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

`ultralytics 8.0.49` task, exports and metadata updates (#1197)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Mehran Ghandehari <mehran.maps@gmail.com>
Co-authored-by: Paul Guerrie <97041392+paulguerrie@users.noreply.github.com>
single_channel
Glenn Jocher 2 years ago committed by GitHub
parent 74e4c94806
commit 3861e6c82a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
20 changed files with 111 additions and 101 deletions
Show Stats Download Patch File Download Diff File

1
.github/workflows/ci.yaml vendored
Unescape View File

@ -13,6 +13,7 @@ on:
jobs: jobs:
HUB: HUB:
if: github.repository == 'ultralytics/ultralytics' && (github.event_name == 'schedule' || github.event_name == 'push')
runs-on: ${{ matrix.os }} runs-on: ${{ matrix.os }}
strategy: strategy:
fail-fast: false fail-fast: false

2
docker/Dockerfile
Unescape View File

@ -18,7 +18,7 @@ RUN apt install --no-install-recommends -y gcc git zip curl htop libgl1-mesa-glx
# Security updates # Security updates
# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796 # https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796
RUN apt upgrade --no-install-recommends -y openssl RUN apt upgrade --no-install-recommends -y openssl tar
# Create working directory # Create working directory
RUN mkdir -p /usr/src/ultralytics RUN mkdir -p /usr/src/ultralytics

2
ultralytics/__init__.py
Unescape View File

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, GPL-3.0 license # Ultralytics YOLO 🚀, GPL-3.0 license
__version__ = '8.0.48' __version__ = '8.0.49'
from ultralytics.yolo.engine.model import YOLO from ultralytics.yolo.engine.model import YOLO
from ultralytics.yolo.utils.checks import check_yolo as checks from ultralytics.yolo.utils.checks import check_yolo as checks

54
ultralytics/nn/autobackend.py
Unescape View File

@ -75,7 +75,7 @@ class AutoBackend(nn.Module):
fp16 &= pt or jit or onnx or engine or nn_module # FP16 fp16 &= pt or jit or onnx or engine or nn_module # FP16
nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH) nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH)
stride = 32 # default stride stride = 32 # default stride
model = None # TODO: resolves ONNX inference, verify effect on other backends model, metadata = None, None
cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA
if not (pt or triton or nn_module): if not (pt or triton or nn_module):
w = attempt_download_asset(w) # download if not local w = attempt_download_asset(w) # download if not local
@ -105,10 +105,7 @@ class AutoBackend(nn.Module):
model = torch.jit.load(w, _extra_files=extra_files, map_location=device) model = torch.jit.load(w, _extra_files=extra_files, map_location=device)
model.half() if fp16 else model.float() model.half() if fp16 else model.float()
if extra_files['config.txt']: # load metadata dict if extra_files['config.txt']: # load metadata dict
d = json.loads(extra_files['config.txt'], metadata = json.loads(extra_files['config.txt'], object_hook=lambda x: dict(x.items()))
object_hook=lambda d: {int(k) if k.isdigit() else k: v
for k, v in d.items()})
stride, names = int(d['stride']), d['names']
elif dnn: # ONNX OpenCV DNN elif dnn: # ONNX OpenCV DNN
LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...') LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
check_requirements('opencv-python>=4.5.4') check_requirements('opencv-python>=4.5.4')
@ -120,23 +117,23 @@ class AutoBackend(nn.Module):
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider'] providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
session = onnxruntime.InferenceSession(w, providers=providers) session = onnxruntime.InferenceSession(w, providers=providers)
output_names = [x.name for x in session.get_outputs()] output_names = [x.name for x in session.get_outputs()]
meta = session.get_modelmeta().custom_metadata_map # metadata metadata = session.get_modelmeta().custom_metadata_map # metadata
if 'stride' in meta:
stride, names = int(meta['stride']), eval(meta['names'])
elif xml: # OpenVINO elif xml: # OpenVINO
LOGGER.info(f'Loading {w} for OpenVINO inference...') LOGGER.info(f'Loading {w} for OpenVINO inference...')
check_requirements('openvino') # requires openvino-dev: https://pypi.org/project/openvino-dev/ check_requirements('openvino') # requires openvino-dev: https://pypi.org/project/openvino-dev/
from openvino.runtime import Core, Layout, get_batch # noqa from openvino.runtime import Core, Layout, get_batch # noqa
ie = Core() ie = Core()
if not Path(w).is_file(): # if not *.xml w = Path(w)
w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir if not w.is_file(): # if not *.xml
network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin')) w = next(w.glob('*.xml')) # get *.xml file from *_openvino_model dir
network = ie.read_model(model=str(w), weights=w.with_suffix('.bin'))
if network.get_parameters()[0].get_layout().empty: if network.get_parameters()[0].get_layout().empty:
network.get_parameters()[0].set_layout(Layout('NCHW')) network.get_parameters()[0].set_layout(Layout('NCHW'))
batch_dim = get_batch(network) batch_dim = get_batch(network)
if batch_dim.is_static: if batch_dim.is_static:
batch_size = batch_dim.get_length() batch_size = batch_dim.get_length()
executable_network = ie.compile_model(network, device_name='CPU') # device_name="MYRIAD" for NCS2 executable_network = ie.compile_model(network, device_name='CPU') # device_name="MYRIAD" for NCS2
metadata = w.parent / 'metadata.yaml'
elif engine: # TensorRT elif engine: # TensorRT
LOGGER.info(f'Loading {w} for TensorRT inference...') LOGGER.info(f'Loading {w} for TensorRT inference...')
import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download
@ -148,7 +145,7 @@ class AutoBackend(nn.Module):
# Read file # Read file
with open(w, 'rb') as f, trt.Runtime(logger) as runtime: with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
meta_len = int.from_bytes(f.read(4), byteorder='little') # read metadata length meta_len = int.from_bytes(f.read(4), byteorder='little') # read metadata length
meta = json.loads(f.read(meta_len).decode('utf-8')) # read metadata metadata = json.loads(f.read(meta_len).decode('utf-8')) # read metadata
model = runtime.deserialize_cuda_engine(f.read()) # read engine model = runtime.deserialize_cuda_engine(f.read()) # read engine
context = model.create_execution_context() context = model.create_execution_context()
bindings = OrderedDict() bindings = OrderedDict()
@ -171,18 +168,17 @@ class AutoBackend(nn.Module):
bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr())) bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items()) binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size
stride, names = int(meta['stride']), meta['names']
elif coreml: # CoreML elif coreml: # CoreML
LOGGER.info(f'Loading {w} for CoreML inference...') LOGGER.info(f'Loading {w} for CoreML inference...')
import coremltools as ct import coremltools as ct
model = ct.models.MLModel(w) model = ct.models.MLModel(w)
names, stride, task = (model.user_defined_metadata.get(k) for k in ('names', 'stride', 'task')) metadata = model.user_defined_metadata
names, stride = eval(names), int(stride)
elif saved_model: # TF SavedModel elif saved_model: # TF SavedModel
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...') LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
import tensorflow as tf import tensorflow as tf
keras = False # assume TF1 saved_model keras = False # assume TF1 saved_model
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w) model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
metadata = Path(w) / 'metadata.yaml'
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...') LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
import tensorflow as tf import tensorflow as tf
@ -221,23 +217,23 @@ class AutoBackend(nn.Module):
with contextlib.suppress(zipfile.BadZipFile): with contextlib.suppress(zipfile.BadZipFile):
with zipfile.ZipFile(w, 'r') as model: with zipfile.ZipFile(w, 'r') as model:
meta_file = model.namelist()[0] meta_file = model.namelist()[0]
meta = ast.literal_eval(model.read(meta_file).decode('utf-8')) metadata = ast.literal_eval(model.read(meta_file).decode('utf-8'))
stride, names = int(meta['stride']), meta['names']
elif tfjs: # TF.js elif tfjs: # TF.js
raise NotImplementedError('YOLOv8 TF.js inference is not supported') raise NotImplementedError('YOLOv8 TF.js inference is not supported')
elif paddle: # PaddlePaddle elif paddle: # PaddlePaddle
LOGGER.info(f'Loading {w} for PaddlePaddle inference...') LOGGER.info(f'Loading {w} for PaddlePaddle inference...')
check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle') check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle')
import paddle.inference as pdi import paddle.inference as pdi
if not Path(w).is_file(): # if not *.pdmodel w = Path(w)
w = next(Path(w).rglob('*.pdmodel')) # get *.pdmodel file from *_paddle_model dir if not w.is_file(): # if not *.pdmodel
weights = Path(w).with_suffix('.pdiparams') w = next(w.rglob('*.pdmodel')) # get *.pdmodel file from *_paddle_model dir
config = pdi.Config(str(w), str(weights)) config = pdi.Config(str(w), str(w.with_suffix('.pdiparams')))
if cuda: if cuda:
config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0) config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0)
predictor = pdi.create_predictor(config) predictor = pdi.create_predictor(config)
input_handle = predictor.get_input_handle(predictor.get_input_names()[0]) input_handle = predictor.get_input_handle(predictor.get_input_names()[0])
output_names = predictor.get_output_names() output_names = predictor.get_output_names()
metadata = w.parents[1] / 'metadata.yaml'
elif triton: # NVIDIA Triton Inference Server elif triton: # NVIDIA Triton Inference Server
LOGGER.info('Triton Inference Server not supported...') LOGGER.info('Triton Inference Server not supported...')
''' '''
@ -254,14 +250,16 @@ class AutoBackend(nn.Module):
f'\n\n{EXPORT_FORMATS_TABLE}') f'\n\n{EXPORT_FORMATS_TABLE}')
# Load external metadata YAML # Load external metadata YAML
w = Path(w) if isinstance(metadata, (str, Path)) and Path(metadata).exists():
if xml or saved_model or paddle:
metadata = (w if saved_model else w.parents[1] if paddle else w.parent) / 'metadata.yaml'
if metadata.exists():
metadata = yaml_load(metadata) metadata = yaml_load(metadata)
stride, names = int(metadata['stride']), metadata['names'] # load metadata if metadata:
else: stride = int(metadata['stride'])
LOGGER.warning(f"WARNING ⚠️ Metadata not found at '{metadata}'") task = metadata['task']
batch = int(metadata['batch'])
imgsz = eval(metadata['imgsz']) if isinstance(metadata['imgsz'], str) else metadata['imgsz']
names = eval(metadata['names']) if isinstance(metadata['names'], str) else metadata['names']
elif not (pt or triton or nn_module):
LOGGER.warning(f"WARNING ⚠️ Metadata not found for 'model={weights}'")
# Check names # Check names
if 'names' not in locals(): # names missing if 'names' not in locals(): # names missing

4
ultralytics/nn/tasks.py
Unescape View File

@ -257,7 +257,7 @@ class ClassificationModel(BaseModel):
cfg=None, cfg=None,
model=None, model=None,
ch=3, ch=3,
nc=1000, nc=None,
cutoff=10, cutoff=10,
verbose=True): # yaml, model, channels, number of classes, cutoff index, verbose flag verbose=True): # yaml, model, channels, number of classes, cutoff index, verbose flag
super().__init__() super().__init__()
@ -286,6 +286,8 @@ class ClassificationModel(BaseModel):
if nc and nc != self.yaml['nc']: if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value self.yaml['nc'] = nc # override yaml value
elif not nc and not self.yaml.get('nc', None):
raise ValueError('nc not specified. Must specify nc in model.yaml or function arguments.')
self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose) # model, savelist self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose) # model, savelist
self.stride = torch.Tensor([1]) # no stride constraints self.stride = torch.Tensor([1]) # no stride constraints
self.names = {i: f'{i}' for i in range(self.yaml['nc'])} # default names dict self.names = {i: f'{i}' for i in range(self.yaml['nc'])} # default names dict

7
ultralytics/tracker/track.py
Unescape View File

@ -1,12 +1,11 @@
# Ultralytics YOLO 🚀, GPL-3.0 license # Ultralytics YOLO 🚀, GPL-3.0 license
from ultralytics.yolo.utils.checks import check_requirements, check_yaml
check_requirements('lap') # for linear_assignment
import torch import torch
from ultralytics.yolo.utils import IterableSimpleNamespace, yaml_load from ultralytics.yolo.utils import IterableSimpleNamespace, yaml_load
from ultralytics.yolo.utils.checks import check_requirements, check_yaml
check_requirements('lap') # for linear_assignment
from .trackers import BOTSORT, BYTETracker from .trackers import BOTSORT, BYTETracker

8
ultralytics/tracker/trackers/bot_sort.py
Unescape View File

@ -65,7 +65,8 @@ class BOTrack(STrack):
@staticmethod @staticmethod
def multi_predict(stracks): def multi_predict(stracks):
if len(stracks) > 0: if len(stracks) <= 0:
return
multi_mean = np.asarray([st.mean.copy() for st in stracks]) multi_mean = np.asarray([st.mean.copy() for st in stracks])
multi_covariance = np.asarray([st.covariance for st in stracks]) multi_covariance = np.asarray([st.covariance for st in stracks])
for i, st in enumerate(stracks): for i, st in enumerate(stracks):
@ -112,10 +113,9 @@ class BOTSORT(BYTETracker):
return [] return []
if self.args.with_reid and self.encoder is not None: if self.args.with_reid and self.encoder is not None:
features_keep = self.encoder.inference(img, dets) features_keep = self.encoder.inference(img, dets)
detections = [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)] return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)] # detections
else: else:
detections = [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] # detections
return detections
def get_dists(self, tracks, detections): def get_dists(self, tracks, detections):
dists = matching.iou_distance(tracks, detections) dists = matching.iou_distance(tracks, detections)

1
ultralytics/tracker/trackers/byte_tracker.py
Unescape View File

@ -92,7 +92,6 @@ class STrack(BaseTrack):
Update a matched track Update a matched track
:type new_track: STrack :type new_track: STrack
:type frame_id: int :type frame_id: int
:type update_feature: bool
:return: :return:
""" """
self.frame_id = frame_id self.frame_id = frame_id

12
ultralytics/tracker/utils/gmc.py
Unescape View File

@ -71,7 +71,7 @@ class GMC:
def apply(self, raw_frame, detections=None): def apply(self, raw_frame, detections=None):
if self.method in ['orb', 'sift']: if self.method in ['orb', 'sift']:
return self.applyFeaures(raw_frame, detections) return self.applyFeatures(raw_frame, detections)
elif self.method == 'ecc': elif self.method == 'ecc':
return self.applyEcc(raw_frame, detections) return self.applyEcc(raw_frame, detections)
elif self.method == 'sparseOptFlow': elif self.method == 'sparseOptFlow':
@ -116,7 +116,7 @@ class GMC:
return H return H
def applyFeaures(self, raw_frame, detections=None): def applyFeatures(self, raw_frame, detections=None):
# Initialize # Initialize
height, width, _ = raw_frame.shape height, width, _ = raw_frame.shape
@ -190,13 +190,13 @@ class GMC:
meanSpatialDistances = np.mean(spatialDistances, 0) meanSpatialDistances = np.mean(spatialDistances, 0)
stdSpatialDistances = np.std(spatialDistances, 0) stdSpatialDistances = np.std(spatialDistances, 0)
inliesrs = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances inliers = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances
goodMatches = [] goodMatches = []
prevPoints = [] prevPoints = []
currPoints = [] currPoints = []
for i in range(len(matches)): for i in range(len(matches)):
if inliesrs[i, 0] and inliesrs[i, 1]: if inliers[i, 0] and inliers[i, 1]:
goodMatches.append(matches[i]) goodMatches.append(matches[i])
prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt) prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt)
currPoints.append(keypoints[matches[i].trainIdx].pt) currPoints.append(keypoints[matches[i].trainIdx].pt)
@ -226,7 +226,7 @@ class GMC:
# Find rigid matrix # Find rigid matrix
if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)): if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)):
H, inliesrs = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC) H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)
# Handle downscale # Handle downscale
if self.downscale > 1.0: if self.downscale > 1.0:
@ -285,7 +285,7 @@ class GMC:
# Find rigid matrix # Find rigid matrix
if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)): if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)):
H, inliesrs = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC) H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)
# Handle downscale # Handle downscale
if self.downscale > 1.0: if self.downscale > 1.0:

4
ultralytics/tracker/utils/kalman_filter.py
Unescape View File

@ -136,7 +136,7 @@ class KalmanFilterXYAH:
The Nx8 dimensional mean matrix of the object states at the previous The Nx8 dimensional mean matrix of the object states at the previous
time step. time step.
covariance : ndarray covariance : ndarray
The Nx8x8 dimensional covariance matrics of the object states at the The Nx8x8 dimensional covariance matrix of the object states at the
previous time step. previous time step.
Returns Returns
------- -------
@ -362,7 +362,7 @@ class KalmanFilterXYWH:
The Nx8 dimensional mean matrix of the object states at the previous The Nx8 dimensional mean matrix of the object states at the previous
time step. time step.
covariance : ndarray covariance : ndarray
The Nx8x8 dimensional covariance matrics of the object states at the The Nx8x8 dimensional covariance matrix of the object states at the
previous time step. previous time step.
Returns Returns
------- -------

2
ultralytics/tracker/utils/matching.py
Unescape View File

@ -119,7 +119,7 @@ def embedding_distance(tracks, detections, metric='cosine'):
# for i, track in enumerate(tracks): # for i, track in enumerate(tracks):
# cost_matrix[i, :] = np.maximum(0.0, cdist(track.smooth_feat.reshape(1,-1), det_features, metric)) # cost_matrix[i, :] = np.maximum(0.0, cdist(track.smooth_feat.reshape(1,-1), det_features, metric))
track_features = np.asarray([track.smooth_feat for track in tracks], dtype=np.float32) track_features = np.asarray([track.smooth_feat for track in tracks], dtype=np.float32)
cost_matrix = np.maximum(0.0, cdist(track_features, det_features, metric)) # Nomalized features cost_matrix = np.maximum(0.0, cdist(track_features, det_features, metric)) # Normalized features
return cost_matrix return cost_matrix

7
ultralytics/yolo/cfg/__init__.py
Unescape View File

@ -273,7 +273,7 @@ def entrypoint(debug=''):
return return
# Task # Task
task = overrides.get('task') task = overrides.pop('task', None)
if task and task not in TASKS: if task and task not in TASKS:
raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}") raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}")
@ -289,9 +289,8 @@ def entrypoint(debug=''):
# Task Update # Task Update
if task and task != model.task: if task and task != model.task:
LOGGER.warning(f"WARNING ⚠️ conflicting 'task={task}' passed with 'task={model.task}' model. " LOGGER.warning(f"WARNING ⚠️ conflicting 'task={task}' passed with 'task={model.task}' model. "
f'This may produce errors.') f"Ignoring 'task={task}' and updating to 'task={model.task}' to match model.")
task = task or model.task task = model.task
overrides['task'] = task
# Mode # Mode
if mode in {'predict', 'track'} and 'source' not in overrides: if mode in {'predict', 'track'} and 'source' not in overrides:

9
ultralytics/yolo/data/build.py
Unescape View File

@ -54,7 +54,7 @@ class _RepeatSampler:
yield from iter(self.sampler) yield from iter(self.sampler)
def seed_worker(worker_id): def seed_worker(worker_id): # noqa
# Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader # Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader
worker_seed = torch.initial_seed() % 2 ** 32 worker_seed = torch.initial_seed() % 2 ** 32
np.random.seed(worker_seed) np.random.seed(worker_seed)
@ -134,7 +134,7 @@ def build_classification_dataloader(path,
def check_source(source): def check_source(source):
webcam, screenshot, from_img, in_memory = False, False, False, False webcam, screenshot, from_img, in_memory = False, False, False, False
if isinstance(source, (str, int, Path)): # int for local usb carame if isinstance(source, (str, int, Path)): # int for local usb camera
source = str(source) source = str(source)
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('https://', 'http://', 'rtsp://', 'rtmp://')) is_url = source.lower().startswith(('https://', 'http://', 'rtsp://', 'rtmp://'))
@ -147,11 +147,10 @@ def check_source(source):
elif isinstance(source, (list, tuple)): elif isinstance(source, (list, tuple)):
source = autocast_list(source) # convert all list elements to PIL or np arrays source = autocast_list(source) # convert all list elements to PIL or np arrays
from_img = True from_img = True
elif isinstance(source, ((Image.Image, np.ndarray))): elif isinstance(source, (Image.Image, np.ndarray)):
from_img = True from_img = True
else: else:
raise Exception( raise TypeError('Unsupported image type. See docs for supported types https://docs.ultralytics.com/predict')
'Unsupported type encountered! See docs for supported types https://docs.ultralytics.com/predict')
return source, webcam, screenshot, from_img, in_memory return source, webcam, screenshot, from_img, in_memory

19
ultralytics/yolo/engine/exporter.py
Unescape View File

@ -215,7 +215,7 @@ class Exporter:
self.model = model self.model = model
self.file = file self.file = file
self.output_shape = tuple(y.shape) if isinstance(y, torch.Tensor) else tuple(tuple(x.shape) for x in y) self.output_shape = tuple(y.shape) if isinstance(y, torch.Tensor) else tuple(tuple(x.shape) for x in y)
self.pretty_name = self.file.stem.replace('yolo', 'YOLO') self.pretty_name = Path(self.model.yaml.get('yaml_file', self.file)).stem.replace('yolo', 'YOLO')
description = f'Ultralytics {self.pretty_name} model ' + f'trained on {Path(self.args.data).name}' \ description = f'Ultralytics {self.pretty_name} model ' + f'trained on {Path(self.args.data).name}' \
if self.args.data else '(untrained)' if self.args.data else '(untrained)'
self.metadata = { self.metadata = {
@ -225,6 +225,8 @@ class Exporter:
'version': __version__, 'version': __version__,
'stride': int(max(model.stride)), 'stride': int(max(model.stride)),
'task': model.task, 'task': model.task,
'batch': self.args.batch,
'imgsz': self.imgsz,
'names': model.names} # model metadata 'names': model.names} # model metadata
LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with input shape {tuple(im.shape)} BCHW and " LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with input shape {tuple(im.shape)} BCHW and "
@ -283,8 +285,7 @@ class Exporter:
f = self.file.with_suffix('.torchscript') f = self.file.with_suffix('.torchscript')
ts = torch.jit.trace(self.model, self.im, strict=False) ts = torch.jit.trace(self.model, self.im, strict=False)
d = {'shape': self.im.shape, 'stride': int(max(self.model.stride)), 'names': self.model.names} extra_files = {'config.txt': json.dumps(self.metadata)} # torch._C.ExtraFilesMap()
extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap()
if self.args.optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html if self.args.optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
LOGGER.info(f'{prefix} optimizing for mobile...') LOGGER.info(f'{prefix} optimizing for mobile...')
from torch.utils.mobile_optimizer import optimize_for_mobile from torch.utils.mobile_optimizer import optimize_for_mobile
@ -429,16 +430,18 @@ class Exporter:
classifier_config=classifier_config) classifier_config=classifier_config)
bits, mode = (8, 'kmeans_lut') if self.args.int8 else (16, 'linear') if self.args.half else (32, None) bits, mode = (8, 'kmeans_lut') if self.args.int8 else (16, 'linear') if self.args.half else (32, None)
if bits < 32: if bits < 32:
if 'kmeans' in mode:
check_requirements('scikit-learn') # scikit-learn package required for k-means quantization
ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode) ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
if self.args.nms and self.model.task == 'detect': if self.args.nms and self.model.task == 'detect':
ct_model = self._pipeline_coreml(ct_model) ct_model = self._pipeline_coreml(ct_model)
m = self.metadata # metadata dict m = self.metadata # metadata dict
ct_model.short_description = m['description'] ct_model.short_description = m.pop('description')
ct_model.author = m['author'] ct_model.author = m.pop('author')
ct_model.license = m['license'] ct_model.license = m.pop('license')
ct_model.version = m['version'] ct_model.version = m.pop('version')
ct_model.user_defined_metadata.update({k: str(v) for k, v in m.items() if k in ('stride', 'task', 'names')}) ct_model.user_defined_metadata.update({k: str(v) for k, v in m.items()})
ct_model.save(str(f)) ct_model.save(str(f))
return f, ct_model return f, ct_model

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

@ -8,8 +8,8 @@ from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, Segmentat
guess_model_task, nn) guess_model_task, nn)
from ultralytics.yolo.cfg import get_cfg from ultralytics.yolo.cfg import get_cfg
from ultralytics.yolo.engine.exporter import Exporter from ultralytics.yolo.engine.exporter import Exporter
from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, ROOT, callbacks, from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, ONLINE, RANK, ROOT,
is_git_dir, is_pip_package, yaml_load) callbacks, is_git_dir, is_pip_package, yaml_load)
from ultralytics.yolo.utils.checks import check_file, check_imgsz, check_pip_update, check_yaml from ultralytics.yolo.utils.checks import check_file, check_imgsz, check_pip_update, check_yaml
from ultralytics.yolo.utils.downloads import GITHUB_ASSET_STEMS from ultralytics.yolo.utils.downloads import GITHUB_ASSET_STEMS
from ultralytics.yolo.utils.torch_utils import smart_inference_mode from ultralytics.yolo.utils.torch_utils import smart_inference_mode
@ -157,7 +157,7 @@ class YOLO:
""" """
Inform user of ultralytics package update availability Inform user of ultralytics package update availability
""" """
if is_pip_package(): if ONLINE and is_pip_package():
check_pip_update() check_pip_update()
def reset(self): def reset(self):

10
ultralytics/yolo/engine/results.py
Unescape View File

@ -5,6 +5,7 @@ Ultralytics Results, Boxes and Masks classes for handling inference results
Usage: See https://docs.ultralytics.com/predict/ Usage: See https://docs.ultralytics.com/predict/
""" """
import pprint
from copy import deepcopy from copy import deepcopy
from functools import lru_cache from functools import lru_cache
@ -96,10 +97,11 @@ class Results:
return len(getattr(self, k)) return len(getattr(self, k))
def __str__(self): def __str__(self):
return ''.join(getattr(self, k).__str__() for k in self._keys) attr = {k: v for k, v in vars(self).items() if not isinstance(v, type(self))}
return pprint.pformat(attr, indent=2, width=120, depth=10, compact=True)
def __repr__(self): def __repr__(self):
return ''.join(getattr(self, k).__repr__() for k in self._keys) return self.__str__()
def __getattr__(self, attr): def __getattr__(self, attr):
name = self.__class__.__name__ name = self.__class__.__name__
@ -261,7 +263,7 @@ class Boxes:
return self.boxes.__str__() return self.boxes.__str__()
def __repr__(self): def __repr__(self):
return (f'Ultralytics YOLO {self.__class__} masks\n' + f'type: {type(self.boxes)}\n' + return (f'Ultralytics YOLO {self.__class__.__name__}\n' + f'type: {type(self.boxes)}\n' +
f'shape: {self.boxes.shape}\n' + f'dtype: {self.boxes.dtype}\n + {self.boxes.__repr__()}') f'shape: {self.boxes.shape}\n' + f'dtype: {self.boxes.dtype}\n + {self.boxes.__repr__()}')
def __getitem__(self, idx): def __getitem__(self, idx):
@ -337,7 +339,7 @@ class Masks:
return self.masks.__str__() return self.masks.__str__()
def __repr__(self): def __repr__(self):
return (f'Ultralytics YOLO {self.__class__} masks\n' + f'type: {type(self.masks)}\n' + return (f'Ultralytics YOLO {self.__class__.__name__}\n' + f'type: {type(self.masks)}\n' +
f'shape: {self.masks.shape}\n' + f'dtype: {self.masks.dtype}\n + {self.masks.__repr__()}') f'shape: {self.masks.shape}\n' + f'dtype: {self.masks.dtype}\n + {self.masks.__repr__()}')
def __getitem__(self, idx): def __getitem__(self, idx):

2
ultralytics/yolo/engine/validator.py
Unescape View File

@ -102,7 +102,7 @@ class BaseValidator:
model = model.half() if self.args.half else model.float() model = model.half() if self.args.half else model.float()
self.model = model self.model = model
self.loss = torch.zeros_like(trainer.loss_items, device=trainer.device) self.loss = torch.zeros_like(trainer.loss_items, device=trainer.device)
self.args.plots = trainer.epoch == trainer.epochs - 1 # always plot final epoch self.args.plots = trainer.stopper.possible_stop or (trainer.epoch == trainer.epochs - 1)
model.eval() model.eval()
else: else:
callbacks.add_integration_callbacks(self) callbacks.add_integration_callbacks(self)

7
ultralytics/yolo/utils/benchmarks.py
Unescape View File

@ -45,9 +45,10 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, hal
y = [] y = []
t0 = time.time() t0 = time.time()
for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU) for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU)
emoji = '❌' # indicates export failure emoji, filename = '❌', None # export defaults
try: try:
assert i != 11, 'paddle exports coming soon' if model.task == 'classify':
assert i != 11, 'paddle cls exports coming soon'
assert i != 9 or LINUX, 'Edge TPU export only supported on Linux' assert i != 9 or LINUX, 'Edge TPU export only supported on Linux'
if 'cpu' in device.type: if 'cpu' in device.type:
assert cpu, 'inference not supported on CPU' assert cpu, 'inference not supported on CPU'
@ -86,7 +87,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, hal
if hard_fail: if hard_fail:
assert type(e) is AssertionError, f'Benchmark hard_fail for {name}: {e}' assert type(e) is AssertionError, f'Benchmark hard_fail for {name}: {e}'
LOGGER.warning(f'ERROR ❌️ Benchmark failure for {name}: {e}') LOGGER.warning(f'ERROR ❌️ Benchmark failure for {name}: {e}')
y.append([name, emoji, None, None, None]) # mAP, t_inference y.append([name, emoji, round(file_size(filename), 1), None, None]) # mAP, t_inference
# Print results # Print results
check_yolo(device=device) # print system info check_yolo(device=device) # print system info

2
ultralytics/yolo/utils/files.py
Unescape View File

@ -70,13 +70,13 @@ def file_date(path=__file__):
def file_size(path): def file_size(path):
# Return file/dir size (MB) # Return file/dir size (MB)
if isinstance(path, (str, Path)):
mb = 1 << 20 # bytes to MiB (1024 ** 2) mb = 1 << 20 # bytes to MiB (1024 ** 2)
path = Path(path) path = Path(path)
if path.is_file(): if path.is_file():
return path.stat().st_size / mb return path.stat().st_size / mb
elif path.is_dir(): elif path.is_dir():
return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / mb return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / mb
else:
return 0.0 return 0.0

7
ultralytics/yolo/v8/segment/train.py
Unescape View File

@ -77,11 +77,18 @@ class SegLoss(Loss):
anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)
# targets # targets
try:
batch_idx = batch['batch_idx'].view(-1, 1) batch_idx = batch['batch_idx'].view(-1, 1)
targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes']), 1) targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes']), 1)
targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy
mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
except RuntimeError as e:
raise TypeError('ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.\n'
"This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, "
"i.e. 'yolo train model=yolov8n-seg.pt data=coco128.yaml'.\nVerify your dataset is a "
"correctly formatted 'segment' dataset using 'data=coco128-seg.yaml' "
'as an example.\nSee https://docs.ultralytics.com/tasks/segmentation/ for help.') from e
# pboxes # pboxes
pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4)

Write Preview
Loading…
Cancel
Save