Skip to content
This repository was archived by the owner on Jun 3, 2025. It is now read-only.

Commit b36eda6

Browse files
authored
yolov5 model page (#73)
1 parent 78ce50d commit b36eda6

File tree

2 files changed

+86
-0
lines changed

2 files changed

+86
-0
lines changed

docs/index.rst

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,7 @@ To learn more about Neural Magic, `check our website <https://www.neuralmagic.co
8181

8282
ResNet-50 <source/model-pages/cv-classification-resnet50>
8383
MobileNetV1 <source/model-pages/cv-classification-mobilenet>
84+
YOLOv5 <source/model-pages/cv-detection-yolov5>
8485
YOLOv3 <source/model-pages/cv-detection-yolov3>
8586
BERT <source/model-pages/nlp-bert>
8687

Lines changed: 85 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,85 @@
1+
<!--
2+
Copyright (c) 2021 - present / Neuralmagic, Inc. All Rights Reserved.
3+
4+
Licensed under the Apache License, Version 2.0 (the "License");
5+
you may not use this file except in compliance with the License.
6+
You may obtain a copy of the License at
7+
8+
http://www.apache.org/licenses/LICENSE-2.0
9+
10+
Unless required by applicable law or agreed to in writing,
11+
software distributed under the License is distributed on an "AS IS" BASIS,
12+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+
See the License for the specific language governing permissions and
14+
limitations under the License.
15+
-->
16+
17+
# YOLOv5: Sparsifying to Improve Object Detection Performance
18+
19+
Neural Magic creates models and recipes that allow anyone to plug in their data and leverage SparseML’s recipe-driven approach on top of Ultralytics’ robust training pipelines for the popular YOLOv5 object detection networks.
20+
Sparsifying involves removing redundant information from neural networks using algorithms such as pruning and quantization, among others.
21+
This sparsification process results in faster inference and smaller file sizes for deployments.
22+
23+
This page walks through the following use cases for trying out the sparsified YOLOv5 models:
24+
- Compare the differences between the models for both accuracy and inference performance
25+
- Run the models for inference in deployment or applications
26+
- Train the models on new datasets
27+
28+
## Sparse Models
29+
30+
<div style="margin-bottom: 24px; display: flex; flex-direction: column; width: auto;">
31+
<iframe style="width: 100%; max-width: 1024px; height: 256px;" src="https://sparsezoo.neuralmagic.com/widgets/models/model-card/cv%2Fdetection%2Fyolov5-l%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none" title="SparseZoo YOLOv5l Available Models" frameborder="0" ></iframe>
32+
<div style="margin-top: 8px;">
33+
<i>YOLOv5l card not loading? View card <a href="https://sparsezoo.neuralmagic.com/widgets/models/model-card/cv%2Fdetection%2Fyolov5-l%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none">here</a>.</i>
34+
</div>
35+
</div>
36+
37+
<div style="margin-bottom: 24px; display: flex; flex-direction: column; width: auto;">
38+
<iframe style="width: 100%; max-width: 1024px; height: 256px;" src="https://sparsezoo.neuralmagic.com/widgets/models/model-card/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none" title="SparseZoo YOLOv5s Available Models" frameborder="0" ></iframe>
39+
<div style="margin-top: 8px;">
40+
<i>YOLOv5s card not loading? View card <a href="https://sparsezoo.neuralmagic.com/widgets/models/model-card/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none">here</a>.</i>
41+
</div>
42+
</div>
43+
44+
## Sparse Inference
45+
46+
<div style="margin-bottom: 24px; display: flex; flex-direction: row;">
47+
<a href="https://github.com/neuralmagic/deepsparse/tree/main/examples/ultralytics-yolo#benchmarking-example" class="model-page-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
48+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-benchmark.png" alt="Benchmark" style="max-width: 160px; width: 100%;" />
49+
<div style="text-align: center;">Benchmark</div>
50+
</a>
51+
<a href="https://github.com/neuralmagic/deepsparse/tree/main/examples/ultralytics-yolo#annotation-example" class="model-page-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
52+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-example-application.png" alt="Example Application" style="max-width: 160px; width: 100%;" />
53+
<div style="text-align: center;">Example Application</div>
54+
</a>
55+
<a href="https://github.com/neuralmagic/deepsparse/tree/main/examples/ultralytics-yolo#example-yolo-deepsparse-flask-server" class="model-page-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
56+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-example-deployment.png" alt="Example Deployment" style="max-width: 160px; width: 100%;" />
57+
<div style="text-align: center;">Example Deployment</div>
58+
</a>
59+
<a class="model-page-button disable-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
60+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-comparison.png" alt="Performance Comparisons" style="max-width: 160px; width: 100%;" />
61+
<div style="text-align: center;">Performance Comparisons</div>
62+
<div class="tooltip">Coming soon!</div>
63+
</a>
64+
</div>
65+
66+
## Sparse Training
67+
68+
<div style="margin-bottom: 24px; display: flex; flex-direction: row;">
69+
<a href="https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/tutorials/yolov5_sparse_transfer_learning.md" class="model-page-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
70+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-train-transfer-learn.png" alt="Sparse Transfer Learning" style="max-width: 160px; width: 100%;" />
71+
<div style="text-align: center;">Sparse Transfer Learning</div>
72+
</a>
73+
<a href="https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/tutorials/sparsifying_yolov5_using_recipes.md" class="model-page-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
74+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-train-apply-recipe.png" alt="Applying a Recipe" style="max-width: 160px; width: 100%;" />
75+
<div style="text-align: center;">Applying a Recipe</div>
76+
</a>
77+
<a class="model-page-button disable-button" style="display: flex; flex-direction: column; margin-right: 8px; align-items: center; max-width: 196px">
78+
<img src="https://docs.neuralmagic.com/docs/source/model-pages/images/icon-train-create-recipe.png" alt="Creating a Recipe" style="max-width: 160px; width: 100%;" />
79+
<div style="text-align: center;">Creating a Recipe</div>
80+
<div class="tooltip">Coming soon!</div>
81+
</a>
82+
<a style="pointer-events: none; margin-right: 8px; width: 100%; max-width: 196px;">
83+
<!-- placeholder for 4 column grid -->
84+
</a>
85+
</div>

0 commit comments

Comments
 (0)