antipisa
antipisa
Has this been resolved?
This is a bug when the quantized pool borders contain -/+ inf. Catboost predict cannot be called on the quantized training pool if the borders file contains inf for any...
Actually, it seems to happen even with quantized pools with finite borders. If you recreate the pool and do not quantize it works but that defeats the purpose of quantizing...
``` train_pool = Pool( data=X_train, label=y_train, group_id=qid_train, cat_features = category_index ) train_pool.quantize(border_count=10, feature_border_type='UniformAndQuantiles', random_seed=1) model = catboost.CatBoostClassifier() model.fit(train_pool) model.predict(train_pool) ```
@rianoc-kx this is on pandas 2.2.1. Could you try going over TCP/IP?
Hi @tilakrayal and @david-thrower , even with the fix mentioned above, the gradients error persists : ```python import tensorflow as tf import keras from keras.layers import Dense, Embedding, Flatten, Input,...
There is also the additional problem that if you save this model and then load and try to predict, the Lambda causes a problem because input and output shapes are...
@tilakrayal @david-thrower checking if you can repro with latest code
Ok, I think the problem is that the Lambda layer which casts to integer is non-differentiable.