Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
The difference betwen Log Softmax and Softmax should be understood together with the loss function.
https://discuss.pytorch.org/t/what-is-the-difference-between-log-softmax-and-softmax/11801
https://discuss.pytorch.org/t/logsoftmax-vs-softmax/21386
https …
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
torchvision has implementation of popular deep learning models for computer vision.
ResNet-50 is a 50-layer Residual Neural Network.
ResNet-101 is a 101-layer Residual Neural Network.
ResNet-152 …
** Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
** Please refer to the Interpretations section of the wiki page Deep Learning.
https://github.com/slundberg/shap#methods-unified-by-shap
https://arxiv.org/pdf/1802.03888.pdf
https://github.com/slundberg/shap
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
http://www.legendu.net/misc/blog/use-xgboost-with-spark/
http://www.legendu.net/misc/blog/use-lightgbm-with-spark/
You can run Apache Ray on top of Spark via analytics-zoo …
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
The easiest way to debug a Jupyter notebook is to use the %debug magic command. Whenever you encounter an error or exception, just open a new notebook …
There are many ways to achievie groupby in HolovViews.
Directly use the groupby method of HoloViews objects!!!
Use the method HoloMap to create a dictionary of parameters to HoloViews objects.
Use the method dataset.to which has groupby option. However, it seems to me that this doesn't give me options to select which one to show. But with click and transparent parameters configured, you can achieve similar effect ...