Holger Caesar comments

Results 10 comments of


                                            Holger Caesar

Train localization cues for different datasets

@yaoqi-zd No sorry, I haven't pursued this any further.

nuPlan paper table comparison

After looking into this we have decided to update the paper to state that your dataset provides a closed-loop planning tutorial, but no official benchmark, which is really the emphasize...

Add conv layer instead of linear layer to meet the original paper

Neither does this... [https://github.com/yenchenlin/pix2pix-tensorflow/blob/master/model.py#L280](https://github.com/yenchenlin/pix2pix-tensorflow/blob/master/model.py#L280) [https://github.com/yenchenlin/pix2pix-tensorflow/blob/master/model.py#L211](https://github.com/yenchenlin/pix2pix-tensorflow/blob/master/model.py#L211)

Applying Wasserstein (Earth Mover) distance to the project

Interesting. Could you make a PR to discuss your implementation?

[Improvement] Use tensorflow global_step instead of counter

But keep in mind that we have two optimizers (for gen. and discr.) and gen. is updated twice, whereas discr. is only updated once per minibatch. So if you want...

Weird boundaries and fixed output size

Thanks for your reply. The code I use is basically the [tutorial](https://github.com/s9xie/hed/blob/master/examples/hed/HED-tutorial.ipynb). Both your suggestion and resizing the image in Python did the job of changing the size. But even...

Testing

I second that. Actually the `train=True` flag in batch_norm already exists, but isn't used. On the other hand the batch_norm documentation says "One can set updates_collections=None to force the updates...

Testing

There seems to be a veery long conversation on this here: https://github.com/tensorflow/tensorflow/issues/1122#issuecomment-232535426 It's all a work in progress, but apparently you can use a tf.cond variable that indicates whether you...

Creating local index for viewing images online

I have the same problem. Using the code from the Git repository fixed it.