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

74
ultralytics/nn/tasks.py
View File

@ -170,7 +170,7 @@ class DetectionModel(BaseModel):
# YOLOv8 detection model
def __init__(self, cfg='yolov8n.yaml', ch=3, nc=None, verbose=True): # model, input channels, number of classes
super().__init__()
self.yaml = cfg if isinstance(cfg, dict) else yaml_load(check_yaml(cfg), append_filename=True) # cfg dict
self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg) # cfg dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
@ -277,7 +277,8 @@ class ClassificationModel(BaseModel):
self.nc = nc
def _from_yaml(self, cfg, ch, nc, verbose):
self.yaml = cfg if isinstance(cfg, dict) else yaml_load(check_yaml(cfg), append_filename=True) # cfg dict
self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg) # cfg dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
if nc and nc != self.yaml['nc']:
@ -418,30 +419,42 @@ def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False):
def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
# Parse a YOLO model.yaml dictionary
if verbose:
LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}")
nc, gd, gw, act = d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
# Parse a YOLO model.yaml dictionary into a PyTorch model
import ast
# Args
max_channels = float('inf')
nc, act, scales = (d.get(x) for x in ('nc', 'act', 'scales'))
depth, width = (d.get(x, 1.0) for x in ('depth_multiple', 'width_multiple'))
if scales:
scale = d.get('scale')
if not scale:
scale = tuple(scales.keys())[0]
LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
depth, width, max_channels = scales[scale]
if act:
Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU()
if verbose:
LOGGER.info(f"{colorstr('activation:')} {act}") # print
if verbose:
LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}")
ch = [ch]
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m] # get module
for j, a in enumerate(args):
# TODO: re-implement with eval() removal if possible
# args[j] = (locals()[a] if a in locals() else ast.literal_eval(a)) if isinstance(a, str) else a
with contextlib.suppress(NameError):
args[j] = eval(a) if isinstance(a, str) else a # eval strings
if isinstance(a, str):
with contextlib.suppress(ValueError):
args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
n = n_ = max(round(n * depth), 1) if n > 1 else n # depth gain
if m in (Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x):
c1, c2 = ch[f], args[0]
if c2 != nc: # if c2 not equal to number of classes (i.e. for Classify() output)
c2 = make_divisible(c2 * gw, 8)
c2 = make_divisible(min(c2, max_channels) * width, 8)
args = [c1, c2, *args[1:]]
if m in (BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x):
@ -454,7 +467,7 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
elif m in (Detect, Segment):
args.append([ch[x] for x in f])
if m is Segment:
args[2] = make_divisible(args[2] * gw, 8)
args[2] = make_divisible(min(args[2], max_channels) * width, 8)
else:
c2 = ch[f]
@ -472,6 +485,41 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
return nn.Sequential(*layers), sorted(save)
def yaml_model_load(path):
import re
path = Path(path)
if path.stem in (f'yolov{d}{x}6' for x in 'nsmlx' for d in (5, 8)):
new_stem = re.sub(r'(\d+)([nslmx])6(.+)?$', r'\1\2-p6\3', path.stem)
LOGGER.warning(f'WARNING ⚠️ Ultralytics YOLO P6 models now use -p6 suffix. Renaming {path.stem} to {new_stem}.')
path = path.with_stem(new_stem)
unified_path = re.sub(r'(\d+)([nslmx])(.+)?$', r'\1\3', str(path)) # i.e. yolov8x.yaml -> yolov8.yaml
yaml_file = check_yaml(unified_path, hard=False) or check_yaml(path)
d = yaml_load(yaml_file) # model dict
d['scale'] = guess_model_scale(path)
d['yaml_file'] = str(path)
return d
def guess_model_scale(model_path):
"""
Takes a path to a YOLO model's YAML file as input and extracts the size character of the model's scale.
The function uses regular expression matching to find the pattern of the model scale in the YAML file name,
which is denoted by n, s, m, l, or x. The function returns the size character of the model scale as a string.
Args:
model_path (str or Path): The path to the YOLO model's YAML file.
Returns:
(str): The size character of the model's scale, which can be n, s, m, l, or x.
"""
with contextlib.suppress(AttributeError):
import re
return re.search(r'yolov\d+([nslmx])', Path(model_path).stem).group(1) # n, s, m, l, or x
return ''
def guess_model_task(model):
"""
Guess the task of a PyTorch model from its architecture or configuration.