Source code for src.yolov5.utils.general

# YOLOv5 general utils

import glob
import logging
import math
import os
import platform
import random
import re
import subprocess
import time
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path

import cv2
import numpy as np
import pandas as pd
import pkg_resources as pkg
import torch
import torchvision
import yaml

from yolov5.utils.google_utils import gsutil_getsize
from yolov5.utils.metrics import fitness
from yolov5.utils.torch_utils import init_torch_seeds

# Settings
torch.set_printoptions(linewidth=320, precision=5, profile='long')
# format short g, %precision=5
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})
pd.options.display.max_columns = 10
# prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
cv2.setNumThreads(0)
os.environ['NUMEXPR_MAX_THREADS'] = str(
    min(os.cpu_count(), 8))  # NumExpr max threads


[docs]def set_logging(rank=-1, verbose=True): logging.basicConfig( format="%(message)s", level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
[docs]def init_seeds(seed=0): # Initialize random number generator (RNG) seeds random.seed(seed) np.random.seed(seed) init_torch_seeds(seed)
[docs]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 ''
[docs]def is_docker(): # Is environment a Docker container return Path('/workspace').exists() # or Path('/.dockerenv').exists()
[docs]def is_colab(): # Is environment a Google Colab instance try: import google.colab return True except Exception as e: return False
[docs]def emojis(str=''): # Return platform-dependent emoji-safe version of string return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
[docs]def file_size(file): # Return file size in MB return Path(file).stat().st_size / 1e6
[docs]def check_online(): # Check internet connectivity import socket try: # check host accesability socket.create_connection(("1.1.1.1", 443), 5) return True except OSError: return False
[docs]def check_git_status(): # Recommend 'git pull' if code is out of date print(colorstr('github: '), end='') try: assert Path('.git').exists(), 'skipping check (not a git repository)' assert not is_docker(), 'skipping check (Docker image)' assert check_online(), 'skipping check (offline)' cmd = 'git fetch && git config --get remote.origin.url' url = subprocess.check_output(cmd, shell=True).decode( ).strip().rstrip('.git') # github repo url branch = subprocess.check_output( 'git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out n = int(subprocess.check_output( f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind if n > 0: s = f"⚠️ WARNING: code is out of date by {n} commit{'s' * (n > 1)}. " \ f"Use 'git pull' to update or 'git clone {url}' to download latest." else: s = f'up to date with {url} ✅' print(emojis(s)) # emoji-safe except Exception as e: print(e)
[docs]def check_python(minimum='3.7.0', required=True): # Check current python version vs. required python version current = platform.python_version() result = pkg.parse_version(current) >= pkg.parse_version(minimum) if required: assert result, f'Python {minimum} required by YOLOv5, but Python {current} is currently installed' return result
[docs]def check_requirements(requirements='requirements.txt', exclude=()): # Check installed dependencies meet requirements (pass *.txt file or list of packages) prefix = colorstr('red', 'bold', 'requirements:') check_python() # check python version if isinstance(requirements, (str, Path)): # requirements.txt file file = Path(requirements) if not file.exists(): print(f"{prefix} {file.resolve()} not found, check failed.") return requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements( file.open()) if x.name not in exclude] else: # list or tuple of packages requirements = [x for x in requirements if x not in exclude] n = 0 # number of packages updates for r in requirements: try: pkg.require(r) except Exception as e: # DistributionNotFound or VersionConflict if requirements not met n += 1 print( f"{prefix} {r} not found and is required by YOLOv5, attempting auto-update...") try: print(subprocess.check_output( f"pip install '{r}'", shell=True).decode()) except Exception as e: print(f'{prefix} {e}') if n: # if packages updated source = file.resolve() if 'file' in locals() else requirements s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \ f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n" print(emojis(s)) # emoji-safe
[docs]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
[docs]def check_imshow(): # Check if environment supports image displays try: assert not is_docker(), 'cv2.imshow() is disabled in Docker environments' assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments' cv2.imshow('test', np.zeros((1, 1, 3))) cv2.waitKey(1) cv2.destroyAllWindows() cv2.waitKey(1) return True except Exception as e: print( f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}') return False
[docs]def check_file(file): # Search/download file (if necessary) and return path file = str(file) # convert to str() if Path(file).is_file() or file == '': # exists return file elif file.startswith(('http://', 'https://')): # download url, file = file, Path(file).name print(f'Downloading {url} to {file}...') torch.hub.download_url_to_file(url, file) assert Path(file).exists() and Path(file).stat( ).st_size > 0, f'File download failed: {url}' # check return file else: # search files = glob.glob('./**/' + file, recursive=True) # find file assert len(files), f'File not found: {file}' # assert file was found # assert unique assert len( files) == 1, f"Multiple files match '{file}', specify exact path: {files}" return files[0] # return file
[docs]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 if s.startswith('http') and s.endswith('.zip'): # URL f = Path(s).name # filename print(f'Downloading {s} ...') torch.hub.download_url_to_file(s, f) r = os.system(f'unzip -q {f} -d ../ && rm {f}') # unzip elif s.startswith('bash '): # bash script print(f'Running {s} ...') r = os.system(s) else: # python script r = exec(s) # return None print('Dataset autodownload %s\n' % ( 'success' if r in (0, None) else 'failure')) # print result else: raise Exception('Dataset not found.')
[docs]def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1): # Multi-threaded file download and unzip function def download_one(url, dir): # Download 1 file f = dir / Path(url).name # filename if not f.exists(): print(f'Downloading {url} to {f}...') if curl: # curl download, retry and resume on fail os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -") else: torch.hub.download_url_to_file( url, f, progress=True) # torch download if unzip and f.suffix in ('.zip', '.gz'): print(f'Unzipping {f}...') if f.suffix == '.zip': # unzip -quiet -overwrite s = f'unzip -qo {f} -d {dir} && rm {f}' elif f.suffix == '.gz': s = f'tar xfz {f} --directory {f.parent}' # unzip if delete: # delete zip file after unzip s += f' && rm {f}' os.system(s) dir = Path(dir) dir.mkdir(parents=True, exist_ok=True) # make directory if threads > 1: pool = ThreadPool(threads) pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multi-threaded pool.close() pool.join() else: for u in tuple(url) if isinstance(url, str) else url: download_one(u, dir)
[docs]def make_divisible(x, divisor): # Returns x evenly divisible by divisor return math.ceil(x / divisor) * divisor
[docs]def clean_str(s): # Cleans a string by replacing special characters with underscore _ return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
[docs]def one_cycle(y1=0.0, y2=1.0, steps=100): # lambda function for sinusoidal ramp from y1 to y2 return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
[docs]def colorstr(*input): # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world') # color arguments, string *args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) colors = {'black': '\033[30m', # basic colors 'red': '\033[31m', 'green': '\033[32m', 'yellow': '\033[33m', 'blue': '\033[34m', 'magenta': '\033[35m', 'cyan': '\033[36m', 'white': '\033[37m', 'bright_black': '\033[90m', # bright colors 'bright_red': '\033[91m', 'bright_green': '\033[92m', 'bright_yellow': '\033[93m', 'bright_blue': '\033[94m', 'bright_magenta': '\033[95m', 'bright_cyan': '\033[96m', 'bright_white': '\033[97m', 'end': '\033[0m', # misc 'bold': '\033[1m', 'underline': '\033[4m'} return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
[docs]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)
[docs]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
[docs]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
[docs]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
[docs]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
[docs]def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): # Convert nx4 boxes from [x, y, w, h] normalized 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] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y return y
[docs]def xyn2xy(x, w=640, h=640, padw=0, padh=0): # Convert normalized segments into pixel segments, shape (n,2) y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) y[:, 0] = w * x[:, 0] + padw # top left x y[:, 1] = h * x[:, 1] + padh # top left y return y
[docs]def segment2box(segment, width=640, height=640): # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy) x, y = segment.T # segment xy inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height) x, y, = x[inside], y[inside] # xyxy return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4))
[docs]def segments2boxes(segments): # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh) boxes = [] for s in segments: x, y = s.T # segment xy boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy return xyxy2xywh(np.array(boxes)) # cls, xywh
[docs]def resample_segments(segments, n=1000): # Up-sample an (n,2) segment for i, s in enumerate(segments): x = np.linspace(0, len(s) - 1, n) xp = np.arange(len(s)) segments[i] = np.concatenate( [np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy return segments
[docs]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
[docs]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
[docs]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: # convex (smallest enclosing box) width cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) 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
[docs]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) # iou = inter / (area1 + area2 - inter) return inter / (area1[:, None] + area2 - inter)
[docs]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] # iou = inter / (area1 + area2 - inter) return inter / (wh1.prod(2) + wh2.prod(2) - inter)
[docs]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 Returns: list of detections, on (n,6) tensor per image [xyxy, conf, cls] """ nc = prediction.shape[2] - 5 # number of classes xc = prediction[..., 4] > conf_thres # candidates # Checks assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0' assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0' # Settings # (pixels) minimum and maximum box width and height min_wh, max_wh = 2, 4096 max_nms = 30000 # maximum number of boxes into torchvision.ops.nms() 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), device=prediction.device) ] * 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 is not None: 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)] # Check shape n = x.shape[0] # number of boxes if not n: # no boxes continue elif n > max_nms: # excess boxes # sort by confidence x = x[x[:, 4].argsort(descending=True)[:max_nms]] # Batched NMS c = x[:, 5:6] * (0 if agnostic else max_wh) # classes # boxes (offset by class), scores boxes, scores = x[:, :4] + c, x[:, 4] 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: print(f'WARNING: NMS time limit {time_limit}s exceeded') break # time limit exceeded return output
# from utils.general import *; strip_optimizer()
[docs]def strip_optimizer(f='best.pt', s=''): # Strip optimizer from 'f' to finalize training, optionally save as 's' x = torch.load(f, map_location=torch.device('cpu')) if x.get('ema'): x['model'] = x['ema'] # replace model with ema for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys x[k] = 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( f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
[docs]def apply_classifier(x, model, img, im0): # Apply 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) # BGR to RGB, to 3x416x416 im = im[:, :, ::-1].transpose(2, 0, 1) 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 # retain matching class detections x[i] = x[i][pred_cls1 == pred_cls2] return x
[docs]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: cv2.imwrite( str(increment_path(file, mkdir=True).with_suffix('.jpg')), crop) return crop
[docs]def increment_path(path, exist_ok=False, sep='', mkdir=False): # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. path = Path(path) # os-agnostic if path.exists() and not exist_ok: suffix = path.suffix path = path.with_suffix('') 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 path = Path(f"{path}{sep}{n}{suffix}") # update path dir = path if path.suffix == '' else path.parent # directory if not dir.exists() and mkdir: dir.mkdir(parents=True, exist_ok=True) # make directory return path