nbouberbachene
commited on
Commit
•
99528e9
1
Parent(s):
2000364
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- ILSVRC/imagenet-1k
|
5 |
+
pipeline_tag: image-classification
|
6 |
+
---
|
7 |
+
|
8 |
+
# Introduction
|
9 |
+
|
10 |
+
This repository stores the model for Alexnet, compatible with Kalray's neural network API. </br>
|
11 |
+
Please see www.github.com/kalray/kann-models-zoo for details and proper usage. </br>
|
12 |
+
|
13 |
+
# Contents
|
14 |
+
|
15 |
+
- ONNX: alexnet-torch.onnx
|
16 |
+
|
17 |
+
# Lecture note reference
|
18 |
+
|
19 |
+
- ImageNet Classification with Deep Convolutional Neural Networks, https://papers.nips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
|
20 |
+
- One weird trick for parallelizing convolutional neural networks, https://arxiv.org/pdf/1404.5997.pdf
|
21 |
+
|
22 |
+
# Repository or links references
|
23 |
+
|
24 |
+
- https://github.com/onnx/models/blob/main/vision/classification/alexnet/
|
25 |
+
- https://pytorch.org/vision/stable/models/generated/torchvision.models.alexnet.html#torchvision.models.alexnet
|
26 |
+
|
27 |
+
BibTeX entry and citation info
|
28 |
+
```
|
29 |
+
@article{ILSVRC15,
|
30 |
+
Author = {Olga Russakovsky and Jia Deng and Hao Su and Jonathan Krause and Sanjeev Satheesh and Sean Ma and Zhiheng Huang and Andrej Karpathy and Aditya Khosla and Michael Bernstein and Alexander C. Berg and Li Fei-Fei},
|
31 |
+
Title = {{ImageNet Large Scale Visual Recognition Challenge}},
|
32 |
+
Year = {2015},
|
33 |
+
journal = {International Journal of Computer Vision (IJCV)},
|
34 |
+
doi = {10.1007/s11263-015-0816-y},
|
35 |
+
volume={115},
|
36 |
+
number={3},
|
37 |
+
pages={211-252}
|
38 |
+
}
|
39 |
+
```
|
40 |
+
|
41 |
+
Author: nbouberbachene@kalrayinc.com
|