Model Zoo
MindYOLO Model Zoo and Baselines
Detection
Name
Scale
Context
ImageSize
Dataset
Box mAP (%)
Params
FLOPs
Recipe
Download
YOLOv8
N
D910x8-G
640
MS COCO 2017
37.2
3.2M
8.7G
yaml
weights
YOLOv8
S
D910x8-G
640
MS COCO 2017
44.6
11.2M
28.6G
yaml
weights
YOLOv8
M
D910x8-G
640
MS COCO 2017
50.5
25.9M
78.9G
yaml
weights
YOLOv8
L
D910x8-G
640
MS COCO 2017
52.8
43.7M
165.2G
yaml
weights
YOLOv8
X
D910x8-G
640
MS COCO 2017
53.7
68.2M
257.8G
yaml
weights
YOLOv7
Tiny
D910x8-G
640
MS COCO 2017
37.5
6.2M
13.8G
yaml
weights
YOLOv7
L
D910x8-G
640
MS COCO 2017
50.8
36.9M
104.7G
yaml
weights
YOLOv7
X
D910x8-G
640
MS COCO 2017
52.4
71.3M
189.9G
yaml
weights
YOLOv5
N
D910x8-G
640
MS COCO 2017
27.3
1.9M
4.5G
yaml
weights
YOLOv5
S
D910x8-G
640
MS COCO 2017
37.6
7.2M
16.5G
yaml
weights
YOLOv5
M
D910x8-G
640
MS COCO 2017
44.9
21.2M
49.0G
yaml
weights
YOLOv5
L
D910x8-G
640
MS COCO 2017
48.5
46.5M
109.1G
yaml
weights
YOLOv5
X
D910x8-G
640
MS COCO 2017
50.5
86.7M
205.7G
yaml
weights
YOLOv4
CSPDarknet53
D910x8-G
608
MS COCO 2017
45.4
27.6M
52G
yaml
weights
YOLOv4
CSPDarknet53(silu)
D910x8-G
608
MS COCO 2017
45.8
27.6M
52G
yaml
weights
YOLOv3
Darknet53
D910x8-G
640
MS COCO 2017
45.5
61.9M
156.4G
yaml
weights
YOLOX
N
D910x8-G
416
MS COCO 2017
24.1
0.9M
1.1G
yaml
weights
YOLOX
Tiny
D910x8-G
416
MS COCO 2017
33.3
5.1M
6.5G
yaml
weights
YOLOX
S
D910x8-G
640
MS COCO 2017
40.7
9.0M
26.8G
yaml
weights
YOLOX
M
D910x8-G
640
MS COCO 2017
46.7
25.3M
73.8G
yaml
weights
YOLOX
L
D910x8-G
640
MS COCO 2017
49.2
54.2M
155.6G
yaml
weights
YOLOX
X
D910x8-G
640
MS COCO 2017
51.6
99.1M
281.9G
yaml
weights
YOLOX
Darknet53
D910x8-G
640
MS COCO 2017
47.7
63.7M
185.3G
yaml
weights
Segmentation
Name
Scale
Context
ImageSize
Dataset
Box mAP (%)
Mask mAP (%)
Params
FLOPs
Recipe
Download
YOLOv8-seg
X
D910x8-G
640
MS COCO 2017
52.5
42.9
71.8M
344.1G
yaml
weights
Depoly inference
Notes
Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
Box mAP: Accuracy reported on the validation set.
Back to top