HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.3.64 new torchvision.ops access in model YAMLs (#18680)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Mohammed Yasin 2025-01-20 06:44:56 +08:00 • committed by GitHub
parent a8e2464a9c
commit 673b43ce17
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/en/models/yolov8.md
View file

@ -8,7 +8,7 @@ keywords: YOLOv8, real-time object detection, YOLO series, Ultralytics, computer
## Overview ## Overview
YOLOv8 is the latest iteration in the YOLO series of real-time object detectors, offering cutting-edge performance in terms of accuracy and speed. Building upon the advancements of previous YOLO versions, YOLOv8 introduces new features and optimizations that make it an ideal choice for various [object detection](https://www.ultralytics.com/glossary/object-detection) tasks in a wide range of applications. YOLOv8 was released by Ultralytic on January 10th, 2023, offering cutting-edge performance in terms of accuracy and speed. Building upon the advancements of previous YOLO versions, YOLOv8 introduced new features and optimizations that make it an ideal choice for various [object detection](https://www.ultralytics.com/glossary/object-detection) tasks in a wide range of applications.
![Ultralytics YOLOv8](https://github.com/ultralytics/docs/releases/download/0/yolov8-comparison-plots.avif) ![Ultralytics YOLOv8](https://github.com/ultralytics/docs/releases/download/0/yolov8-comparison-plots.avif)

2
ultralytics/__init__.py
View file

@ -1,6 +1,6 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
__version__ = "8.3.63" __version__ = "8.3.64"
import os import os

4
ultralytics/nn/modules/block.py
View file

@ -1139,10 +1139,10 @@ class TorchVision(nn.Module):
else: else:
self.m = torchvision.models.__dict__[model](pretrained=bool(weights)) self.m = torchvision.models.__dict__[model](pretrained=bool(weights))
if unwrap: if unwrap:
layers = list(self.m.children())[:-truncate] layers = list(self.m.children())
if isinstance(layers[0], nn.Sequential): # Second-level for some models like EfficientNet, Swin if isinstance(layers[0], nn.Sequential): # Second-level for some models like EfficientNet, Swin
layers = [*list(layers[0].children()), *layers[1:]] layers = [*list(layers[0].children()), *layers[1:]]
self.m = nn.Sequential(*layers) self.m = nn.Sequential(*(layers[:-truncate] if truncate else layers))
self.split = split self.split = split
else: else:
self.split = False self.split = False

8
ultralytics/nn/tasks.py
View file

@ -955,7 +955,13 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
ch = [ch] ch = [ch]
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out 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 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 m = (
getattr(torch.nn, m[3:])
if "nn." in m
else getattr(__import__("torchvision").ops, m[16:])
if "torchvision.ops." in m
else globals()[m]
) # get module
for j, a in enumerate(args): for j, a in enumerate(args):
if isinstance(a, str): if isinstance(a, str):
with contextlib.suppress(ValueError): with contextlib.suppress(ValueError):