iSee is a Mobile Deep-Learning based App for visually Impaired persons
The App helps a person who is visually-impaired to better understand who and what is going on
around them.
1. Developed a Classifier software to classify 1000 different objects.
Fine-Tuning pre-trained ConvNet model (inception-v2) on TensorFlow.
Model evaluation: 91.8% Accuracy.
2. Developed an Image Captioning software.
Image captioning model is a deep neural network that learns how to describe the content of
images. It`s a TensorFlow implementation of the image-to-text model described in the
paper:"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge."
اسم المستقل | محمد ع. |
عدد الإعجابات | 0 |
عدد المشاهدات | 220 |
تاريخ الإضافة | |
تاريخ الإنجاز |