adapt

adapt copied to clipboard

Default buffer size should be lower (e.g., 1000) to avoid memory error. cf. https://github.com/adapt-python/adapt/blob/3d064837e5e4120d87c0f37a782e18439e0ece66/adapt/base.py#L1083

antoinedemathelin

ModelCheckPoint problem

2

Hello, Thank you for your work. I am doing domain adaptation with DANN. I would like to save the best model using model checkpoint based on the loss value of...

redaelhail

Adapt performance degrades when using several consecuitive times

3

I defined the following DANN models. The DANN model starts performing well, then the accuracy drops (under 0.1 for some cases) for both unadapted and adapted models. Can you explain...

mmorsy1981

I am using FA wrapped around an sklearn predictor in an sklearn Pipeline. Basically Pipeline([("some_name",FA(SomePredictor()))]) fit and transform methods have signatures: [fit](https://adapt-python.github.io/adapt/generated/adapt.feature_based.FA.html#adapt.feature_based.FA.fit)(X, y[, Xt, yt, domains]) [fit_estimator](https://adapt-python.github.io/adapt/generated/adapt.feature_based.FA.html#adapt.feature_based.FA.fit_estimator)(X, y[, sample_weight, ...])...

g-simmons

I am building a tensorflow model for regression with multi-inpout. the first input is a 50*3 sequence feature, and the other input is a float tensor. The base model: ```...

HoraceLiu1010