Robin Cole

@dkhokhlov I did not

OSX Mojave 10.14.2 with Anaconda , using `venv` ``` print("python", sys.version) for module in mpl, np, pd, sklearn, tf, keras: print(module.__name__, module.__version__) python 3.6.5 |Anaconda, Inc.| (default, Apr 26 2018,...

``` absl-py==0.6.1 appnope==0.1.0 astor==0.7.1 backcall==0.1.0 bleach==3.1.0 cycler==0.10.0 decorator==4.3.0 defusedxml==0.5.0 entrypoints==0.3 environment-kernels==1.1.1 gast==0.2.1.post0 google-pasta==0.1 graphviz==0.10.1 grpcio==1.17.1 h5py==2.9.0 ipykernel==5.1.0 ipython==7.2.0 ipython-genutils==0.2.0 ipywidgets==7.4.2 jedi==0.13.2 Jinja2==2.10 jsonschema==2.6.0 jupyter==1.0.0 jupyter-client==5.2.4 jupyter-console==6.0.0 jupyter-core==4.4.0 Keras-Applications==1.0.6 Keras-Preprocessing==1.0.5 kiwisolver==1.0.1...

Yes it could be on another pi, and ideally would allow you to just add more movidius sticks as required

Also the imports raise the error: ``` ImportError Traceback (most recent call last) in () ----> 1 import dask_ml.joblib # register the distriubted backend 2 from sklearn.datasets import make_classification 3...

@anderl80 I am able to execute the entire notebook. Try putting `import dask_ml.joblib` in its own cell

I noticed that classes.txt appears to be a file that is actually specific to labelImg as discussed on https://github.com/tzutalin/labelImg#steps-yolo and not actually part of the yolo format, which is why...

I just noticed that labelimg will by default add all default labels to the classes txt file: ```dog person cat tv car meatballs marinara sauce tomato soup chicken noodle soup...

On looking at my old notes, 100 epoch looks like a sensible value https://github.com/robmarkcole/fire-detection-from-images/tree/master/pytorch/object-detection/yolov5

I think this should be straightforward, W&B also shown in https://github.com/johnolafenwa/deepstack-trainer/blob/main/tutorial.ipynb although I personally found tensorboard more useful