Max C Watson
Max C Watson
The LODA paper describes an optimal method for choosing the number bins. It would be great to include that as a n_bins='auto' method.
When I perform training, models for the generator, discriminator and feature extractor are saved. When I want to perform prediction, is there a way to combine these models? How would...
In the training object, the default losses are MSE, binary cross-entropy, and MAE. Is this what the models are minimizing? If so, how can we make the losses the same...
It would be great if there's an option for embarrassingly parallel computations, especially if all N^2 distances are calculated.
It looks like all distances are currently being calculated, which is expensive. Borrowing from sklearn, BallTree and KDTree could be used to speed up nearest neighbor calculations.
I have a dense network, and when my mouse hovers over nodes, the label is sometimes obstructed by other nodes. I would love it if the text was 'on top...
Firstly, thank for creating tfimm! I am interested in using the individual blocks from a vision transformer. In torch, a common approach is to apply each block of the transformer...