Gilt Open Source

Say we want to build system to detect dresses in images using a deep convolutional network. What we have is a database of 64x128 pixels images that either fully contain a dress or another object (a tree, the sky, a building, a car…). With that data we train a deep convolutional network and we end up successfully with a high accuracy rate in the test set. The problem comes when trying to detect dresses on arbitrarily large images. As images from cameras are usually far larger than 64x128 pixels, the output of the last convolutional layer will also be larger. Thus, the fully connected layer won't be able to use it as the dimensions will be incompatible.