Repository files navigation

A neural network to generate captions for an image using CNN and RNN with BEAM Search.

Examples

Image Credits :Towardsdatascience

1. Requirements
2. Training parameters and results
3. Generated Captions on Test Images
4. Procedure to Train Model
5. Procedure to Test on new images
6. Configurations (config.py)
7. Frequently encountered problems
8. TODO
9. References

Recommended System Requirements to train model.

• A good CPU and a GPU with atleast 8GB memory
• Atleast 8GB of RAM
• Active internet connection so that keras can download inceptionv3/vgg16 model weights

Required libraries for Python along with their version numbers used while making & testing of this project

• Python - 3.6.7
• Numpy - 1.16.4
• Tensorflow - 1.13.1
• Keras - 2.2.4
• nltk - 3.2.5
• PIL - 4.3.0
• Matplotlib - 3.0.3
• tqdm - 4.28.1

Flickr8k Dataset:Dataset Request Form

UPDATE (April/2019): The official site seems to have been taken down (although the form still works). Here are some direct download links:

• Flickr8k_Dataset
• Flickr8k_text
Download Link Credits: Jason Brownlee

Important: After downloading the dataset, put the reqired files in train_val_data folder

• batch_size=64 took ~14GB GPU memory in case ofInceptionV3 + AlternativeRNN andVGG16 + AlternativeRNN
• batch_size=64 took ~8GB GPU memory in case ofInceptionV3 + RNN andVGG16 + RNN
• If you're low on memory, use google colab or reduce batch size
• In case of BEAM Search,loss andval_loss are same as in case of argmax since the model is same

Model used -InceptionV3 + AlternativeRNN

Image	Caption
	Argmax: A man in a blue shirt is riding a bike on a dirt path. BEAM Search, k=3: A man is riding a bicycle on a dirt path.
	Argmax: A man in a red kayak is riding down a waterfall. BEAM Search, k=3: A man on a surfboard is riding a wave.

1. Clone the repository to preserve directory structure.
   git clone https://github.com/dabasajay/Image-Caption-Generator.git
2. Put the required dataset files intrain_val_data folder (files mentioned in readme there).
3. Reviewconfig.py for paths and other configurations (explained below).
4. Runtrain_val.py.

1. Clone the repository to preserve directory structure.
   git clone https://github.com/dabasajay/Image-Caption-Generator.git
2. Train the model to generate required files inmodel_data folder (steps given above).
3. Put the test images intest_data folder.
4. Reviewconfig.py for paths and other configurations (explained below).
5. Runtest.py.

config

1. images_path :- Folder path containing flickr dataset images
2. train_data_path :- .txt file path containing images ids for training
3. val_data_path :- .txt file path containing imgage ids for validation
4. captions_path :- .txt file path containing captions
5. tokenizer_path :- path for saving tokenizer
6. model_data_path :- path for saving files related to model
7. model_load_path :- path for loading trained model
8. num_of_epochs :- Number of epochs
9. max_length :- Maximum length of captions. This is set manually after training of model and required for test.py
10. batch_size :- Batch size for training (larger will consume more GPU & CPU memory)
11. beam_search_k :- BEAM search parameter which tells the algorithm how many words to consider at a time.
12. test_data_path :- Folder path containing images for testing/inference
13. model_type :- CNN Model type to use -> inceptionv3 or vgg16
14. random_seed :- Random seed for reproducibility of results

rnnConfig

1. embedding_size :- Embedding size used in Decoder(RNN) Model
2. LSTM_units :- Number of LSTM units in Decoder(RNN) Model
3. dense_units :- Number of Dense units in Decoder(RNN) Model
4. dropout :- Dropout probability used in Dropout layer in Decoder(RNN) Model

• Out of memory issue:
  • Try reducingbatch_size
• Results differ everytime I run script:
  • Due to stochastic nature of these algoritms, resultsmay differ slightly everytime. Even though I did set random seed to make results reproducible, resultsmay differ slightly.
• Results aren't very great using beam search compared to argmax:
  • Try higherk in BEAM search usingbeam_search_k parameter in config. Note that higherk will improve results but it'll also increase inference time significantly.

• Support for VGG16 Model. Uses InceptionV3 Model by default.

• Implement 2 architectures of RNN Model.

• Support for batch processing in data generator with shuffling.

• Implement BEAM Search.

• Calculate BLEU Scores using BEAM Search.

• Implement Attention and change model architecture.

• Support for pre-trained word vectors like word2vec, GloVe etc.

• Show and Tell: A Neural Image Caption Generator - Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan
• Where to put the Image in an Image Caption Generator - Marc Tanti, Albert Gatt, Kenneth P. Camilleri
• How to Develop a Deep Learning Photo Caption Generator from Scratch