Rodrigo Laguna
Rodrigo Laguna
I have implemented a python class supporting sckit learn's interfaces to train my predictor using sckit learn's grid search. However, after running some time it throws this: File "/home/rodrigo/FastTextClassifier.py", line...
Hello, I'm trying to understand how does the weights get initialized. There are several implementations for encoders (mobilenet, vgg16, resnet) which are implemented on diferent modules, providing a similar operation...
- Return History object in fit operation to make this function more keras-like - Include sample on how to use it in `Readme.md` - Minor changes on code-style to make...
Great work! * remove annoying empty spaces on code samples * add alt_text on images from docs * fix copy-paste error on horizontally-vertically on data augmentation technique
Hello I'm starting to use this awesome library and noticed that several functions are not well documented, in particular, they do not provide [doc strings](https://www.python.org/dev/peps/pep-0257/#what-is-a-docstring). In addition to this, [type...
Hello I've been reading your evaluation.py example, and I can't understand why weights aren't loaded when the VGGish model is made, nor it's fit after the model is made. As...
This repo is amazing, I mean, VGG-ish is a powerfull model, but tensorflow is a little bit complicated. However, Keras is far more easier to learn. Now a days keras...
I've been reading the retinaNet tutorial and running it, it works like a charm. It was introduced in #109 by @srihari-humbarwadi, awesome work! . However, I can not underestand, and...
Hello! according to Mnih, the function phi applies a preprocessing to the last 4 frames of a history and stacks them to produce the input to the Q function, however,...
Hey! I think docs can be improved with a step by step guide on how to get the credentials properly. I found [this guy](https://morioh.com/p/c3ecc243221c) who explains it step by step,...