-
When I used ut_medium to do experiments on the finetune kinetics400 dataset, I found that categorical_cross_entropy decreased at the beginning, began to rise after 3000steps, and top1 began to decline…
-
There exist numerical instability in **objectives.categorical_crossentropy** function, which cause gradient vanishing right after the first training batch.
I suggest adding $\epsilon$ to prevent the …
-
* [x] support `score` method for use with `GridSearchCV`
* [x] use custom Ridge solver for speed and multiple regularization types (i.e., Ross's Fourier-based code)
* [x] change to positive lags for…
-
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import matplotlib.pyplot as plt
import numpy as np
(X_train, y_train), (X_test,y_test) = datasets.cifar10.load_data()
X_t…
-
Hello,
I was having problem with shap.TreeExplainer
The problem is binary classification, sample size is too small, and model predictions are all from one class
Code to reproduce:
Shap vers…
-
I am using `LGBM` for my modelling stack and trying to extract out the `shap_interaction_values` and receiving the following error:
```
ValueError: could not convert string to float:
'62||160…
-
I'd like to propose a few changes to our Formula/ModelMatrix interface:
- Make it possible to generate a model matrix in which observations are columns in addition to the current implementation in whi…
-
The sets of functions
**Preparation functions**
- [ ] Check class of columns
- [ ] Prior functions - sets prior based on class, variable and random effect
- [ ] Function assessing amount of missin…
-
Hello Aymeric,
I am sorry to bother U again.
Last few days I've asked U a question about multi-GPUs support and the low training accuracy, U said to me that maybe it's because my dataset's problem. Ho…
-
1) Make a single model predicting 0 or (1 and log revenue)
2) Make class variable for categorical values and a lot of data cleaning incldng date (Weekday/Weekend), time (Morning, Afternoon, Evening, …