In [1]:
#http://nbviewer.ipython.org/github/lisa-lab/pylearn2/blob/master/pylearn2/scripts/tutorials/softmax_regression.ipynb
%autosave 20
Autosaving every 20 seconds
In [2]:
#PYLEARN2_DATA_PATH='/home/ubuntu/stableDisk/img/pyl2-corp'
In [3]:
dataset = """!obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
one_hot: 1,
start: 0,
stop: 50000
}"""
In [4]:
model = """!obj:pylearn2.models.softmax_regression.SoftmaxRegression {
n_classes: 10,
irange: 0.,
nvis: 784,
}"""
In [56]:
algorithm = """!obj:pylearn2.training_algorithms.bgd.BGD {
batch_size: 5000,
line_search_mode: 'exhaustive', # for bgd.BGD
conjugate: 1, # for bgd.BGD
#learning_rate: 0.1, # for sgd.SGD
monitoring_dataset:
{
'train' : *train,
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
one_hot: 1,
start: 50000,
stop: 60000
},
'test' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'test',
one_hot: 1,
}
},
termination_criterion: !obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass"
}
}"""
In [57]:
train = """!obj:pylearn2.train.Train {
dataset: &train %(dataset)s,
model: %(model)s,
algorithm: %(algorithm)s,
extensions: [
!obj:pylearn2.train_extensions.best_params.MonitorBasedSaveBest {
channel_name: 'valid_y_misclass',
save_path: "softmax_regression_best.pkl"
},
],
save_path: "softmax_regression.pkl",
save_freq: 1
}""" % locals()
In [58]:
print train
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
one_hot: 1,
start: 0,
stop: 50000
},
model: !obj:pylearn2.models.softmax_regression.SoftmaxRegression {
n_classes: 10,
irange: 0.,
nvis: 784,
},
algorithm: !obj:pylearn2.training_algorithms.bgd.BGD {
batch_size: 5000,
line_search_mode: 'exhaustive', # for bgd.BGD
conjugate: 1, # for bgd.BGD
#learning_rate: 0.1, # for sgd.SGD
monitoring_dataset:
{
'train' : *train,
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
one_hot: 1,
start: 50000,
stop: 60000
},
'test' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'test',
one_hot: 1,
}
},
termination_criterion: !obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass"
}
},
extensions: [
!obj:pylearn2.train_extensions.best_params.MonitorBasedSaveBest {
channel_name: 'valid_y_misclass',
save_path: "softmax_regression_best.pkl"
},
],
save_path: "softmax_regression.pkl",
save_freq: 1
}
In [59]:
from pylearn2.config import yaml_parse
train = yaml_parse.load(train)
train.main_loop()
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.000000 seconds
Monitored channels:
ave_grad_mult
ave_grad_size
ave_step_size
monitor_seconds_per_epoch
test_objective
test_y_col_norms_max
test_y_col_norms_mean
test_y_col_norms_min
test_y_max_max_class
test_y_mean_max_class
test_y_min_max_class
test_y_misclass
test_y_nll
test_y_row_norms_max
test_y_row_norms_mean
test_y_row_norms_min
train_objective
train_y_col_norms_max
train_y_col_norms_mean
train_y_col_norms_min
train_y_max_max_class
train_y_mean_max_class
train_y_min_max_class
train_y_misclass
train_y_nll
train_y_row_norms_max
train_y_row_norms_mean
train_y_row_norms_min
valid_objective
valid_y_col_norms_max
valid_y_col_norms_mean
valid_y_col_norms_min
valid_y_max_max_class
valid_y_mean_max_class
valid_y_min_max_class
valid_y_misclass
valid_y_nll
valid_y_row_norms_max
valid_y_row_norms_mean
valid_y_row_norms_min
Compiling accum...
graph size: 56
graph size: 52
graph size: 52
Compiling accum done. Time elapsed: 1.000000 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
ave_grad_mult: 0.0
ave_grad_size: 0.0
ave_step_size: 0.0
monitor_seconds_per_epoch: 0.0
test_objective: 2.30258509299
test_y_col_norms_max: 0.0
test_y_col_norms_mean: 0.0
test_y_col_norms_min: 0.0
test_y_max_max_class: 0.1
test_y_mean_max_class: 0.1
test_y_min_max_class: 0.1
test_y_misclass: 0.902
test_y_nll: 2.30258509299
test_y_row_norms_max: 0.0
test_y_row_norms_mean: 0.0
test_y_row_norms_min: 0.0
train_objective: 2.30258509299
train_y_col_norms_max: 0.0
train_y_col_norms_mean: 0.0
train_y_col_norms_min: 0.0
train_y_max_max_class: 0.1
train_y_mean_max_class: 0.1
train_y_min_max_class: 0.1
train_y_misclass: 0.90136
train_y_nll: 2.30258509299
train_y_row_norms_max: 0.0
train_y_row_norms_mean: 0.0
train_y_row_norms_min: 0.0
valid_objective: 2.30258509299
valid_y_col_norms_max: 0.0
valid_y_col_norms_mean: 0.0
valid_y_col_norms_min: 0.0
valid_y_max_max_class: 0.1
valid_y_mean_max_class: 0.1
valid_y_min_max_class: 0.1
valid_y_misclass: 0.9009
valid_y_nll: 2.30258509299
valid_y_row_norms_max: 0.0
valid_y_row_norms_mean: 0.0
valid_y_row_norms_min: 0.0
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 10
Examples seen: 50000
ave_grad_mult: 2.42674550538
ave_grad_size: 0.459652485838
ave_step_size: 1.1398668499
monitor_seconds_per_epoch: 32.0
test_objective: 0.291959023706
test_y_col_norms_max: 3.84736626614
test_y_col_norms_mean: 3.44938578007
test_y_col_norms_min: 2.65670626663
test_y_max_max_class: 0.999997773332
test_y_mean_max_class: 0.895789248557
test_y_min_max_class: 0.210107128255
test_y_misclass: 0.0819
test_y_nll: 0.291959023706
test_y_row_norms_max: 1.05067239091
test_y_row_norms_mean: 0.297745452803
test_y_row_norms_min: 0.0
train_objective: 0.296726579517
train_y_col_norms_max: 3.84736626614
train_y_col_norms_mean: 3.44938578007
train_y_col_norms_min: 2.65670626663
train_y_max_max_class: 0.999998983271
train_y_mean_max_class: 0.89107733902
train_y_min_max_class: 0.243243097303
train_y_misclass: 0.08262
train_y_nll: 0.296726579517
train_y_row_norms_max: 1.05067239091
train_y_row_norms_mean: 0.297745452803
train_y_row_norms_min: 0.0
valid_objective: 0.285538146975
valid_y_col_norms_max: 3.84736626614
valid_y_col_norms_mean: 3.44938578007
valid_y_col_norms_min: 2.65670626663
valid_y_max_max_class: 0.99999830798
valid_y_mean_max_class: 0.897064376308
valid_y_min_max_class: 0.248221909725
valid_y_misclass: 0.0782
valid_y_nll: 0.285538146975
valid_y_row_norms_max: 1.05067239091
valid_y_row_norms_mean: 0.297745452803
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 20
Examples seen: 100000
ave_grad_mult: 2.7229913995
ave_grad_size: 0.212862481359
ave_step_size: 0.543583064891
monitor_seconds_per_epoch: 32.0
test_objective: 0.28495499265
test_y_col_norms_max: 4.81607013697
test_y_col_norms_mean: 4.21584511449
test_y_col_norms_min: 3.28219343164
test_y_max_max_class: 0.99999962323
test_y_mean_max_class: 0.905540454826
test_y_min_max_class: 0.243516228695
test_y_misclass: 0.0811
test_y_nll: 0.28495499265
test_y_row_norms_max: 1.21910206043
test_y_row_norms_mean: 0.375146708025
test_y_row_norms_min: 0.0
train_objective: 0.279943016711
train_y_col_norms_max: 4.81607013697
train_y_col_norms_mean: 4.21584511449
train_y_col_norms_min: 3.28219343164
train_y_max_max_class: 0.999999763452
train_y_mean_max_class: 0.902362408132
train_y_min_max_class: 0.242062832474
train_y_misclass: 0.079
train_y_nll: 0.279943016711
train_y_row_norms_max: 1.21910206043
train_y_row_norms_mean: 0.375146708025
train_y_row_norms_min: 0.0
valid_objective: 0.274345756676
valid_y_col_norms_max: 4.81607013697
valid_y_col_norms_mean: 4.21584511449
valid_y_col_norms_min: 3.28219343164
valid_y_max_max_class: 0.999999282252
valid_y_mean_max_class: 0.906968529641
valid_y_min_max_class: 0.244351153943
valid_y_misclass: 0.0756
valid_y_nll: 0.274345756676
valid_y_row_norms_max: 1.21910206043
valid_y_row_norms_mean: 0.375146708025
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 30
Examples seen: 150000
ave_grad_mult: 2.94688703207
ave_grad_size: 0.121585109473
ave_step_size: 0.330356515993
monitor_seconds_per_epoch: 32.0
test_objective: 0.279183324593
test_y_col_norms_max: 5.36573616676
test_y_col_norms_mean: 4.72036477412
test_y_col_norms_min: 3.76520877217
test_y_max_max_class: 0.999999747113
test_y_mean_max_class: 0.910141229869
test_y_min_max_class: 0.259831143618
test_y_misclass: 0.0794
test_y_nll: 0.279183324593
test_y_row_norms_max: 1.34711187148
test_y_row_norms_mean: 0.426050149303
test_y_row_norms_min: 0.0
train_objective: 0.269252125704
train_y_col_norms_max: 5.36573616676
train_y_col_norms_mean: 4.72036477412
train_y_col_norms_min: 3.76520877217
train_y_max_max_class: 0.999999897248
train_y_mean_max_class: 0.906503256329
train_y_min_max_class: 0.244821560716
train_y_misclass: 0.07668
train_y_nll: 0.269252125704
train_y_row_norms_max: 1.34711187148
train_y_row_norms_mean: 0.426050149303
train_y_row_norms_min: 0.0
valid_objective: 0.273166881784
valid_y_col_norms_max: 5.36573616676
valid_y_col_norms_mean: 4.72036477412
valid_y_col_norms_min: 3.76520877217
valid_y_max_max_class: 0.999999519424
valid_y_mean_max_class: 0.910427478117
valid_y_min_max_class: 0.262867277861
valid_y_misclass: 0.0772
valid_y_nll: 0.273166881784
valid_y_row_norms_max: 1.34711187148
valid_y_row_norms_mean: 0.426050149303
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 40
Examples seen: 200000
ave_grad_mult: 3.06095846462
ave_grad_size: 0.087343651465
ave_step_size: 0.25151521273
monitor_seconds_per_epoch: 32.0
test_objective: 0.281619501489
test_y_col_norms_max: 5.78970250247
test_y_col_norms_mean: 5.14848493463
test_y_col_norms_min: 4.12959171981
test_y_max_max_class: 0.999999961606
test_y_mean_max_class: 0.91227117732
test_y_min_max_class: 0.257789287314
test_y_misclass: 0.0809
test_y_nll: 0.281619501489
test_y_row_norms_max: 1.53655975006
test_y_row_norms_mean: 0.469191348662
test_y_row_norms_min: 0.0
train_objective: 0.263561800952
train_y_col_norms_max: 5.78970250247
train_y_col_norms_mean: 5.14848493463
train_y_col_norms_min: 4.12959171981
train_y_max_max_class: 0.999999986734
train_y_mean_max_class: 0.908020709496
train_y_min_max_class: 0.25291904385
train_y_misclass: 0.07402
train_y_nll: 0.263561800952
train_y_row_norms_max: 1.53655975006
train_y_row_norms_mean: 0.469191348662
train_y_row_norms_min: 0.0
valid_objective: 0.266440138565
valid_y_col_norms_max: 5.78970250247
valid_y_col_norms_mean: 5.14848493463
valid_y_col_norms_min: 4.12959171981
valid_y_max_max_class: 0.999999895147
valid_y_mean_max_class: 0.912481835757
valid_y_min_max_class: 0.252653804071
valid_y_misclass: 0.0723
valid_y_nll: 0.266440138565
valid_y_row_norms_max: 1.53655975006
valid_y_row_norms_mean: 0.469191348662
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 5
Batches seen: 50
Examples seen: 250000
ave_grad_mult: 3.11156773153
ave_grad_size: 0.0729705953681
ave_step_size: 0.218813575028
monitor_seconds_per_epoch: 32.0
test_objective: 0.279756515107
test_y_col_norms_max: 6.25005328692
test_y_col_norms_mean: 5.51725947216
test_y_col_norms_min: 4.43848919909
test_y_max_max_class: 0.999999975973
test_y_mean_max_class: 0.915923881842
test_y_min_max_class: 0.25866032752
test_y_misclass: 0.0791
test_y_nll: 0.279756515107
test_y_row_norms_max: 1.71358537767
test_y_row_norms_mean: 0.505716589803
test_y_row_norms_min: 0.0
train_objective: 0.26068183448
train_y_col_norms_max: 6.25005328692
train_y_col_norms_mean: 5.51725947216
train_y_col_norms_min: 4.43848919909
train_y_max_max_class: 0.999999982755
train_y_mean_max_class: 0.912226630764
train_y_min_max_class: 0.23877622507
train_y_misclass: 0.07398
train_y_nll: 0.26068183448
train_y_row_norms_max: 1.71358537767
train_y_row_norms_mean: 0.505716589803
train_y_row_norms_min: 0.0
valid_objective: 0.267533404828
valid_y_col_norms_max: 6.25005328692
valid_y_col_norms_mean: 5.51725947216
valid_y_col_norms_min: 4.43848919909
valid_y_max_max_class: 0.999999868684
valid_y_mean_max_class: 0.916747406348
valid_y_min_max_class: 0.256345530956
valid_y_misclass: 0.0726
valid_y_nll: 0.267533404828
valid_y_row_norms_max: 1.71358537767
valid_y_row_norms_mean: 0.505716589803
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 6
Batches seen: 60
Examples seen: 300000
ave_grad_mult: 3.19037484517
ave_grad_size: 0.0681826863739
ave_step_size: 0.212048207105
monitor_seconds_per_epoch: 32.0
test_objective: 0.278183212868
test_y_col_norms_max: 6.61773808823
test_y_col_norms_mean: 5.85265994759
test_y_col_norms_min: 4.7246947841
test_y_max_max_class: 0.999999918464
test_y_mean_max_class: 0.915942497818
test_y_min_max_class: 0.241312574319
test_y_misclass: 0.079
test_y_nll: 0.278183212868
test_y_row_norms_max: 1.81234814408
test_y_row_norms_mean: 0.53969043257
test_y_row_norms_min: 0.0
train_objective: 0.258776678906
train_y_col_norms_max: 6.61773808823
train_y_col_norms_mean: 5.85265994759
train_y_col_norms_min: 4.7246947841
train_y_max_max_class: 0.99999998314
train_y_mean_max_class: 0.912247572894
train_y_min_max_class: 0.242989029859
train_y_misclass: 0.07258
train_y_nll: 0.258776678906
train_y_row_norms_max: 1.81234814408
train_y_row_norms_mean: 0.53969043257
train_y_row_norms_min: 0.0
valid_objective: 0.269362149667
valid_y_col_norms_max: 6.61773808823
valid_y_col_norms_mean: 5.85265994759
valid_y_col_norms_min: 4.7246947841
valid_y_max_max_class: 0.999999910586
valid_y_mean_max_class: 0.916442594982
valid_y_min_max_class: 0.27889564694
valid_y_misclass: 0.0752
valid_y_nll: 0.269362149667
valid_y_row_norms_max: 1.81234814408
valid_y_row_norms_mean: 0.53969043257
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 7
Batches seen: 70
Examples seen: 350000
ave_grad_mult: 3.25427552263
ave_grad_size: 0.0662370515518
ave_step_size: 0.212437508554
monitor_seconds_per_epoch: 32.0
test_objective: 0.276463834491
test_y_col_norms_max: 6.97756305257
test_y_col_norms_mean: 6.15997134423
test_y_col_norms_min: 4.99057373458
test_y_max_max_class: 0.999999959883
test_y_mean_max_class: 0.919271641593
test_y_min_max_class: 0.232250962056
test_y_misclass: 0.0791
test_y_nll: 0.276463834491
test_y_row_norms_max: 1.94114764922
test_y_row_norms_mean: 0.569787872012
test_y_row_norms_min: 0.0
train_objective: 0.255875821731
train_y_col_norms_max: 6.97756305257
train_y_col_norms_mean: 6.15997134423
train_y_col_norms_min: 4.99057373458
train_y_max_max_class: 0.999999986761
train_y_mean_max_class: 0.915449736307
train_y_min_max_class: 0.262414542312
train_y_misclass: 0.07208
train_y_nll: 0.255875821731
train_y_row_norms_max: 1.94114764922
train_y_row_norms_mean: 0.569787872012
train_y_row_norms_min: 0.0
valid_objective: 0.269106516399
valid_y_col_norms_max: 6.97756305257
valid_y_col_norms_mean: 6.15997134423
valid_y_col_norms_min: 4.99057373458
valid_y_max_max_class: 0.99999995977
valid_y_mean_max_class: 0.91842641437
valid_y_min_max_class: 0.220829022028
valid_y_misclass: 0.0752
valid_y_nll: 0.269106516399
valid_y_row_norms_max: 1.94114764922
valid_y_row_norms_mean: 0.569787872012
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 8
Batches seen: 80
Examples seen: 400000
ave_grad_mult: 3.27272578659
ave_grad_size: 0.065193507663
ave_step_size: 0.209507843133
monitor_seconds_per_epoch: 32.0
test_objective: 0.27655215298
test_y_col_norms_max: 7.30132953922
test_y_col_norms_mean: 6.42197355156
test_y_col_norms_min: 5.15367059455
test_y_max_max_class: 0.999999963273
test_y_mean_max_class: 0.918077954229
test_y_min_max_class: 0.246185005029
test_y_misclass: 0.077
test_y_nll: 0.27655215298
test_y_row_norms_max: 2.04807659951
test_y_row_norms_mean: 0.596363333954
test_y_row_norms_min: 0.0
train_objective: 0.251294152506
train_y_col_norms_max: 7.30132953922
train_y_col_norms_mean: 6.42197355156
train_y_col_norms_min: 5.15367059455
train_y_max_max_class: 0.999999990582
train_y_mean_max_class: 0.914918757394
train_y_min_max_class: 0.253171378726
train_y_misclass: 0.07042
train_y_nll: 0.251294152506
train_y_row_norms_max: 2.04807659951
train_y_row_norms_mean: 0.596363333954
train_y_row_norms_min: 0.0
valid_objective: 0.268260895378
valid_y_col_norms_max: 7.30132953922
valid_y_col_norms_mean: 6.42197355156
valid_y_col_norms_min: 5.15367059455
valid_y_max_max_class: 0.999999877365
valid_y_mean_max_class: 0.91932733744
valid_y_min_max_class: 0.256145293681
valid_y_misclass: 0.0728
valid_y_nll: 0.268260895378
valid_y_row_norms_max: 2.04807659951
valid_y_row_norms_mean: 0.596363333954
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Time this epoch: 32.000000 seconds
Monitoring step:
Epochs seen: 9
Batches seen: 90
Examples seen: 450000
ave_grad_mult: 3.32138053996
ave_grad_size: 0.0639427431351
ave_step_size: 0.209206837815
monitor_seconds_per_epoch: 32.0
test_objective: 0.272143108687
test_y_col_norms_max: 7.57544058297
test_y_col_norms_mean: 6.69310339119
test_y_col_norms_min: 5.39333837635
test_y_max_max_class: 0.999999990598
test_y_mean_max_class: 0.921213526655
test_y_min_max_class: 0.253036742732
test_y_misclass: 0.0745
test_y_nll: 0.272143108687
test_y_row_norms_max: 2.16516164442
test_y_row_norms_mean: 0.622773151754
test_y_row_norms_min: 0.0
train_objective: 0.248213933326
train_y_col_norms_max: 7.57544058297
train_y_col_norms_mean: 6.69310339119
train_y_col_norms_min: 5.39333837635
train_y_max_max_class: 0.999999989089
train_y_mean_max_class: 0.917575466467
train_y_min_max_class: 0.25214031527
train_y_misclass: 0.06912
train_y_nll: 0.248213933326
train_y_row_norms_max: 2.16516164442
train_y_row_norms_mean: 0.622773151754
train_y_row_norms_min: 0.0
valid_objective: 0.26452645505
valid_y_col_norms_max: 7.57544058297
valid_y_col_norms_mean: 6.69310339119
valid_y_col_norms_min: 5.39333837635
valid_y_max_max_class: 0.999999980474
valid_y_mean_max_class: 0.922253206417
valid_y_min_max_class: 0.275636373003
valid_y_misclass: 0.0721
valid_y_nll: 0.26452645505
valid_y_row_norms_max: 2.16516164442
valid_y_row_norms_mean: 0.622773151754
valid_y_row_norms_min: 0.0
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
Saving to softmax_regression.pkl...
Saving to softmax_regression.pkl done. Time elapsed: 0.000000 seconds
In [50]:
!/usr/local/lib/python2.7/dist-packages/pylearn2/scripts/print_monitor.py softmax_regression_best.pkl
/usr/local/lib/python2.7/dist-packages/pylearn2/models/mlp.py:41: UserWarning: MLP changing the recursion limit.
warnings.warn("MLP changing the recursion limit.")
epochs seen: 27
time trained: 74.5750799179
learning_rate : 0.1
monitor_seconds_per_epoch : 1.0
test_objective : 0.525645077342
test_y_col_norms_max : 1.36876984952
test_y_col_norms_mean : 1.21279755629
test_y_col_norms_min : 0.978046018316
test_y_max_max_class : 0.998390070153
test_y_mean_max_class : 0.707043402415
test_y_min_max_class : 0.138155780862
test_y_misclass : 0.1212
test_y_nll : 0.525645077342
test_y_row_norms_max : 0.387471856771
test_y_row_norms_mean : 0.0959992478682
test_y_row_norms_min : 0.0
train_objective : 0.557478745151
train_y_col_norms_max : 1.36876984952
train_y_col_norms_mean : 1.21279755629
train_y_col_norms_min : 0.978046018316
train_y_max_max_class : 0.998155097537
train_y_mean_max_class : 0.697060251235
train_y_min_max_class : 0.156963994985
train_y_misclass : 0.13368
train_y_nll : 0.557478745151
train_y_row_norms_max : 0.387471856771
train_y_row_norms_mean : 0.0959992478682
train_y_row_norms_min : 0.0
valid_objective : 0.510181701317
valid_y_col_norms_max : 1.36876984952
valid_y_col_norms_mean : 1.21279755629
valid_y_col_norms_min : 0.978046018316
valid_y_max_max_class : 0.999280479451
valid_y_mean_max_class : 0.71345600523
valid_y_min_max_class : 0.164950385055
valid_y_misclass : 0.1182
valid_y_nll : 0.510181701317
valid_y_row_norms_max : 0.387471856771
valid_y_row_norms_mean : 0.0959992478682
valid_y_row_norms_min : 0.0
In [51]:
!/usr/local/lib/python2.7/dist-packages/pylearn2/scripts/show_weights.py softmax_regression_best.pkl
making weights report
loading model
/usr/local/lib/python2.7/dist-packages/pylearn2/models/mlp.py:41: UserWarning: MLP changing the recursion limit.
warnings.warn("MLP changing the recursion limit.")
loading done
loading dataset...
...done
smallest enc weight magnitude: 0.0
mean enc weight magnitude: 0.0247576242979
max enc weight magnitude: 0.275250196587
min norm: 0.978046018316
mean norm: 1.21279755629
max norm: 1.36876984952
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/pylearn2/scripts/show_weights.py", line 24, in <module>
main()
File "/usr/local/lib/python2.7/dist-packages/pylearn2/scripts/show_weights.py", line 19, in main
pv.show()
File "/usr/local/lib/python2.7/dist-packages/pylearn2/gui/patch_viewer.py", line 224, in show
show(self.image)
File "/usr/local/lib/python2.7/dist-packages/pylearn2/utils/image.py", line 147, in show
image.save(name)
File "/usr/local/lib/python2.7/dist-packages/PIL/Image.py", line 1439, in save
save_handler(self, fp, filename)
File "/usr/local/lib/python2.7/dist-packages/PIL/PngImagePlugin.py", line 572, in _save
ImageFile._save(im, _idat(fp, chunk), [("zip", (0,0)+im.size, 0, rawmode)])
File "/usr/local/lib/python2.7/dist-packages/PIL/ImageFile.py", line 481, in _save
e = Image._getencoder(im.mode, e, a, im.encoderconfig)
File "/usr/local/lib/python2.7/dist-packages/PIL/Image.py", line 401, in _getencoder
raise IOError("encoder %s not available" % encoder_name)
IOError: encoder zip not available
In [ ]:
Content source: ageek/pynotebooks
Similar notebooks: