Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 468e302

Browse files
committed
update readme and include transformed_test image
1 parent 42313fe commit 468e302

File tree

3 files changed

+19
-23
lines changed

3 files changed

+19
-23
lines changed

‎Cifar/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,7 @@ The original Caffe implementation can be found here : [Original Caffe implementa
4141

4242

4343
#### Models and logs
44-
-- Models and training logs can be found in [snapshot folder](https://github.com/Coderx7/SimpleNet_Pytorch/tree/master/snapshots).
44+
-- Models and training logs can be found in [snapshot folder](https://github.com/Coderx7/SimpleNet_Pytorch/tree/master/Cifar/snapshots).
4545

4646

4747

6.38 KB
Loading[フレーム]

‎README.md

Lines changed: 18 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -15,10 +15,16 @@ The pytorch implementation is also very effieicent and the whole model takes onl
1515

1616
#### Update History:
1717

18-
-- 2022: Adding ImageNet models
19-
20-
-- 2018: Initial commit
21-
18+
<pre>
19+
-- 2023 Feb 12:
20+
-- re-structured the repository, moving the old implementation into new directory named 'Cifar` and imagenet into its respective directory
21+
-- updated the old implementation to work with latest version of pytorch.
22+
-- updated the imagenet scripts/models compatible with timm and a separate version for pure pytorch uscases
23+
-- updated pretrained models with the latest results
24+
-- 2022: Adding initial ImageNet models
25+
-- 2018: Initial Pytorch implementation (for CIFAR10/100/MNIST/SVHN datasets)
26+
-- 2016: Initial model release for caffe
27+
</pre>
2228

2329

2430
The original Caffe implementation can be found here : [Original Caffe implementation - 2016](https://github.com/Coderx7/SimpleNet)
@@ -27,18 +33,15 @@ The original Caffe implementation can be found here : [Original Caffe implementa
2733

2834
| **Method** | **\#Params** | **ImageNet** | **ImageNet-Real-Labels** |
2935
| :--------------------------- | :----------: | :-----------: | :-----------: |
30-
| SimpleNetV1_imagenet(23 MB) | 5.7m | 71.50/90.05 | 78.88/93.43 |
31-
| SimpleNetV1_imagenet(13 MB) | 3m | 67.85/87.76 | 75.42/91.76 |
32-
| SimpleNetV1_imagenet(6 MB) | 1.5m | 61.39/83.36 | 69.07/88.01 |
36+
| SimpleNetV1_imagenet(38 MB) | 9.5m | 74.17/91.61 | 81.24/94.63 |
37+
| SimpleNetV1_imagenet(23 MB) | 5.7m | 71.94/90.3 | 79.12/93.68 |
38+
| SimpleNetV1_imagenet(13 MB) | 3m | 68.15/87.76 | 75.66/91.80 |
39+
| SimpleNetV1_imagenet(6 MB) | 1.5m | 61.53/83.43 | 69.11/88.10 |
3340

34-
-- After nearly 7 years I could finally get my hands on a good GPU(RTX3080) and train the model on imagenet!
35-
I used [rwightman/pytorch-image-models](https://github.com/rwightman/pytorch-image-models) repository to train the models.
36-
He did a great job by the way!
37-
I'll be updating the whole repository in the upcomming days inshaalah!
38-
SimpleNet performs very decently, it outperforms VGGNet, ResNet and even some variants of MobileNets(1-3)
39-
and its fast, very fast! (based on the model up to 2x faster).
41+
SimpleNet performs very decently, it outperforms VGGNet, variants of ResNet and MobileNets(1-3)
42+
and its fast, very fast!
4043

41-
-- The models(pytorch, onnx, jit) can be found in [imagenet models directory](https://github.com/Coderx7/SimpleNet_Pytorch/tree/master/ImageNet%20models).
44+
-- The models pretrained weights (pytorch, onnx, jit) can be found in [Release section](https://github.com/Coderx7/SimpleNet_Pytorch/releases)
4245

4346

4447
#### CIFAR10/100 Results achieved using this implementation :
@@ -69,15 +72,8 @@ and its fast, very fast! (based on the model up to 2x faster).
6972

7073

7174
#### Models and logs
72-
-- Models and training logs can be found in [snapshot folder](https://github.com/Coderx7/SimpleNet_Pytorch/tree/master/snapshots).
73-
74-
75-
76-
#### How to run ?
77-
Simply initiate the training like :
78-
`python3 main.py ./data/cifar.python --dataset cifar10 --arch simplenet --save_path ./snapshots/simplenet --epochs 540 --batch_size 100 --workers 2`
75+
-- refer to each dataset directory in the repository for further information on how to access models.
7976

80-
Note that, the initial learning rate, and optimization policy is hard coded just like caffe.
8177

8278
## Citation
8379
If you find SimpleNet useful in your research, please consider citing:

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /