Dmitry Kurtaev

> Yes, that has resolved it @dkurt. Basecalling results are now correct for the CRF models but I'm finding the performance much slower than expected even with the smaller models...

@iiSeymour, can you please add an empty file `bonito/openvino/__init__.py`? (see https://github.com/nanoporetech/bonito/issues/229#issuecomment-1028648476). BTW, is that possible to merge this PR? So users of pip package could use OpenVINO as well.

Hi! Please try https://github.com/nanoporetech/bonito/pull/52. It was adopted for CPU only environment

Hi! > openvino-python 2021.1 requires numpy==1.16.3, but you'll have numpy 1.19.2 which is incompatible. Please try an updated version of the branch. I modified requirements.txt so it installs `numpy==1.16.3`.

Hi, @cszn! We test this model with OpenVINO engine at https://github.com/openvinotoolkit/openvino_contrib/tree/master/modules/mo_pytorch. To keep the model tested we need to refer origin license. Can we ask to add one? Thanks in...

@cszn, just a reminder

Hi! You may find this useful: https://github.com/dkurt/qupath-extension-openvino/blob/main/src/main/java/qupath/ext/openvino/OpenVINOBundle.java. @likholat, can you please handle this issue and update Java samples?

Please take a look at updated sample https://github.com/openvinotoolkit/openvino_contrib/blob/master/modules/java_api/samples/face_detection_java_sample

Hi! First of all, please check if you training dataset has background as 0th class. If not, can you try to change `background_label_id="0"` to `background_label_id="2"` in the .xml? If it's...

@jsiebert, thanks for catching this! The thing is that by default, model has some [parameters](https://github.com/pytorch/vision/blob/d367a01a18a3ae6bee13d8be3b63fd6a581ea46f/torchvision/models/detection/mask_rcnn.py#L159-L160) named `min_size` and `max_size` (800 and 1333 are default values correspondingly ). So in PyTorch...