https://github.com/houseofai/alexnet

This project intends to replicate the AlexNet CNN network by strictly following the original paper.
https://github.com/houseofai/alexnet

alexnet deep-learning imagenet tensorflow2

Last synced: 5 days ago
JSON representation

This project intends to replicate the AlexNet CNN network by strictly following the original paper.

• Host: GitHub
• URL: https://github.com/houseofai/alexnet
• Owner: houseofai
• Created: 2020-10-24T11:50:44.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2020-11-14T10:43:29.000Z (about 4 years ago)
• Last Synced: 2023-07-28T08:36:00.874Z (over 1 year ago)
• Topics: alexnet, deep-learning, imagenet, tensorflow2
• Language: Python
• Homepage:
• Size: 2.35 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# AlexNet

This project intends to replicate the AlexNet CNN network by strictly following the original paper.

___

### 1. Dataset

Currently, the project is configured to be trained on *imagenette/full-size-v2*, a dataset delivered by Tensorflow. From the documentation:

> Imagenette is a subset of 10 easily classified classes from the Imagenet dataset. It was originally prepared by Jeremy Howard of FastAI. The objective behind putting together a small version of the Imagenet dataset was mainly because running new ideas/algorithms/experiments on the whole Imagenet take a lot of time. 

Link: https://github.com/fastai/imagenette 

**TODO: Find ImageNet 2010**  

Please drop me an email if you know where to find this specific dataset  

### 2. Prerequisites

- Python 3.7.9

- Tensorflow 2.3.1

```

pip install tensorflow-gpu==2.3.1

```

### 3. Setup

1. Clone the repo:

 ```

 git clone https://github.com/houseofai/alexnet.git

 ```

2. Install the 3rd party packages

```

cd alexnet/

pip install -r requirements.txt

```

### 4. Training

To train the model, launch the following command:

 ```

 python train.py

 ```

 To test the configuration on a smaller dataset:

 ```

 python train.py --conf=test

 ```

### 5. Predict

To predict class probabilities on an image:

```

python train.py --mode=predict --image=/path/to/image

```

### 6. Bibliographies: ImageNet Classification with Deep Convolutional Neural Networks

https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf