villanuevab

So far the scripts at least run using python2.7 as well as TensorFlow r0.12. You can try using a virtualenv to test it out yourself. Hope this helps!

This issue is related to https://github.com/tensorflow/tensorflow/issues/7496 . This may fix your errors. If other errors occur, note that the author @balancap has updated SSD-Tensorflow but not yet pushed changes to...

Hello. Thank you for your question! Actually, although I got SSD-Tensorflow to run, I was never able to get good results. Training using this repo (unchanged), SDC-Vehicle-Detection, was more fruitful....

I am encountering the same issue after trying the same steps. I believe this is also related to #19. Is the issue that the modules are not being symlinked properly?

Hi @MarvinTeichmann, thank you for your quick response. I did try that command. I am using an Anaconda vitualenv with Python 3.6.1 and Tensorflow 1.1.0. Attempting to run `demo.py` yields:...

Ah, the code runs with Python 2.7.

Hello! Do you have updates on the code for fast inference?

@lukaspistelak the code that @MarvinTeichmann posted, i.e., ``` for image in images: feed = {image_pl: image} softmax = prediction['softmax'] output = sess.run([softmax], feed_dict=feed) ``` is for KittiSeg's `demo.py`. For KittiBox,...

[UPDATE:] My questions about `forward_graph` and `interpretation_graph` still stand, but I have since been able to get much better performance speeds by modifying my inference script. The following metrics were...

It looks like `P2` parameters are required. I am still confused by why there are parameters implying a stereo setup (e.g., `KEY_STEREO_CALIB_P2` in `kitti_dataset.py`). We run training and inference with...