StarDist now exists as a QuPath Extension,
It is included in the QuPath Common Data folder used for the BIOP QuPath Installation
There are multiple ways to get custom models into QuPath's StarDist, and the methods are evolving.
You can read about the latest ways of using it here
https://qupath.readthedocs.io/en/0.4/docs/deep/stardist.html#getting-pretrained-models
The currently no longer documented method is to convert the model folder from a StarDist training to a .pb file using tf2onnx
tf2onnxmamba create -y -n tf2onnx python=3.7
mamba activate tf2onnx
pip install -r tf2onnx.txt
Pip dependencies for converting a TF 1.15 model:
absl-py==0.14.1
astor==0.8.1
cached-property==1.5.2
certifi==2021.5.30
charset-normalizer==2.0.6
flatbuffers==1.12
gast==0.2.2
google-pasta==0.2.0
grpcio==1.41.0
h5py==3.4.0
idna==3.2
importlib-metadata==4.8.1
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.2
Markdown==3.3.4
numpy==1.21.2
onnx==1.10.1
opt-einsum==3.3.0
protobuf==3.18.0
requests==2.26.0
six==1.16.0
tensorboard==1.15.0
tensorflow==1.15.0
tensorflow-estimator==1.15.1
termcolor==1.1.0
tf2onnx==1.9.2
typing-extensions==3.10.0.2
urllib3==1.26.7
Werkzeug==2.0.1
wrapt==1.13.1
zipp==3.6.0
demo-modeltf2onnx environmentpython -m tf2onnx.convert --opset 10 --saved-model "L:\public\0-BIOP_Data\StarDist Models\demo-model" --output_frozen_graph "L:\public\0-BIOP_Data\StarDist Models\demo-model.pb"demo-model.pb