Benjamin Ramhorst
Benjamin Ramhorst
Hi @HCC2620, which branch of Coyote are you using?
Could you check out this branch: https://github.com/fpgasystems/Coyote/tree/tutorial. This is a more up-to-date branch with Coyote v2. It's still experimental and not part of main, but more stable then the ACCL...
No, Coyote doesn't support for Alveo U50. The target branch mainly supports U55C, U250 and some limited support for the U280.
Closing due to inactivity. Please re-open at a later stage if still applicable.
HI @qianyich, Are there any updates on this issue? Have you managed to resolve it and get it to run? If not and using Coyote is still of interest, can...
@maximilianheer @JonasDann this is an early attempt of getting synthesis tests as part of our CI/CD running on self-hosted machines. All the checks passed, but let's not merge this just...
Fixed in this commit: https://github.com/fpgasystems/Coyote/commit/b8921b7e189bf8985fec2b40b502adac8f67970b. PR of the branch to come soon. Closing for now.
I just ran this code - removing the NumPy behaviour doesn't break prints, it breaks the line above `avg_loss = round(epoch_loss_avg.result(), 3)` in the file `dsp_aware_pruning/keras/__init__.py` (line 234). So this...
> > I just ran this code - removing the NumPy behaviour doesn't break prints, it breaks the line above `avg_loss = round(epoch_loss_avg.result(), 3)` in the file `dsp_aware_pruning/keras/__init__.py` (line 234)....
Turns out the changes in this PR have already been merged into main and DSP-aware pruning is actually broken in the main branch. My guess is that one of @calad0i...