xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.93 HUB docs and JSON2YOLO converter (#2431)

Browse Source 
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: 李际朝 <tubkninght@gmail.com>
Co-authored-by: Danny Kim <imbird0312@gmail.com>
This commit is contained in:
Glenn Jocher
2023-05-06 01:12:43 +02:00
committed by GitHub
parent 0ebd3f2959
commit ddb354ce5e
34 changed files with 1107 additions and 759 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ultralytics/yolo/cfg/__init__.py
View File

@ -68,7 +68,7 @@ CFG_FRACTION_KEYS = ('dropout', 'iou', 'lr0', 'lrf', 'momentum', 'weight_decay',
'label_smoothing', 'hsv_h', 'hsv_s', 'hsv_v', 'translate', 'scale', 'perspective', 'flipud',
'fliplr', 'mosaic', 'mixup', 'copy_paste', 'conf', 'iou') # fractional floats limited to 0.0 - 1.0
CFG_INT_KEYS = ('epochs', 'patience', 'batch', 'workers', 'seed', 'close_mosaic', 'mask_ratio', 'max_det', 'vid_stride',
'line_thickness', 'workspace', 'nbs', 'save_period')
'line_width', 'workspace', 'nbs', 'save_period')
CFG_BOOL_KEYS = ('save', 'exist_ok', 'verbose', 'deterministic', 'single_cls', 'rect', 'cos_lr', 'overlap_mask', 'val',
'save_json', 'save_hybrid', 'half', 'dnn', 'plots', 'show', 'save_txt', 'save_conf', 'save_crop',
'show_labels', 'show_conf', 'visualize', 'augment', 'agnostic_nms', 'retina_masks', 'boxes', 'keras',
@ -152,6 +152,9 @@ def _handle_deprecation(custom):
if key == 'hide_conf':
deprecation_warn(key, 'show_conf')
custom['show_conf'] = custom.pop('hide_conf') == 'False'
if key == 'line_thickness':
deprecation_warn(key, 'line_width')
custom['line_width'] = custom.pop('line_thickness')
return custom

2
ultralytics/yolo/cfg/default.yaml
View File

@ -57,7 +57,7 @@ save_crop: False # save cropped images with results
show_labels: True # show object labels in plots
show_conf: True # show object confidence scores in plots
vid_stride: 1 # video frame-rate stride
line_thickness: 3 # bounding box thickness (pixels)
line_width: # line width of the bounding boxes
visualize: False # visualize model features
augment: False # apply image augmentation to prediction sources
agnostic_nms: False # class-agnostic NMS

35
ultralytics/yolo/data/annotator.py
View File

@ -8,7 +8,6 @@ from ultralytics.yolo.utils.torch_utils import select_device
def auto_annotate(data, det_model='yolov8x.pt', sam_model='sam_b.pt', device='', output_dir=None):
"""
Automatically annotates images using a YOLO object detection model and a SAM segmentation model.
Args:
data (str): Path to a folder containing images to be annotated.
det_model (str, optional): Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'.
@ -16,7 +15,6 @@ def auto_annotate(data, det_model='yolov8x.pt', sam_model='sam_b.pt', device='',
device (str, optional): Device to run the models on. Defaults to an empty string (CPU or GPU, if available).
output_dir (str, None, optional): Directory to save the annotated results.
Defaults to a 'labels' folder in the same directory as 'data'.
"""
device = select_device(device)
det_model = YOLO(det_model)
@ -34,21 +32,22 @@ def auto_annotate(data, det_model='yolov8x.pt', sam_model='sam_b.pt', device='',
for result in det_results:
boxes = result.boxes.xyxy # Boxes object for bbox outputs
class_ids = result.boxes.cls.int().tolist() # noqa
prompt_predictor.set_image(result.orig_img)
masks, _, _ = prompt_predictor.predict_torch(
point_coords=None,
point_labels=None,
boxes=prompt_predictor.transform.apply_boxes_torch(boxes, result.orig_shape[:2]),
multimask_output=False,
)
if len(class_ids):
prompt_predictor.set_image(result.orig_img)
masks, _, _ = prompt_predictor.predict_torch(
point_coords=None,
point_labels=None,
boxes=prompt_predictor.transform.apply_boxes_torch(boxes, result.orig_shape[:2]),
multimask_output=False,
)
result.update(masks=masks.squeeze(1))
segments = result.masks.xyn # noqa
result.update(masks=masks.squeeze(1))
segments = result.masks.xyn # noqa
with open(f'{str(Path(output_dir) / Path(result.path).stem)}.txt', 'w') as f:
for i in range(len(segments)):
s = segments[i]
if len(s) == 0:
continue
segment = map(str, segments[i].reshape(-1).tolist())
f.write(f'{class_ids[i]} ' + ' '.join(segment) + '\n')
with open(str(Path(output_dir) / Path(result.path).stem) + '.txt', 'w') as f:
for i in range(len(segments)):
s = segments[i]
if len(s) == 0:
continue
segment = map(str, segments[i].reshape(-1).tolist())
f.write(f'{class_ids[i]} ' + ' '.join(segment) + '\n')

230
ultralytics/yolo/data/converter.py Normal file
View File

@ -0,0 +1,230 @@
import json
from collections import defaultdict
from pathlib import Path
import cv2
import numpy as np
from tqdm import tqdm
from ultralytics.yolo.utils.checks import check_requirements
from ultralytics.yolo.utils.files import make_dirs
def coco91_to_coco80_class():
"""Converts 91-index COCO class IDs to 80-index COCO class IDs.
Returns:
(list): A list of 91 class IDs where the index represents the 80-index class ID and the value is the
corresponding 91-index class ID.
"""
return [
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, None, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, None, 24, 25, None,
None, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, None, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
51, 52, 53, 54, 55, 56, 57, 58, 59, None, 60, None, None, 61, None, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72,
None, 73, 74, 75, 76, 77, 78, 79, None]
def convert_coco(labels_dir='../coco/annotations/', use_segments=False, use_keypoints=False, cls91to80=True):
"""Converts COCO dataset annotations to a format suitable for training YOLOv5 models.
Args:
labels_dir (str, optional): Path to directory containing COCO dataset annotation files.
use_segments (bool, optional): Whether to include segmentation masks in the output.
use_keypoints (bool, optional): Whether to include keypoint annotations in the output.
cls91to80 (bool, optional): Whether to map 91 COCO class IDs to the corresponding 80 COCO class IDs.
Raises:
FileNotFoundError: If the labels_dir path does not exist.
Example Usage:
convert_coco(labels_dir='../coco/annotations/', use_segments=True, use_keypoints=True, cls91to80=True)
Output:
Generates output files in the specified output directory.
"""
save_dir = make_dirs('yolo_labels') # output directory
coco80 = coco91_to_coco80_class()
# Import json
for json_file in sorted(Path(labels_dir).resolve().glob('*.json')):
fn = Path(save_dir) / 'labels' / json_file.stem.replace('instances_', '') # folder name
fn.mkdir(parents=True, exist_ok=True)
with open(json_file) as f:
data = json.load(f)
# Create image dict
images = {'%g' % x['id']: x for x in data['images']}
# Create image-annotations dict
imgToAnns = defaultdict(list)
for ann in data['annotations']:
imgToAnns[ann['image_id']].append(ann)
# Write labels file
for img_id, anns in tqdm(imgToAnns.items(), desc=f'Annotations {json_file}'):
img = images['%g' % img_id]
h, w, f = img['height'], img['width'], img['file_name']
bboxes = []
segments = []
keypoints = []
for ann in anns:
if ann['iscrowd']:
continue
# The COCO box format is [top left x, top left y, width, height]
box = np.array(ann['bbox'], dtype=np.float64)
box[:2] += box[2:] / 2 # xy top-left corner to center
box[[0, 2]] /= w # normalize x
box[[1, 3]] /= h # normalize y
if box[2] <= 0 or box[3] <= 0: # if w <= 0 and h <= 0
continue
cls = coco80[ann['category_id'] - 1] if cls91to80 else ann['category_id'] - 1 # class
box = [cls] + box.tolist()
if box not in bboxes:
bboxes.append(box)
if use_segments and ann.get('segmentation') is not None:
if len(ann['segmentation']) == 0:
segments.append([])
continue
if isinstance(ann['segmentation'], dict):
ann['segmentation'] = rle2polygon(ann['segmentation'])
if len(ann['segmentation']) > 1:
s = merge_multi_segment(ann['segmentation'])
s = (np.concatenate(s, axis=0) / np.array([w, h])).reshape(-1).tolist()
else:
s = [j for i in ann['segmentation'] for j in i] # all segments concatenated
s = (np.array(s).reshape(-1, 2) / np.array([w, h])).reshape(-1).tolist()
s = [cls] + s
if s not in segments:
segments.append(s)
if use_keypoints and ann.get('keypoints') is not None:
k = (np.array(ann['keypoints']).reshape(-1, 3) / np.array([w, h, 1])).reshape(-1).tolist()
k = box + k
keypoints.append(k)
# Write
with open((fn / f).with_suffix('.txt'), 'a') as file:
for i in range(len(bboxes)):
if use_keypoints:
line = *(keypoints[i]), # cls, box, keypoints
else:
line = *(segments[i]
if use_segments and len(segments[i]) > 0 else bboxes[i]), # cls, box or segments
file.write(('%g ' * len(line)).rstrip() % line + '\n')
def rle2polygon(segmentation):
"""
Convert Run-Length Encoding (RLE) mask to polygon coordinates.
Args:
segmentation (dict, list): RLE mask representation of the object segmentation.
Returns:
(list): A list of lists representing the polygon coordinates for each contour.
Note:
Requires the 'pycocotools' package to be installed.
"""
check_requirements('pycocotools')
from pycocotools import mask
m = mask.decode(segmentation)
m[m > 0] = 255
contours, _ = cv2.findContours(m, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_TC89_KCOS)
polygons = []
for contour in contours:
epsilon = 0.001 * cv2.arcLength(contour, True)
contour_approx = cv2.approxPolyDP(contour, epsilon, True)
polygon = contour_approx.flatten().tolist()
polygons.append(polygon)
return polygons
def min_index(arr1, arr2):
"""
Find a pair of indexes with the shortest distance between two arrays of 2D points.
Args:
arr1 (np.array): A NumPy array of shape (N, 2) representing N 2D points.
arr2 (np.array): A NumPy array of shape (M, 2) representing M 2D points.
Returns:
(tuple): A tuple containing the indexes of the points with the shortest distance in arr1 and arr2 respectively.
"""
dis = ((arr1[:, None, :] - arr2[None, :, :]) ** 2).sum(-1)
return np.unravel_index(np.argmin(dis, axis=None), dis.shape)
def merge_multi_segment(segments):
"""
Merge multiple segments into one list by connecting the coordinates with the minimum distance between each segment.
This function connects these coordinates with a thin line to merge all segments into one.
Args:
segments (List[List]): Original segmentations in COCO's JSON file.
Each element is a list of coordinates, like [segmentation1, segmentation2,...].
Returns:
s (List[np.ndarray]): A list of connected segments represented as NumPy arrays.
"""
s = []
segments = [np.array(i).reshape(-1, 2) for i in segments]
idx_list = [[] for _ in range(len(segments))]
# record the indexes with min distance between each segment
for i in range(1, len(segments)):
idx1, idx2 = min_index(segments[i - 1], segments[i])
idx_list[i - 1].append(idx1)
idx_list[i].append(idx2)
# use two round to connect all the segments
for k in range(2):
# forward connection
if k == 0:
for i, idx in enumerate(idx_list):
# middle segments have two indexes
# reverse the index of middle segments
if len(idx) == 2 and idx[0] > idx[1]:
idx = idx[::-1]
segments[i] = segments[i][::-1, :]
segments[i] = np.roll(segments[i], -idx[0], axis=0)
segments[i] = np.concatenate([segments[i], segments[i][:1]])
# deal with the first segment and the last one
if i in [0, len(idx_list) - 1]:
s.append(segments[i])
else:
idx = [0, idx[1] - idx[0]]
s.append(segments[i][idx[0]:idx[1] + 1])
else:
for i in range(len(idx_list) - 1, -1, -1):
if i not in [0, len(idx_list) - 1]:
idx = idx_list[i]
nidx = abs(idx[1] - idx[0])
s.append(segments[i][nidx:])
return s
def delete_dsstore(path='../datasets'):
"""Delete Apple .DS_Store files in the specified directory and its subdirectories."""
from pathlib import Path
files = list(Path(path).rglob('.DS_store'))
print(files)
for f in files:
f.unlink()
if __name__ == '__main__':
source = 'COCO'
if source == 'COCO':
convert_coco(
'../datasets/coco/annotations', # directory with *.json
use_segments=False,
use_keypoints=True,
cls91to80=False)

20
ultralytics/yolo/engine/predictor.py
View File

@ -146,7 +146,7 @@ class BasePredictor:
log_string += result.verbose()
if self.args.save or self.args.show: # Add bbox to image
plot_args = dict(line_width=self.args.line_thickness,
plot_args = dict(line_width=self.args.line_width,
boxes=self.args.boxes,
conf=self.args.show_conf,
labels=self.args.show_labels)
@ -212,7 +212,7 @@ class BasePredictor:
self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))
self.done_warmup = True
self.seen, self.windows, self.dt, self.batch = 0, [], (ops.Profile(), ops.Profile(), ops.Profile()), None
self.seen, self.windows, self.batch, profilers = 0, [], None, (ops.Profile(), ops.Profile(), ops.Profile())
self.run_callbacks('on_predict_start')
for batch in self.dataset:
self.run_callbacks('on_predict_batch_start')
@ -222,15 +222,15 @@ class BasePredictor:
mkdir=True) if self.args.visualize and (not self.source_type.tensor) else False
# Preprocess
with self.dt[0]:
with profilers[0]:
im = self.preprocess(im0s)
# Inference
with self.dt[1]:
with profilers[1]:
preds = self.model(im, augment=self.args.augment, visualize=visualize)
# Postprocess
with self.dt[2]:
with profilers[2]:
self.results = self.postprocess(preds, im, im0s)
self.run_callbacks('on_predict_postprocess_end')
@ -238,9 +238,9 @@ class BasePredictor:
n = len(im0s)
for i in range(n):
self.results[i].speed = {
'preprocess': self.dt[0].dt * 1E3 / n,
'inference': self.dt[1].dt * 1E3 / n,
'postprocess': self.dt[2].dt * 1E3 / n}
'preprocess': profilers[0].dt * 1E3 / n,
'inference': profilers[1].dt * 1E3 / n,
'postprocess': profilers[2].dt * 1E3 / n}
if self.source_type.tensor: # skip write, show and plot operations if input is raw tensor
continue
p, im0 = path[i], im0s[i].copy()
@ -259,7 +259,7 @@ class BasePredictor:
# Print time (inference-only)
if self.args.verbose:
LOGGER.info(f'{s}{self.dt[1].dt * 1E3:.1f}ms')
LOGGER.info(f'{s}{profilers[1].dt * 1E3:.1f}ms')
# Release assets
if isinstance(self.vid_writer[-1], cv2.VideoWriter):
@ -267,7 +267,7 @@ class BasePredictor:
# Print results
if self.args.verbose and self.seen:
t = tuple(x.t / self.seen * 1E3 for x in self.dt) # speeds per image
t = tuple(x.t / self.seen * 1E3 for x in profilers) # speeds per image
LOGGER.info(f'Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape '
f'{(1, 3, *self.imgsz)}' % t)
if self.args.save or self.args.save_txt or self.args.save_crop:

5
ultralytics/yolo/engine/results.py
View File

@ -197,6 +197,11 @@ class Results(SimpleClass):
conf = kwargs['show_conf']
assert type(conf) == bool, '`show_conf` should be of boolean type, i.e, show_conf=True/False'
if 'show_conf' in kwargs:
deprecation_warn('line_thickness', 'line_width')
line_width = kwargs['line_thickness']
assert type(line_width) == int, '`line_width` should be of int type, i.e, line_width=3'
names = self.names
annotator = Annotator(deepcopy(self.orig_img if img is None else img),
line_width,

11
ultralytics/yolo/utils/files.py
View File

@ -3,6 +3,7 @@
import contextlib
import glob
import os
import shutil
from datetime import datetime
from pathlib import Path
@ -87,3 +88,13 @@ 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 make_dirs(dir='new_dir/'):
# Create folders
dir = Path(dir)
if dir.exists():
shutil.rmtree(dir) # delete dir
for p in dir, dir / 'labels', dir / 'images':
p.mkdir(parents=True, exist_ok=True) # make dir
return dir