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

ultralytics 8.0.55 unified YOLOv8 model YAMLs (#1475)

Browse Source
This commit is contained in:
Glenn Jocher
2023-03-20 13:54:20 +01:00
committed by GitHub
parent 701fba4770
commit 25cc07401f
45 changed files with 203 additions and 896 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/yolo/data/dataset.py
View File

@ -17,7 +17,7 @@ from .utils import HELP_URL, LOCAL_RANK, LOGGER, get_hash, img2label_paths, veri
class YOLODataset(BaseDataset):
cache_version = '1.0.1' # dataset labels *.cache version, >= 1.0.0 for YOLOv8
cache_version = '1.0.2' # dataset labels *.cache version, >= 1.0.0 for YOLOv8
rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4]
"""
Dataset class for loading images object detection and/or segmentation labels in YOLO format.

16
ultralytics/yolo/engine/exporter.py
View File

@ -245,8 +245,7 @@ class Exporter:
if tflite:
f[7], _ = self._export_tflite(s_model, nms=False, agnostic_nms=self.args.agnostic_nms)
if edgetpu:
f[8], _ = self._export_edgetpu(tflite_model=str(
Path(f[5]) / (self.file.stem + '_full_integer_quant.tflite'))) # int8 in/out
f[8], _ = self._export_edgetpu(tflite_model=Path(f[5]) / f'{self.file.stem}_full_integer_quant.tflite')
if tfjs:
f[9], _ = self._export_tfjs()
if paddle: # PaddlePaddle
@ -532,9 +531,16 @@ class Exporter:
subprocess.run(cmd, shell=True)
yaml_save(f / 'metadata.yaml', self.metadata) # add metadata.yaml
# Remove/rename TFLite models
if self.args.int8:
for file in f.rglob('*_dynamic_range_quant.tflite'):
file.rename(file.with_stem(file.stem.replace('_dynamic_range_quant', '_int8')))
for file in f.rglob('*_integer_quant_with_int16_act.tflite'):
file.unlink() # delete extra fp16 activation TFLite files
# Add TFLite metadata
for file in f.rglob('*.tflite'):
self._add_tflite_metadata(file)
f.unlink() if 'quant_with_int16_act.tflite' in str(f) else self._add_tflite_metadata(file)
# Load saved_model
keras_model = tf.saved_model.load(f, tags=None, options=None)
@ -565,9 +571,9 @@ class Exporter:
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
saved_model = Path(str(self.file).replace(self.file.suffix, '_saved_model'))
if self.args.int8:
f = saved_model / f'{self.file.stem}_integer_quant.tflite' # fp32 in/out
f = saved_model / f'{self.file.stem}_int8.tflite' # fp32 in/out
elif self.args.half:
f = saved_model / f'{self.file.stem}_float16.tflite'
f = saved_model / f'{self.file.stem}_float16.tflite' # fp32 in/out
else:
f = saved_model / f'{self.file.stem}_float32.tflite'
return str(f), None

6
ultralytics/yolo/engine/model.py
View File

@ -5,7 +5,7 @@ from pathlib import Path
from ultralytics import yolo # noqa
from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, SegmentationModel, attempt_load_one_weight,
guess_model_task, nn)
guess_model_task, nn, yaml_model_load)
from ultralytics.yolo.cfg import get_cfg
from ultralytics.yolo.engine.exporter import Exporter
from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, ROOT, callbacks,
@ -111,8 +111,8 @@ class YOLO:
task (str) or (None): model task
verbose (bool): display model info on load
"""
self.cfg = check_yaml(cfg) # check YAML
cfg_dict = yaml_load(self.cfg, append_filename=True) # model dict
cfg_dict = yaml_model_load(cfg)
self.cfg = cfg
self.task = task or guess_model_task(cfg_dict)
self.model = TASK_MAP[self.task][0](cfg_dict, verbose=verbose and RANK == -1) # build model
self.overrides['model'] = self.cfg

18
ultralytics/yolo/utils/checks.py
View File

@ -248,9 +248,9 @@ def check_yolov5u_filename(file: str, verbose: bool = True):
# Replace legacy YOLOv5 filenames with updated YOLOv5u filenames
if ('yolov3' in file or 'yolov5' in file) and 'u' not in file:
original_file = file
file = re.sub(r'(.*yolov5([nsmlx]))\.', '\\1u.', file) # i.e. yolov5n.pt -> yolov5nu.pt
file = re.sub(r'(.*yolov5([nsmlx])6)\.', '\\1u.', file) # i.e. yolov5n6.pt -> yolov5n6u.pt
file = re.sub(r'(.*yolov3(|-tiny|-spp))\.', '\\1u.', file) # i.e. yolov3-spp.pt -> yolov3-sppu.pt
file = re.sub(r'(.*yolov5([nsmlx]))\.pt', '\\1u.pt', file) # i.e. yolov5n.pt -> yolov5nu.pt
file = re.sub(r'(.*yolov5([nsmlx])6)\.pt', '\\1u.pt', file) # i.e. yolov5n6.pt -> yolov5n6u.pt
file = re.sub(r'(.*yolov3(|-tiny|-spp))\.pt', '\\1u.pt', file) # i.e. yolov3-spp.pt -> yolov3-sppu.pt
if file != original_file and verbose:
LOGGER.info(f"PRO TIP 💡 Replace 'model={original_file}' with new 'model={file}'.\nYOLOv5 'u' models are "
f'trained with https://github.com/ultralytics/ultralytics and feature improved performance vs '
@ -258,7 +258,7 @@ def check_yolov5u_filename(file: str, verbose: bool = True):
return file
def check_file(file, suffix='', download=True):
def check_file(file, suffix='', download=True, hard=True):
# Search/download file (if necessary) and return path
check_suffix(file, suffix) # optional
file = str(file) # convert to string
@ -277,16 +277,16 @@ def check_file(file, suffix='', download=True):
files = []
for d in 'models', 'datasets', 'tracker/cfg', 'yolo/cfg': # search directories
files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True)) # find file
if not files:
if not files and hard:
raise FileNotFoundError(f"'{file}' does not exist")
elif len(files) > 1:
elif len(files) > 1 and hard:
raise FileNotFoundError(f"Multiple files match '{file}', specify exact path: {files}")
return files[0] # return file
return files[0] if len(files) else [] # return file
def check_yaml(file, suffix=('.yaml', '.yml')):
def check_yaml(file, suffix=('.yaml', '.yml'), hard=True):
# Search/download YAML file (if necessary) and return path, checking suffix
return check_file(file, suffix)
return check_file(file, suffix, hard=hard)
def check_imshow(warn=False):

7
ultralytics/yolo/v8/detect/predict.py
View File

@ -63,13 +63,12 @@ class DetectionPredictor(BasePredictor):
# write
for d in reversed(det):
cls, conf, id = d.cls.squeeze(), d.conf.squeeze(), None if d.id is None else int(d.id.item())
c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
if self.args.save_txt: # Write to file
line = (cls, *d.xywhn.view(-1)) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
line = (c, *d.xywhn.view(-1)) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
with open(f'{self.txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if self.args.save or self.args.save_crop or self.args.show: # Add bbox to image
c = int(cls) # integer class
if self.args.save or self.args.show: # Add bbox to image
name = ('' if id is None else f'id:{id} ') + self.model.names[c]
label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))

10
ultralytics/yolo/v8/segment/predict.py
View File

@ -76,17 +76,17 @@ class SegmentationPredictor(DetectionPredictor):
# Write results
for j, d in enumerate(reversed(det)):
cls, conf, id = d.cls.squeeze(), d.conf.squeeze(), None if d.id is None else int(d.id.item())
c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
if self.args.save_txt: # Write to file
seg = mask.segments[len(det) - j - 1].copy().reshape(-1) # reversed mask.segments, (n,2) to (n*2)
line = (cls, *seg) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
line = (c, *seg) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
with open(f'{self.txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if self.args.save or self.args.save_crop or self.args.show: # Add bbox to image
c = int(cls) # integer class
if self.args.save or self.args.show: # Add bbox to image
name = ('' if id is None else f'id:{id} ') + self.model.names[c]
label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True)) if self.args.boxes else None
if self.args.boxes:
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
if self.args.save_crop:
save_one_box(d.xyxy,
imc,

16
ultralytics/yolo/v8/segment/train.py
View File

@ -122,13 +122,15 @@ class SegLoss(Loss):
xyxyn = target_bboxes[i][fg_mask[i]] / imgsz[[1, 0, 1, 0]]
marea = xyxy2xywh(xyxyn)[:, 2:].prod(1)
mxyxy = xyxyn * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device)
loss[1] += self.single_mask_loss(gt_mask, pred_masks[i][fg_mask[i]], proto[i], mxyxy,
marea) # seg loss
# WARNING: Uncomment lines below in case of Multi-GPU DDP unused gradient errors
# else:
# loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
# else:
# loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
loss[1] += self.single_mask_loss(gt_mask, pred_masks[i][fg_mask[i]], proto[i], mxyxy, marea) # seg
# WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
else:
loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
# WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
else:
loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
loss[0] *= self.hyp.box # box gain
loss[1] *= self.hyp.box / batch_size # seg gain