Tips and Traps¶
- Adpative pooling an generate fixed-sized output, which enables a model to handle varying sized input. The models in torchvision are such examples.
References¶
Ways to Enable and Disable Gradient in PyTorch
set_grad_enable¶
Make Your Model Training Reproducible in PyTorch
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
The PyTorch doc Reproducibility has very detailed instructions on how to make your model training reproducible. Basically, you need the following code.
torch.manual_seed(args.seed)
np.random.seed(args.seed …Resize a Tensor in PyTorch
Distance and Similarity for Machine Learning
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Cosine Similarity
Jaccard Index (Jaccard Similarity Coefficient)
Eucleadian Distance
L1 Distance
Chebyshev Distance
References
https://en.wikipedia.org/wiki/Cosine_similarity
https://en.wikipedia.org/wiki/Jaccard_index
Use XGBoost With Spark
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
The split-by-leaf mode (grow_policy="lossguide") is not supported in distributed training,
which makes XGBoost4J on Spark much slower than LightGBM on Spark.
XGBoost with Spark
https://towardsdatascience.com/build-xgboost-lightgbm-models-on-large-datasets-what-are-the-possible-solutions-bf882da2c27d
https://xgboost …