m in matches if m] # indices n = max(i) + 1 if i else 2 # increment number return f"{path}{sep}{n}" # update path
def init_seeds(seed=0)
-
Expand source code Browse git
def init_seeds(seed=0): random.seed(seed) np.random.seed(seed) init_torch_seeds(seed)
def labels_to_class_weights(labels, nc=80)
-
Expand source code Browse git
def labels_to_class_weights(labels, nc=80): # Get class weights (inverse frequency) from training labels if labels[0] is None: # no labels loaded return torch.Tensor() labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO classes = labels[:, 0].astype(np.int) # labels = [class xywh] weights = np.bincount(classes, minlength=nc) # occurrences per class # Prepend gridpoint count (for uCE training) # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image # weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start weights[weights == 0] = 1 # replace empty bins with 1 weights = 1 / weights # number of targets per class weights /= weights.sum() # normalize return torch.from_numpy(weights)
def labels_to_image_weights(labels, nc=80, class_weights=array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]))
-
Expand source code Browse git
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)): # Produces image weights based on class_weights and image contents class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels]) image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1) # index = random.choices(range(n), weights=image_weights, k=1) # weight image sample return image_weights
def make_divisible(x, divisor)
-
Expand source code Browse git
def make_divisible(x, divisor): # Returns x evenly divisible by divisor return math.ceil(x / divisor) * divisor
def non_max_suppression(prediction, conf_thres=0.1, iou_thres=0.6, classes=None, agnostic=False, labels=())
-
Performs Non-Maximum Suppression (NMS) on inference results
Returns
detections with shape
- nx6 (x1, y1, x2, y2, conf, cls)
Expand source code Browse git
def non_max_suppression(prediction, conf_thres=0.1, iou_thres=0.6, classes=None, agnostic=False, labels=()): """Performs Non-Maximum Suppression (NMS) on inference results Returns: detections with shape: nx6 (x1, y1, x2, y2, conf, cls) """ nc = prediction[0].shape[1] - 5 # number of classes xc = prediction[..., 4] > conf_thres # candidates # Settings min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height max_det = 300 # maximum number of detections per image time_limit = 10.0 # seconds to quit after redundant = True # require redundant detections multi_label = nc > 1 # multiple labels per box (adds 0.5ms/img) merge = False # use merge-NMS t = time.time() output = [torch.zeros(0, 6)] * prediction.shape[0] for xi, x in enumerate(prediction): # image index, image inference # Apply constraints # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height x = x[xc[xi]] # confidence # Cat apriori labels if autolabelling if labels and len(labels[xi]): l = labels[xi] v = torch.zeros((len(l), nc + 5), device=x.device) v[:, :4] = l[:, 1:5] # box v[:, 4] = 1.0 # conf v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls x = torch.cat((x, v), 0) # If none remain process next image if not x.shape[0]: continue # Compute conf x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf # Box (center x, center y, width, height) to (x1, y1, x2, y2) box = xywh2xyxy(x[:, :4]) # Detections matrix nx6 (xyxy, conf, cls) if multi_label: i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1) else: # best class only conf, j = x[:, 5:].max(1, keepdim=True) x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres] # Filter by class if classes: x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] # Apply finite constraint # if not torch.isfinite(x).all(): # x = x[torch.isfinite(x).all(1)] # If none remain process next image n = x.shape[0] # number of boxes if not n: continue # Sort by confidence # x = x[x[:, 4].argsort(descending=True)] # Batched NMS c = x[:, 5:6] * (0 if agnostic else max_wh) # classes boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS if i.shape[0] > max_det: # limit detections i = i[:max_det] if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean) # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix weights = iou * scores[None] # box weights x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes if redundant: i = i[iou.sum(1) > 1] # require redundancy output[xi] = x[i] if (time.time() - t) > time_limit: break # time limit exceeded return output
def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket='')
-
Expand source code Browse git
def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''): # Print mutation results to evolve.txt (for use with train.py --evolve) a = '%10s' * len(hyp) % tuple(hyp.keys()) # hyperparam keys b = '%10.3g' * len(hyp) % tuple(hyp.values()) # hyperparam values c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3) print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c)) if bucket: url = 'gs://%s/evolve.txt' % bucket if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0): os.system('gsutil cp %s .' % url) # download evolve.txt if larger than local with open('evolve.txt', 'a') as f: # append result f.write(c + b + '\n') x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0) # load unique rows x = x[np.argsort(-fitness(x))] # sort np.savetxt('evolve.txt', x, '%10.3g') # save sort by fitness # Save yaml for i, k in enumerate(hyp.keys()): hyp[k] = float(x[0, i + 7]) with open(yaml_file, 'w') as f: results = tuple(x[0, :7]) c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3) f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n') yaml.dump(hyp, f, sort_keys=False) if bucket: os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket)) # upload
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None)
-
Expand source code Browse git
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None): # Rescale coords (xyxy) from img1_shape to img0_shape if ratio_pad is None: # calculate from img0_shape gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding else: gain = ratio_pad[0][0] pad = ratio_pad[1] coords[:, [0, 2]] -= pad[0] # x padding coords[:, [1, 3]] -= pad[1] # y padding coords[:, :4] /= gain clip_coords(coords, img0_shape) return coords
def set_logging(rank=-1)
-
Expand source code Browse git
def set_logging(rank=-1): logging.basicConfig( format="%(message)s", level=logging.INFO if rank in [-1, 0] else logging.WARN)
def strip_optimizer(f='weights/best.pt', s='')
-
Expand source code Browse git
def strip_optimizer(f='weights/best.pt', s=''): # from utils.general import *; strip_optimizer() # Strip optimizer from 'f' to finalize training, optionally save as 's' x = torch.load(f, map_location=torch.device('cpu')) x['optimizer'] = None x['training_results'] = None x['epoch'] = -1 x['model'].half() # to FP16 for p in x['model'].parameters(): p.requires_grad = False torch.save(x, s or f) mb = os.path.getsize(s or f) / 1E6 # filesize print('Optimizer stripped from %s,%s %.1fMB' % (f, (' saved as %s,' % s) if s else '', mb))
def wh_iou(wh1, wh2)
-
Expand source code Browse git
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 xywh2xyxy(x)
-
Expand source code Browse git
def xywh2xyxy(x): # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y return y
def xyxy2xywh(x)
-
Expand source code Browse git
def xyxy2xywh(x): # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center y[:, 2] = x[:, 2] - x[:, 0] # width y[:, 3] = x[:, 3] - x[:, 1] # height return y