Manage your machine learning experiments with trixi - modular, reproducible, high fashion. An experiment infrastructure optimized for PyTorch, but flexible enough to work for your framework and your tastes.
A PyTorch implementation of Compositional coding Capsule Network based on the paper "Compositional coding capsule network with k-means routing for text classification"
A PyTorch implementation of Parameter-sharing Capsule Network based on the paper "Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification"
Is your feature request related to a problem? Please describe.
Right now it is hard to debug the validation loop cause there is no way of bypassing the training loop.
Describe the solution you'd like
Ideally some options like quick_run or gradient norm inspection could be interesting
The pytvision package consists of my datasets, models, and image transformations methods for computer vision projects. This package also containing the synthetic render methods.
Hi,
it appears that the logic of https://github.com/pytorch/tnt/blob/master/torchnet/meter/confusionmeter.py#L44
implies if the prediction is 1-d, it is always considered as a row of prediction for different input data points, rather than for different categories of a single data point.
This behavior is somehow slightly different to the description in the documentation (https://tnt.readthedoc