Making use of (Language model + Image model) to generate captions on flikr8k images. CNN + LSTM + Transfer learning
Image Captioning Using Deep Learning Deep Learning Application. In Which we have to pass the image to the model and the model does some processing and generating captions or descriptions as per its training. This prediction is sometimes not that much accurate and generates some meaningless sentences. We need very high computational power and a very huge dataset for better results.
Get in touch with team -> [Ghulam Abbas] (malikghulamabbas894@gmail.com)
-
Download and extract Flickr8k_Dataset.zip and Flickr8k_text.zip
-
Now, create a folder named 'ML' in root directory of your Google Drive.
-
Then upload extracted version of
Flickr8k_Dataset
andFlickr8k_text
into the ML folder. This may take times depending on your IP provider. -
Also upload the
testing_caption_generator.py
into ML folder. -
Now create a notebook in Google Colab by Image_Captioning_Using_Deep_Learning name, and copy paste Shells from
ImageCaption.ipynb
-
Then Run all the shells.
Do not use it for Commercially.