https://github.com/mrdvince/image_captioning
Automatically produce captions given an input image, using a resnet 50 as the encoder and a custom defined Decoder RNN, basically by combining a CNN for feature extraction and an RNN
https://github.com/mrdvince/image_captioning
anaconda cnn computer-vision-nanodegree exercises image-captioning miniconda python3 pytorch rnn
Last synced: 6 months ago
JSON representation
Automatically produce captions given an input image, using a resnet 50 as the encoder and a custom defined Decoder RNN, basically by combining a CNN for feature extraction and an RNN
- Host: GitHub
- URL: https://github.com/mrdvince/image_captioning
- Owner: mrdvince
- Created: 2020-06-06T12:01:36.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2021-05-09T20:25:48.000Z (over 4 years ago)
- Last Synced: 2025-02-03T14:45:56.157Z (8 months ago)
- Topics: anaconda, cnn, computer-vision-nanodegree, exercises, image-captioning, miniconda, python3, pytorch, rnn
- Language: Jupyter Notebook
- Homepage:
- Size: 280 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Captioning
# Configure and Manage Your Environment with Anaconda
Per the Anaconda [docs](http://conda.pydata.org/docs):
> Conda is an open source package management system and environment management system
for installing multiple versions of software packages and their dependencies and
switching easily between them. It works on Linux, OS X and Windows, and was created
for Python programs but can package and distribute any software.
## Overview
Using Anaconda consists of the following:
1. Install [`miniconda`](http://conda.pydata.org/miniconda.html) on your computer, by selecting the latest Python version for your operating system. If you already have `conda` or `miniconda` installed, you should be able to skip this step and move on to step 2.
2. Create and activate * a new `conda` [environment](http://conda.pydata.org/docs/using/envs.html).
\* Each time you wish to work on any exercises, activate your `conda` environment!
---
## 1. Installation
**Download** the latest version of `miniconda` that matches your system.
**NOTE**: There have been reports of issues creating an environment using miniconda `v4.3.13`. If it gives you issues try versions `4.3.11` or `4.2.12` from [here](https://repo.continuum.io/miniconda/).
| | Linux | Mac | Windows |
|--------|-------|-----|---------|
| 64-bit | [64-bit (bash installer)][lin64] | [64-bit (bash installer)][mac64] | [64-bit (exe installer)][win64]
| 32-bit | [32-bit (bash installer)][lin32] | | [32-bit (exe installer)][win32]
[win64]: https://repo.continuum.io/miniconda/Miniconda3-latest-Windows-x86_64.exe
[win32]: https://repo.continuum.io/miniconda/Miniconda3-latest-Windows-x86.exe
[mac64]: https://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
[lin64]: https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
[lin32]: https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86.sh
**Install** [miniconda](http://conda.pydata.org/miniconda.html) on your machine. Detailed instructions:
- **Linux:** http://conda.pydata.org/docs/install/quick.html#linux-miniconda-install
- **Mac:** http://conda.pydata.org/docs/install/quick.html#os-x-miniconda-install
- **Windows:** http://conda.pydata.org/docs/install/quick.html#windows-miniconda-install
## 2. Create and Activate the Environment
For Windows users, these following commands need to be executed from the **Anaconda prompt** as opposed to a Windows terminal window. For Mac, a normal terminal window will work.
#### Git and version control
These instructions also assume you have `git` installed for working with Github from a terminal window, but if you do not, you can download that first with the command:
```
conda install git
```
**Create our local environment!**
1. Clone the repository, and navigate to the downloaded folder. This may take a minute or two to clone due to the included image data.
```
https://github.com/mrdvince/image_captioning
cd image_captioning
```
2. Create (and activate) a new environment, named `imgcap` with Python 3.6. If prompted to proceed with the install `(Proceed [y]/n)` type y.
- __Linux__ or __Mac__:
```
conda create -n imgcap python=3.6
source activate imgcap
```
- __Windows__:
```
conda create --name imgcap python=3.6
activate imgcap
```
At this point your command line should look something like: `(imgcap) :image-captioning $`. The `(imgcap)` indicates that your environment has been activated, and you can proceed with further package installations.
3. Install PyTorch and torchvision; this should install the latest version of PyTorch.
- __Linux__ or __Mac__:
```
conda install pytorch torchvision -c pytorch
```
- __Windows__:
```
conda install pytorch-cpu -c pytorch
pip install torchvision
```
6. Install a few required pip packages, which are specified in the requirements text file (including OpenCV).
```
pip install -r requirements.txt
```
7. That's it!
Now all of the `imgcap` libraries are available
```
cd
cd image_captioning
python train.py -c config.json
```
### Notes on environment creation and deletion
**Verify** that the `imgcap` environment was created in your environments:
```
conda info --envs
```
**Cleanup** downloaded libraries (remove tarballs, zip files, etc):
```
conda clean -tp
```
**Uninstall** the environment (if you want); you can remove it by name:
```
conda env remove -n imgcap
```