Lately, I have been working on yolov3 and have been trying to train it on x-ray images to detect a fracture. However, I have decided that I would want to increase the number of convolution layers for the neural network to be more accurate. In fact, I am thinking about doubling the number of convolution layers. How should I approach this problem, should I start creating my own object detection algorithm or is there a way to double the number of convolution layers in yolov3. I want to prioritize accuracy over speed since I want to minimize the possibility of a false-positive or a false-negative. Thank you


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.