I had success running the code with the RBC dataset as discussed in “A Practical Implementation of the Faster R-CNN Algorithm for Object Detection (Part 2 – with Python codes).” I have prepared a custom image dataset, each image having 512 x 512 dimensions and their respective bounding box coordinates. Do i need to change the VGG or ResNet architecture for the new dimensions or will the code work with any image dimensions? Kindly clarity. Many thanks.
1 post - 1 participant