Performance numbers on TF1 OD and TF2 OD

[devloper13]

Prerequisites

Please answer the following question for yourself before submitting an issue.

• [x] I checked to make sure that this issue has not been filed already.

1. The entire URL of the documentation with the issue

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md

2. Describe the issue

I've been trying to compare the performance numbers on TF1 and TF2 OD. I'm not sure if any of the models in both are same but lets take 'faster_rcnn_resnet101_coco' for instance in TF1 OD (106ms) and 'Faster R-CNN ResNet101 V1 640x640' in TF2 OD (55ms). Why is there such a huge difference? Also It is clearly documented in TF1 OD that the results are based on Nvidia GeForce GTX TITAN X. But TF2 OD does not have any details listed.

Moreover, when I tested them I didn't get much difference in their execution speed (about 7-8 FPS in both). Please help me understand the discrepancy.

[gcunhase]

Any updates on how to calculate "Speed (ms)" in https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md ?

[Petros626]

I dont know why its so important to know the hardware, on which they've tested the models. You mentioned the GPU they used, but for TF2 just assume it was the same. Really it doesn't matter dude.