In [1]:

    

cd ..


    

    




/afs/inf.ed.ac.uk/user/s13/s1320903/Neuroglycerin/neukrill-net-work

In [2]:

    

import pylearn2.utils
import pylearn2.config
import theano
import neukrill_net.dense_dataset
import neukrill_net.utils
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import holoviews as hl
%load_ext holoviews.ipython
import sklearn.metrics


    

    




Using gpu device 1: Tesla K40c
:0: FutureWarning: IPython widgets are experimental and may change in the future.






    




Welcome to the HoloViews IPython extension! (http://ioam.github.io/holoviews/)
Available magics: %compositor, %opts, %params, %view, %%labels, %%opts, %%view






    






<matplotlib.figure.Figure at 0x7faff9d6d7d0>






    






<matplotlib.figure.Figure at 0x7faff9d6de90>






    






<matplotlib.figure.Figure at 0x7faff9d6dc90>

In [3]:

    

m = pylearn2.utils.serial.load(
    "/disk/scratch/neuroglycerin/models/quicker_learning_1_fc_layer_experiment_no_norms_repeat_recent.pkl")


    

In [4]:

    

channel = m.monitor.channels["train_h1_kernel_norms_max"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h1_kernel_norms_min"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h1_kernel_norms_mean"]
plt.plot(channel.val_record)


    

    
Out[4]:





[<matplotlib.lines.Line2D at 0x7faff8054cd0>]






    

In [5]:

    

2 * 0.8


    

    
Out[5]:





1.6

In [6]:

    

channel = m.monitor.channels["train_h2_kernel_norms_max"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h2_kernel_norms_min"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h2_kernel_norms_mean"]
plt.plot(channel.val_record)


    

    
Out[6]:





[<matplotlib.lines.Line2D at 0x7faff7db6a10>]






    

In [7]:

    

channel = m.monitor.channels["train_h3_kernel_norms_max"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h3_kernel_norms_min"]
plt.plot(channel.val_record)
channel = m.monitor.channels["train_h3_kernel_norms_mean"]
plt.plot(channel.val_record)


    

    
Out[7]:





[<matplotlib.lines.Line2D at 0x7faff7efff90>]






    

In [8]:

    

2.25 * 0.8


    

    
Out[8]:





1.8

In [9]:

    

channel = m.monitor.channels["train_h4_col_norms_max"]
plt.plot(channel.epoch_record, channel.val_record)
channel = m.monitor.channels["train_h4_col_norms_min"]
plt.plot(channel.epoch_record, channel.val_record)
channel = m.monitor.channels["train_h4_col_norms_mean"]
plt.plot(channel.epoch_record, channel.val_record)


    

    
Out[9]:





[<matplotlib.lines.Line2D at 0x7faff7dc9d50>]






    

In [10]:

    

2.5 * 0.8


    

    
Out[10]:





2.0

In [69]:

    

m_h_aug = pylearn2.utils.serial.load(
    "/disk/scratch/neuroglycerin/models/experiment_setting_colnorms_higher_aug_recent.pkl")


    

In [70]:

    

import neukrill_net.plotting as pl
pl.monitor_channels(m_h_aug, ["valid_y_y_1_nll"], x_axis = "epoch") * pl.monitor_channels(m_h_aug, ["train_y_y_1_nll"], x_axis = "epoch")


    

    
Out[70]:

In [71]:

    

pl.monitor_channels(m_h_aug, [c for c in m.monitor.channels if "norms_mean" in c], x_axis = "epoch")


    

    
Out[71]:

In [57]:

    

m_h_lr = pylearn2.utils.serial.load(
    "/disk/scratch/neuroglycerin/models/experiment_highcolnorms_aug_lr_recent.pkl")


    

In [65]:

    

pl.monitor_channels(m_h_lr, ["valid_y_y_1_nll"], x_axis = "epoch") * pl.monitor_channels(m_h_lr, ["train_y_y_1_nll"], x_axis = "epoch")


    

    
Out[65]:

In [68]:

    

pl.monitor_channels(m_h_lr, [c for c in m.monitor.channels if "norms_mean" in c], x_axis = "epoch")


    

    
Out[68]: