Bill Ross

Scaling up

1

First issue in scaling up: Looks like one needs to analyze all the photos to train with, to get preprocess() factors like in this example: http://blog.outcome.io/pytorch-quick-start-classifying-an-image/ Seems someone would have...

other python 2.7

9

Lots of similar changes as in download issue #1 I closed with fix, plus this pattern: -- train.py < def get_pct_accuracy(pred: Variable, target) : > def get_pct_accuracy(pred, target) :

viz.py no result

2

After making the same 2.7 os.makedirs() change to viz.py as in #2, % python viz.py --load 0.677756249905 --same /Users/priot/anaconda/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may...

How wrong might this be? Gradle (per maven in README): implementation group: 'org.xerial.larray', name: 'larray_2.12', version: '0.4.0' Java: openjdk version "11.0.18" 2023-01-17 Code: new MMapBuffer(new File(floatFile), MMapMode.READ_ONLY); Full warning: WARNING:...

expected dense_10 shape (None, <dense_size>) but got array shape (<batch_size>, 1)

44

Batch size is 2048. Getting the training data from the q I see x_train, y_train = train_q.get() print('X.. ' + str(x_train.shape) + ' Y.. ' + str(y_train.shape)) X.. (2048, 2980)...

I use weighted random selection, so if the distances are already available internally, it would be nice to expose them for use in weighting rather than recalculate.