scikit-learn: machine learning in Python. Please feel free to ask specific questions about scikit-learn. Please try to keep the discussion focused on scikit-learn usage and immediately related open source projects from the Python ecosystem.
i..e that pixels next to each other are related
or you can use scikit-image HoG features for instance. Depending on the kinds of images, it might be enough.
Histogram of Oriented Gradients ?
yes
@glemaitre thanks
yes, you have to do feature engineering first. You can consider the 2D conv layers before the final flatten / global average pooling as a feature extractor and the last fully connected layers as a standard classifier. It's just that both the feature extraction and the classifier are trained end-to-end together
@ogrisel right.
@ogrisel that's true but I am also thinking of time series data
where it makes a big difference if two values are from successive times or not
it's only really the convolutions that take advantage of the neighborhood of pixels I suppose
No: if you have deep conv layers with downsampling (strides or max pooling for instance) the conv layers can capture large high level complex patterns that span a large receptive field.
But what I meant is that deep conv net can model non-local patterns
on an NN topic, is there software to give you a good guess at a reasonable architecture for a classification task? I saw autokeras but it's pretty heavy.
if you really want to use decision trees for image classification you might be interested in https://arxiv.org/abs/1905.10073 but this is not (and will not) be implemented in scikit-learn ;)
image classification was just interesting because the data is in 2d
@ogrisel I have read those guidelines! They seem very sensible to me
@ogrisel I read that second link too :)
