I’m a novice in deep learning. I saw an implementation of attention mechanism for CNN from an article written by Analytics Vidhya available at Novel techniques to win an Image Classification hackathon (Part-3) | by Tapas Das | Analytics Vidhya | Medium
What value can be used for input_shape and ratio in “input_shape//ratio” as shown on the attached image. The input channel of the images I used is (224, 224, 3). Can these two values be gotten from this channel.
1 post - 1 participant