evaluator

[dngu7]

The evaluator needs some instructions on how to use it.

I'm testing the evaluator but the read_activations function does not accept the reference dataset. python evaluations/evaluator.py datasets/airplane.npz datasets/airplane.npz

The above command throws the below error: ValueError: missing arr_0 in npz file

Can you also advise on the right format for samples? Its not very clear from the code.

[dngu7]

Also. the sample.py does not save any samples anywhere.

sample_all = bin_pen(sample_all, args.pen_break)
print(f"sample all {sample_all} is saved!")

This code seems to be printing the whole vector ?

[wangqiang9]

Please use the correct method to read and use npz files. If you are not familiar with the relevant methods, please learn the relevant APIs yourself, such as: https://numpy.org/doc/stable/reference/generated/numpy.savez.html、 https://numpy.org/doc/stable/reference/generated/numpy.savez_compressed.html

[wangqiang9]

The evaluator needs some instructions on how to use it.

Here are the ways to use scripts for your reference: https://github.com/XDUWQ/SketchKnitter#evaluation

[dngu7]

I am following the script from your readme file, however that exact script creates the error I mentioned earlier.

Are you suggesting that I need to load and savez the dataset before calling python evaluations/evaluator.py [/path/to/reference-data]

I assumed from your script that the [/path/to/reference-data] argument would accept the dataset automatically.

Can you please re-open this issue?