ultralytics 8.0.72 faster Windows trainings and corrupt cache fix (#1912)
Co-authored-by: andreaswimmer <53872150+andreaswimmer@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
GitHub
@ -1,6 +1,6 @@
|
||||
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||
|
||||
__version__ = '8.0.71'
|
||||
__version__ = '8.0.72'
|
||||
|
||||
from ultralytics.hub import start
|
||||
from ultralytics.yolo.engine.model import YOLO
|
||||
|
||||
@ -87,14 +87,14 @@ Available Models:
|
||||
|
||||
### Pose
|
||||
|
||||
| Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>pose<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
||||
| ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
|
||||
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | - | 49.7 | 131.8 | 1.18 | 3.3 | 9.2 |
|
||||
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | - | 59.2 | 233.2 | 1.42 | 11.6 | 30.2 |
|
||||
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | - | 63.6 | 456.3 | 2.00 | 26.4 | 81.0 |
|
||||
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | - | 67.0 | 784.5 | 2.59 | 44.4 | 168.6 |
|
||||
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | - | 68.9 | 1607.1 | 3.73 | 69.4 | 263.2 |
|
||||
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | - | 71.5 | 4088.7 | 10.04 | 99.1 | 1066.4 |
|
||||
| Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
||||
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
|
||||
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 49.7 | 79.7 | 131.8 | 1.18 | 3.3 | 9.2 |
|
||||
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 59.2 | 85.8 | 233.2 | 1.42 | 11.6 | 30.2 |
|
||||
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 63.6 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
|
||||
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.0 | 89.9 | 784.5 | 2.59 | 44.4 | 168.6 |
|
||||
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 68.9 | 90.4 | 1607.1 | 3.73 | 69.4 | 263.2 |
|
||||
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.5 | 91.3 | 4088.7 | 10.04 | 99.1 | 1066.4 |
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
import copy
|
||||
|
||||
import cv2
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
|
||||
from ultralytics.yolo.utils import LOGGER
|
||||
@ -205,24 +204,25 @@ class GMC:
|
||||
currPoints = np.array(currPoints)
|
||||
|
||||
# Draw the keypoint matches on the output image
|
||||
if 0:
|
||||
matches_img = np.hstack((self.prevFrame, frame))
|
||||
matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR)
|
||||
W = np.size(self.prevFrame, 1)
|
||||
for m in goodMatches:
|
||||
prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
|
||||
curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
|
||||
curr_pt[0] += W
|
||||
color = np.random.randint(0, 255, 3)
|
||||
color = (int(color[0]), int(color[1]), int(color[2]))
|
||||
|
||||
matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)
|
||||
matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1)
|
||||
matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1)
|
||||
|
||||
plt.figure()
|
||||
plt.imshow(matches_img)
|
||||
plt.show()
|
||||
# if False:
|
||||
# import matplotlib.pyplot as plt
|
||||
# matches_img = np.hstack((self.prevFrame, frame))
|
||||
# matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR)
|
||||
# W = np.size(self.prevFrame, 1)
|
||||
# for m in goodMatches:
|
||||
# prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
|
||||
# curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
|
||||
# curr_pt[0] += W
|
||||
# color = np.random.randint(0, 255, 3)
|
||||
# color = (int(color[0]), int(color[1]), int(color[2]))
|
||||
#
|
||||
# matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)
|
||||
# matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1)
|
||||
# matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1)
|
||||
#
|
||||
# plt.figure()
|
||||
# plt.imshow(matches_img)
|
||||
# plt.show()
|
||||
|
||||
# Find rigid matrix
|
||||
if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)):
|
||||
|
||||
@ -28,7 +28,7 @@ single_cls: False # train multi-class data as single-class
|
||||
image_weights: False # use weighted image selection for training
|
||||
rect: False # rectangular training if mode='train' or rectangular validation if mode='val'
|
||||
cos_lr: False # use cosine learning rate scheduler
|
||||
close_mosaic: 10 # disable mosaic augmentation for final 10 epochs
|
||||
close_mosaic: 0 # (int) disable mosaic augmentation for final epochs
|
||||
resume: False # resume training from last checkpoint
|
||||
amp: True # Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
|
||||
# Segmentation
|
||||
|
||||
@ -162,7 +162,18 @@ def check_source(source):
|
||||
|
||||
def load_inference_source(source=None, transforms=None, imgsz=640, vid_stride=1, stride=32, auto=True):
|
||||
"""
|
||||
TODO: docs
|
||||
Loads an inference source for object detection and applies necessary transformations.
|
||||
|
||||
Args:
|
||||
source (str, Path, Tensor, PIL.Image, np.ndarray): The input source for inference.
|
||||
transforms (callable, optional): Custom transformations to be applied to the input source.
|
||||
imgsz (int, optional): The size of the image for inference. Default is 640.
|
||||
vid_stride (int, optional): The frame interval for video sources. Default is 1.
|
||||
stride (int, optional): The model stride. Default is 32.
|
||||
auto (bool, optional): Automatically apply pre-processing. Default is True.
|
||||
|
||||
Returns:
|
||||
dataset: A dataset object for the specified input source.
|
||||
"""
|
||||
source, webcam, screenshot, from_img, in_memory, tensor = check_source(source)
|
||||
source_type = source.source_type if in_memory else SourceTypes(webcam, screenshot, from_img, tensor)
|
||||
@ -179,7 +190,6 @@ def load_inference_source(source=None, transforms=None, imgsz=640, vid_stride=1,
|
||||
auto=auto,
|
||||
transforms=transforms,
|
||||
vid_stride=vid_stride)
|
||||
|
||||
elif screenshot:
|
||||
dataset = LoadScreenshots(source, imgsz=imgsz, stride=stride, auto=auto, transforms=transforms)
|
||||
elif from_img:
|
||||
@ -192,6 +202,7 @@ def load_inference_source(source=None, transforms=None, imgsz=640, vid_stride=1,
|
||||
transforms=transforms,
|
||||
vid_stride=vid_stride)
|
||||
|
||||
setattr(dataset, 'source_type', source_type) # attach source types
|
||||
# Attach source types to the dataset
|
||||
setattr(dataset, 'source_type', source_type)
|
||||
|
||||
return dataset
|
||||
|
||||
@ -77,7 +77,6 @@ class YOLODataset(BaseDataset):
|
||||
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
|
||||
desc = f'{self.prefix}Scanning {path.parent / path.stem}...'
|
||||
total = len(self.im_files)
|
||||
nc = len(self.data['names'])
|
||||
nkpt, ndim = self.data.get('kpt_shape', (0, 0))
|
||||
if self.use_keypoints and (nkpt <= 0 or ndim not in (2, 3)):
|
||||
raise ValueError("'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
|
||||
|
||||
@ -253,10 +253,10 @@ class YOLO:
|
||||
source (str, optional): The input source for object tracking. Can be a file path or a video stream.
|
||||
stream (bool, optional): Whether the input source is a video stream. Defaults to False.
|
||||
persist (bool, optional): Whether to persist the trackers if they already exist. Defaults to False.
|
||||
**kwargs: Additional keyword arguments for the tracking process.
|
||||
**kwargs (optional): Additional keyword arguments for the tracking process.
|
||||
|
||||
Returns:
|
||||
object: The tracking results.
|
||||
(List[ultralytics.yolo.engine.results.Results]): The tracking results.
|
||||
|
||||
"""
|
||||
if not hasattr(self.predictor, 'trackers'):
|
||||
|
||||
@ -244,8 +244,7 @@ class Boxes(BaseTensor):
|
||||
orig_shape (tuple): Original image size, in the format (height, width).
|
||||
|
||||
Attributes:
|
||||
boxes (torch.Tensor) or (numpy.ndarray): A tensor or numpy array containing the detection boxes,
|
||||
with shape (num_boxes, 6).
|
||||
boxes (torch.Tensor) or (numpy.ndarray): The detection boxes with shape (num_boxes, 6).
|
||||
orig_shape (torch.Tensor) or (numpy.ndarray): Original image size, in the format (height, width).
|
||||
is_track (bool): True if the boxes also include track IDs, False otherwise.
|
||||
|
||||
@ -272,7 +271,6 @@ class Boxes(BaseTensor):
|
||||
boxes = boxes[None, :]
|
||||
n = boxes.shape[-1]
|
||||
assert n in (6, 7), f'expected `n` in [6, 7], but got {n}' # xyxy, (track_id), conf, cls
|
||||
# TODO
|
||||
self.is_track = n == 7
|
||||
self.boxes = boxes
|
||||
self.orig_shape = torch.as_tensor(orig_shape, device=boxes.device) if isinstance(boxes, torch.Tensor) \
|
||||
|
||||
@ -102,6 +102,7 @@ np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})
|
||||
cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
|
||||
os.environ['NUMEXPR_MAX_THREADS'] = str(NUM_THREADS) # NumExpr max threads
|
||||
os.environ['CUBLAS_WORKSPACE_CONFIG'] = ':4096:8' # for deterministic training
|
||||
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # suppress verbose TF compiler warnings in Colab
|
||||
|
||||
|
||||
class SimpleClass:
|
||||
|
||||
Reference in New Issue
Block a user