Alessandro Ottaviano

Results 29 issues of Alessandro Ottaviano

Python version: 3.7 Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.15 Destination framework with version (like CNTK 2.3 with GPU): Pytorch Pre-trained model path (webpath or webdisk...

## 🐛 Bug Hello, I am trying to quantize a model. I have done post training static quantization following the tutorial. During the conversion, I: - define my model: mymodel...

module: models.quantization

Hello, Are you using pre-trained weights to initialize your training? I am referring in particular to Mobilenetv2-ssdlite. If yes, where can I find these pre-trained weights? Thank you,

Hello, is it possible to fine tune the model? I mean the detector. For example, starting from an already trained SqueezeDet, fine-tune this model. Thank you!

Hello, What do you mean exactly by 'use only for inference'? I had a Pytorch .pth model and converted it to .onnx by performing - before conversion - the model.eval()...

* Count hit/miss/refill/evict/access events * Store in status regs

- [ ] Bump AXI-REALM to latest version - [ ] Align with cheshire main branch

bug
enhancement

* Bump CLIC to support virtualization * Bump CVA6 accordingly

enhancement

* Careful when routing the watchdog timer reset as it is a vital signal * Better to keep the watchdog disabled by default and then enable it

enhancement