Ego-motion inference problem

[yoavnaveh5]

Hello @rezama, thanks for sharing the code.

System information

• What is the top-level directory of the model you are using: models/research/vid2depth
• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
• TensorFlow installed from (source or binary): binary
• TensorFlow version (use command below): v1.4.0-19-ga52c8d9 1.4.1
• Bazel version (if compiling from source):
• CUDA/cuDNN version:cuda-9.0
• GPU model and memory: NVIDIA-SMI 384.81
• Exact command to reproduce:

Describe the problem

I am trying to test the ego-motion predictions by your trained model on the KITTI dataset. currently inference.py produces only depth estimations. can you instruct me on the needed modifications to be able to predict egomotion? thanks!!

[tensorflowbutler]

Hi There, We are checking to see if you still need help on this, as this seems to be an old issue. Please update this issue with the latest information, code snippet to reproduce your issue and error you are seeing. If we don't hear from you in the next 7 days, this issue will be closed automatically. If you don't need help on this issue any more, please consider closing this.

[rezama]

You can get egomotion predictions by passing a mode argument to the inference method:

inference_model.inference(inputs, sess, mode='egomotion')

Note that here inputs should be an image containing 3 frames, as defined here:

https://github.com/tensorflow/models/blob/20c78a9186ff3d35612f15764262f7e3e33eeae9/research/vid2depth/model.py#L345