How long does it typically take to train a Faster RCNN model on MSCOCO on a single GPU card (e.g. K40 or 1080) using the Tensorflow Object Detection API? It would be great if you could provide training times for other models (SSD and R-FCN), too.
I have never trained a model on COCO using a single GPU --- we typically train using ~10 k40 GPUs with asynchronous SGD, which takes 3-4 days to converge on COCO. SSD and R-FCN take about the same amount of time.