algila

preprocess_input

1

Hi, in file SSD.ipynb code line `inputs = preprocess_input(np.array(inputs))` is it not mentioned the **mode** used by the keras library. Looking in keras source file this method need a **mode**...

Hi, may you kindly communicate about the weights you provided what validation accuracy was reached ? - Restarting the training using MobileNetSSD300 on PASCALVOC2012 loading the weights on DRIVE (PASCAL...

Install nolearn with Lasagne dependance not working

2

Sorry for the disturb. I have Ubuntu 16.04 When I try to follow the suggestion to install nolearn using the command: `pip install -r https://raw.githubusercontent.com/dnouri/nolearn/master/requirements.txt` I install every dependence but...

remove('trainable') Lasagne's command doesn't work in nolearn

6

I would ask to keep working the Lasagne's command remove('trainable') needed after loading pretrained models to train those again in a modified model. I realised that this is not working...

flip_filters and pad parameter not used by NeuralNet's class

5

I would suggest to add into NeuralNet's class the Lasagne's parameters 'pad' and 'flip_filters' used in ImageNet nn like VGG or GoogleNet or ResNet today available in several library but...

Dropout in mobilenet.py

1

I see in line 299 the following line of code. `dropout=1e-3` Usually dropout in 0,2 or 0,5 apper to me very small. Is it a bug, or voluntary set at...