Alessandro Ottaviano

@XiaoXYe thank you for your quick answer. I would have a couple of question, given the situation: 1. Do you know another method to convert a tensorflow model to pytorch?...

@XiaoXYe yes I am having a try, but I got some issues Nevertheless, thank you :)

@andreapiso I have the same question: if I train the SqueezeDet model, i.e. the detector, can I - in a second moment - have its weights as an initial starting...

> @BichenWuUCB if one is using custom data resolution and want to modify eval script, I mean "evaluate_object.cpp", do you have any ideas on how these KITTI evaluation parameters (see...

**[Update]** * Bumped cva6 with `vCLIC` additions on top of `pulp-v1`, waiting for [this PR](https://github.com/pulp-platform/cva6/pull/44) to be merged + new release @ezelioli @niwis * Waiting for CLIC to be released,...

@DiyouS, @hopang-0221 this needs a rebase and CI is not passing; can you check please?

I think your CI problem can be fixed as [here](https://iis-git.ee.ethz.ch/carfield/intel16/-/blob/aottaviano/fix-i2c-spi/.gitlab-ci.yml?ref_type=heads#L100) Just filter the error on I2C on both `us` and `ns` in [`cheshire-nonfree`](https://iis-git.ee.ethz.ch/pulp-restricted/cheshire-nonfree/-/blob/main/ci.yml?ref_type=heads#L35)

@bluewww let's not forget to update this once we verify everything on FPGA and merge back into main; this can be useful for future chips such as Astral Do we...

[Update] @yvantor assigning to you as perhaps this feature will find space during Astral development, and we will merge back findings (bugs, new tests) in Carfield as parent repository

Thanks! I will review it next week