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

ultralytics 8.0.89 SAM predict and auto-annotate (#2298)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: Paula Derrenger <107626595+pderrenger@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: Snyk bot <snyk-bot@snyk.io>
Co-authored-by: Laughing-q <1185102784@qq.com>
This commit is contained in:
Glenn Jocher
2023-04-28 00:36:50 +02:00
committed by GitHub
parent 3e118f6170
commit 243fc4b1fe
44 changed files with 2915 additions and 440 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
ultralytics/yolo/utils/callbacks/comet.py
View File

@ -13,20 +13,8 @@ try:
except (ImportError, AssertionError):
comet_ml = None
COMET_MODE = os.getenv('COMET_MODE', 'online')
COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'YOLOv8')
# Determines how many batches of image predictions to log from the validation set
COMET_EVAL_BATCH_LOGGING_INTERVAL = int(os.getenv('COMET_EVAL_BATCH_LOGGING_INTERVAL', 1))
# Determines whether to log confusion matrix every evaluation epoch
COMET_EVAL_LOG_CONFUSION_MATRIX = (os.getenv('COMET_EVAL_LOG_CONFUSION_MATRIX', 'true').lower() == 'true')
# Determines whether to log image predictions every evaluation epoch
COMET_EVAL_LOG_IMAGE_PREDICTIONS = (os.getenv('COMET_EVAL_LOG_IMAGE_PREDICTIONS', 'true').lower() == 'true')
COMET_MAX_IMAGE_PREDICTIONS = int(os.getenv('COMET_MAX_IMAGE_PREDICTIONS', 100))
# Ensures certain logging functions only run for supported tasks
COMET_SUPPORTED_TASKS = ['detect']
# Scales reported confidence scores (0.0-1.0) by this value
COMET_MAX_CONFIDENCE_SCORE = int(os.getenv('COMET_MAX_CONFIDENCE_SCORE', 100))
# Names of plots created by YOLOv8 that are logged to Comet
EVALUATION_PLOT_NAMES = 'F1_curve', 'P_curve', 'R_curve', 'PR_curve', 'confusion_matrix'
@ -35,6 +23,35 @@ LABEL_PLOT_NAMES = 'labels', 'labels_correlogram'
_comet_image_prediction_count = 0
def _get_comet_mode():
return os.getenv('COMET_MODE', 'online')
def _get_comet_model_name():
return os.getenv('COMET_MODEL_NAME', 'YOLOv8')
def _get_eval_batch_logging_interval():
return int(os.getenv('COMET_EVAL_BATCH_LOGGING_INTERVAL', 1))
def _get_max_image_predictions_to_log():
return int(os.getenv('COMET_MAX_IMAGE_PREDICTIONS', 100))
def _scale_confidence_score(score):
scale = float(os.getenv('COMET_MAX_CONFIDENCE_SCORE', 100.0))
return score * scale
def _should_log_confusion_matrix():
return os.getenv('COMET_EVAL_LOG_CONFUSION_MATRIX', 'true').lower() == 'true'
def _should_log_image_predictions():
return os.getenv('COMET_EVAL_LOG_IMAGE_PREDICTIONS', 'true').lower() == 'true'
def _get_experiment_type(mode, project_name):
"""Return an experiment based on mode and project name."""
if mode == 'offline':
@ -48,13 +65,14 @@ def _create_experiment(args):
if RANK not in (-1, 0):
return
try:
experiment = _get_experiment_type(COMET_MODE, args.project)
comet_mode = _get_comet_mode()
experiment = _get_experiment_type(comet_mode, args.project)
experiment.log_parameters(vars(args))
experiment.log_others({
'eval_batch_logging_interval': COMET_EVAL_BATCH_LOGGING_INTERVAL,
'log_confusion_matrix': COMET_EVAL_LOG_CONFUSION_MATRIX,
'log_image_predictions': COMET_EVAL_LOG_IMAGE_PREDICTIONS,
'max_image_predictions': COMET_MAX_IMAGE_PREDICTIONS, })
'eval_batch_logging_interval': _get_eval_batch_logging_interval(),
'log_confusion_matrix': _should_log_confusion_matrix(),
'log_image_predictions': _should_log_image_predictions(),
'max_image_predictions': _get_max_image_predictions_to_log(), })
experiment.log_other('Created from', 'yolov8')
except Exception as e:
@ -74,7 +92,12 @@ def _fetch_trainer_metadata(trainer):
save_interval = curr_epoch % save_period == 0
save_assets = save and save_period > 0 and save_interval and not final_epoch
return dict(curr_epoch=curr_epoch, curr_step=curr_step, save_assets=save_assets, final_epoch=final_epoch)
return dict(
curr_epoch=curr_epoch,
curr_step=curr_step,
save_assets=save_assets,
final_epoch=final_epoch,
)
def _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad):
@ -117,7 +140,10 @@ def _format_ground_truth_annotations_for_detection(img_idx, image_path, batch, c
data = []
for box, label in zip(bboxes, cls_labels):
box = _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad)
data.append({'boxes': [box], 'label': f'gt_{label}', 'score': COMET_MAX_CONFIDENCE_SCORE})
data.append({
'boxes': [box],
'label': f'gt_{label}',
'score': _scale_confidence_score(1.0), })
return {'name': 'ground_truth', 'data': data}
@ -135,7 +161,7 @@ def _format_prediction_annotations_for_detection(image_path, metadata, class_lab
data = []
for prediction in predictions:
boxes = prediction['bbox']
score = prediction['score'] * COMET_MAX_CONFIDENCE_SCORE
score = _scale_confidence_score(prediction['score'])
cls_label = prediction['category_id']
if class_label_map:
cls_label = str(class_label_map[cls_label])
@ -207,13 +233,16 @@ def _log_image_predictions(experiment, validator, curr_step):
dataloader = validator.dataloader
class_label_map = validator.names
batch_logging_interval = _get_eval_batch_logging_interval()
max_image_predictions = _get_max_image_predictions_to_log()
for batch_idx, batch in enumerate(dataloader):
if (batch_idx + 1) % COMET_EVAL_BATCH_LOGGING_INTERVAL != 0:
if (batch_idx + 1) % batch_logging_interval != 0:
continue
image_paths = batch['im_file']
for img_idx, image_path in enumerate(image_paths):
if _comet_image_prediction_count >= COMET_MAX_IMAGE_PREDICTIONS:
if _comet_image_prediction_count >= max_image_predictions:
return
image_path = Path(image_path)
@ -244,8 +273,9 @@ def _log_plots(experiment, trainer):
def _log_model(experiment, trainer):
"""Log the best-trained model to Comet.ml."""
model_name = _get_comet_model_name()
experiment.log_model(
COMET_MODEL_NAME,
model_name,
file_or_folder=str(trainer.best),
file_name='best.pt',
overwrite=True,
@ -255,7 +285,8 @@ def _log_model(experiment, trainer):
def on_pretrain_routine_start(trainer):
"""Creates or resumes a CometML experiment at the start of a YOLO pre-training routine."""
experiment = comet_ml.get_global_experiment()
if not experiment:
is_alive = getattr(experiment, 'alive', False)
if not experiment or not is_alive:
_create_experiment(trainer.args)
@ -296,16 +327,16 @@ def on_fit_epoch_end(trainer):
model_info = {
'model/parameters': get_num_params(trainer.model),
'model/GFLOPs': round(get_flops(trainer.model), 3),
'model/speed(ms)': round(trainer.validator.speed['inference'], 3)}
'model/speed(ms)': round(trainer.validator.speed['inference'], 3), }
experiment.log_metrics(model_info, step=curr_step, epoch=curr_epoch)
if not save_assets:
return
_log_model(experiment, trainer)
if COMET_EVAL_LOG_CONFUSION_MATRIX:
if _should_log_confusion_matrix():
_log_confusion_matrix(experiment, trainer, curr_step, curr_epoch)
if COMET_EVAL_LOG_IMAGE_PREDICTIONS:
if _should_log_image_predictions():
_log_image_predictions(experiment, trainer.validator, curr_step)

3
ultralytics/yolo/utils/downloads.py
View File

@ -17,7 +17,8 @@ from ultralytics.yolo.utils import LOGGER, checks, clean_url, emojis, is_online,
GITHUB_ASSET_NAMES = [f'yolov8{k}{suffix}.pt' for k in 'nsmlx' for suffix in ('', '6', '-cls', '-seg', '-pose')] + \
[f'yolov5{k}u.pt' for k in 'nsmlx'] + \
[f'yolov3{k}u.pt' for k in ('', '-spp', '-tiny')]
[f'yolov3{k}u.pt' for k in ('', '-spp', '-tiny')] + \
[f'sam_{k}.pt' for k in 'bl']
GITHUB_ASSET_STEMS = [Path(k).stem for k in GITHUB_ASSET_NAMES]

68
ultralytics/yolo/utils/plotting.py
View File

@ -192,14 +192,27 @@ class Annotator:
"""Add rectangle to image (PIL-only)."""
self.draw.rectangle(xy, fill, outline, width)
def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'):
def text(self, xy, text, txt_color=(255, 255, 255), anchor='top', box_style=False):
"""Adds text to an image using PIL or cv2."""
if anchor == 'bottom': # start y from font bottom
w, h = self.font.getsize(text) # text width, height
xy[1] += 1 - h
if self.pil:
if box_style:
w, h = self.font.getsize(text)
self.draw.rectangle((xy[0], xy[1], xy[0] + w + 1, xy[1] + h + 1), fill=txt_color)
# Using `txt_color` for background and draw fg with white color
txt_color = (255, 255, 255)
self.draw.text(xy, text, fill=txt_color, font=self.font)
else:
if box_style:
tf = max(self.lw - 1, 1) # font thickness
w, h = cv2.getTextSize(text, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height
outside = xy[1] - h >= 3
p2 = xy[0] + w, xy[1] - h - 3 if outside else xy[1] + h + 3
cv2.rectangle(self.im, xy, p2, txt_color, -1, cv2.LINE_AA) # filled
# Using `txt_color` for background and draw fg with white color
txt_color = (255, 255, 255)
tf = max(self.lw - 1, 1) # font thickness
cv2.putText(self.im, text, xy, 0, self.lw / 3, txt_color, thickness=tf, lineType=cv2.LINE_AA)
@ -283,7 +296,7 @@ def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False,
def plot_images(images,
batch_idx,
cls,
bboxes,
bboxes=np.zeros(0, dtype=np.float32),
masks=np.zeros(0, dtype=np.uint8),
kpts=np.zeros((0, 51), dtype=np.float32),
paths=None,
@ -337,27 +350,33 @@ def plot_images(images,
annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames
if len(cls) > 0:
idx = batch_idx == i
boxes = xywh2xyxy(bboxes[idx, :4]).T
classes = cls[idx].astype('int')
labels = bboxes.shape[1] == 4 # labels if no conf column
conf = None if labels else bboxes[idx, 4] # check for confidence presence (label vs pred)
if boxes.shape[1]:
if boxes.max() <= 1.01: # if normalized with tolerance 0.01
boxes[[0, 2]] *= w # scale to pixels
boxes[[1, 3]] *= h
elif scale < 1: # absolute coords need scale if image scales
boxes *= scale
boxes[[0, 2]] += x
boxes[[1, 3]] += y
for j, box in enumerate(boxes.T.tolist()):
c = classes[j]
color = colors(c)
c = names.get(c, c) if names else c
if labels or conf[j] > 0.25: # 0.25 conf thresh
label = f'{c}' if labels else f'{c} {conf[j]:.1f}'
annotator.box_label(box, label, color=color)
if len(bboxes):
boxes = xywh2xyxy(bboxes[idx, :4]).T
labels = bboxes.shape[1] == 4 # labels if no conf column
conf = None if labels else bboxes[idx, 4] # check for confidence presence (label vs pred)
if boxes.shape[1]:
if boxes.max() <= 1.01: # if normalized with tolerance 0.01
boxes[[0, 2]] *= w # scale to pixels
boxes[[1, 3]] *= h
elif scale < 1: # absolute coords need scale if image scales
boxes *= scale
boxes[[0, 2]] += x
boxes[[1, 3]] += y
for j, box in enumerate(boxes.T.tolist()):
c = classes[j]
color = colors(c)
c = names.get(c, c) if names else c
if labels or conf[j] > 0.25: # 0.25 conf thresh
label = f'{c}' if labels else f'{c} {conf[j]:.1f}'
annotator.box_label(box, label, color=color)
elif len(classes):
for c in classes:
color = colors(c)
c = names.get(c, c) if names else c
annotator.text((x, y), f'{c}', txt_color=color, box_style=True)
# Plot keypoints
if len(kpts):
@ -403,11 +422,14 @@ def plot_images(images,
@plt_settings()
def plot_results(file='path/to/results.csv', dir='', segment=False, pose=False):
def plot_results(file='path/to/results.csv', dir='', segment=False, pose=False, classify=False):
"""Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv')."""
import pandas as pd
save_dir = Path(file).parent if file else Path(dir)
if segment:
if classify:
fig, ax = plt.subplots(2, 2, figsize=(6, 6), tight_layout=True)
index = [1, 4, 2, 3]
elif segment:
fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True)
index = [1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12]
elif pose:

2
ultralytics/yolo/utils/tal.py
View File

@ -225,7 +225,7 @@ class TaskAlignedAssigner(nn.Module):
target_bboxes = gt_bboxes.view(-1, 4)[target_gt_idx]
# Assigned target scores
target_labels.clamp(0)
target_labels.clamp_(0)
target_scores = F.one_hot(target_labels, self.num_classes) # (b, h*w, 80)
fg_scores_mask = fg_mask[:, :, None].repeat(1, 1, self.num_classes) # (b, h*w, 80)
target_scores = torch.where(fg_scores_mask > 0, target_scores, 0)