Matteo Fabbri comments

Results 9 comments of


                                            Matteo Fabbri

The code does not inhibit the learning process of the discriminator

@jacobgil i am confused by the fact that if you run: > model.summary() before and after the command .trainable=False you can see that the number of trainable parameters does not...

Wrong flow on human limbs

Did you solve this issue?

Debug New Code

Hi Simone! Unfortunately, as far as I know, there is no way to debug the code. What you can do is to log stuff on a file!

How to set the CAMERA_PARAMS

Have a look at [this](https://github.com/fabbrimatteo/LoCO/issues/7#issuecomment-764556723).

Could not find a version that satisfies the requirement graphviz>2.40.1

Is the script still valid?

Yes sure! You simply need to recompile it

When will the image depth information be uploaded?

We are working on that. Hope to release them soon!

When will the image depth information be uploaded?

You can find pose annotations in the COCO-style format: https://motchallenge.net/data/MOTSynth_coco_annotations.zip

why to frames need to substract 3

Yeah sorry for that. Do not skip the 3 frames.