In [6]:
%matplotlib inline
from pylearn2.config import yaml_parse
from matplotlib import pyplot as plt, cm
In [2]:
!ls /Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/multilayer_perceptron/
%cd /Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/multilayer_perceptron/
README mlp_tutorial_part_2.yaml mlp_tutorial_part_4.yaml tests
mlp_best.pkl mlp_tutorial_part_3.yaml multilayer_perceptron.ipynb
/Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/multilayer_perceptron
In [3]:
with open("mlp_tutorial_part_2.yaml", 'r') as f:
train = f.read()
hyper_params = {'train_stop' : 50000,
'valid_stop' : 60000,
'dim_h0' : 500,
'max_epochs' : 1, #10000
'save_path' : '.'}
train = train % (hyper_params)
print train
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: 50000
},
model: !obj:pylearn2.models.mlp.MLP {
layers: [
!obj:pylearn2.models.mlp.Sigmoid {
layer_name: 'h0',
dim: 500,
sparse_init: 15,
}, !obj:pylearn2.models.mlp.Softmax {
layer_name: 'y',
n_classes: 10,
irange: 0.
}
],
nvis: 784,
},
algorithm: !obj:pylearn2.training_algorithms.bgd.BGD {
batch_size: 10000,
line_search_mode: 'exhaustive',
conjugate: 1,
updates_per_batch: 10,
monitoring_dataset:
{
'train' : *train,
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 50000,
stop: 60000
},
'test' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'test',
}
},
termination_criterion: !obj:pylearn2.termination_criteria.And {
criteria: [
!obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass"
},
!obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: 1
}
]
}
},
extensions: [
!obj:pylearn2.train_extensions.best_params.MonitorBasedSaveBest {
channel_name: 'valid_y_misclass',
save_path: "./mlp_best.pkl"
},
]
}
In [4]:
train = yaml_parse.load(train)
train.main_loop()
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.316489 seconds
Monitored channels:
ave_grad_mult
ave_grad_size
ave_step_size
test_h0_col_norms_max
test_h0_col_norms_mean
test_h0_col_norms_min
test_h0_max_x_max_u
test_h0_max_x_mean_u
test_h0_max_x_min_u
test_h0_mean_x_max_u
test_h0_mean_x_mean_u
test_h0_mean_x_min_u
test_h0_min_x_max_u
test_h0_min_x_mean_u
test_h0_min_x_min_u
test_h0_range_x_max_u
test_h0_range_x_mean_u
test_h0_range_x_min_u
test_h0_row_norms_max
test_h0_row_norms_mean
test_h0_row_norms_min
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
total_seconds_last_epoch
train_h0_col_norms_max
train_h0_col_norms_mean
train_h0_col_norms_min
train_h0_max_x_max_u
train_h0_max_x_mean_u
train_h0_max_x_min_u
train_h0_mean_x_max_u
train_h0_mean_x_mean_u
train_h0_mean_x_min_u
train_h0_min_x_max_u
train_h0_min_x_mean_u
train_h0_min_x_min_u
train_h0_range_x_max_u
train_h0_range_x_mean_u
train_h0_range_x_min_u
train_h0_row_norms_max
train_h0_row_norms_mean
train_h0_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
training_seconds_this_epoch
valid_h0_col_norms_max
valid_h0_col_norms_mean
valid_h0_col_norms_min
valid_h0_max_x_max_u
valid_h0_max_x_mean_u
valid_h0_max_x_min_u
valid_h0_mean_x_max_u
valid_h0_mean_x_mean_u
valid_h0_mean_x_min_u
valid_h0_min_x_max_u
valid_h0_min_x_mean_u
valid_h0_min_x_min_u
valid_h0_range_x_max_u
valid_h0_range_x_mean_u
valid_h0_range_x_min_u
valid_h0_row_norms_max
valid_h0_row_norms_mean
valid_h0_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: 118
graph size: 113
graph size: 113
Compiling accum done. Time elapsed: 4.033446 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
test_h0_col_norms_max: 6.23503405999
test_h0_col_norms_mean: 3.82355643971
test_h0_col_norms_min: 2.06193996111
test_h0_max_x_max_u: 0.999900672858
test_h0_max_x_mean_u: 0.909941495671
test_h0_max_x_min_u: 0.508436836559
test_h0_mean_x_max_u: 0.901069905001
test_h0_mean_x_mean_u: 0.476713326581
test_h0_mean_x_min_u: 0.152832768345
test_h0_min_x_max_u: 0.480607664972
test_h0_min_x_mean_u: 0.0718067763455
test_h0_min_x_min_u: 0.000174344384626
test_h0_range_x_max_u: 0.98963074706
test_h0_range_x_mean_u: 0.838134719326
test_h0_range_x_min_u: 0.461663761987
test_h0_row_norms_max: 5.89326124667
test_h0_row_norms_mean: 2.98549156744
test_h0_row_norms_min: 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
total_seconds_last_epoch: 0.0
train_h0_col_norms_max: 6.23503405999
train_h0_col_norms_mean: 3.82355643971
train_h0_col_norms_min: 2.06193996111
train_h0_max_x_max_u: 0.999884207079
train_h0_max_x_mean_u: 0.910601234661
train_h0_max_x_min_u: 0.542480235261
train_h0_mean_x_max_u: 0.899177645344
train_h0_mean_x_mean_u: 0.477026786605
train_h0_mean_x_min_u: 0.158626428409
train_h0_min_x_max_u: 0.458495451967
train_h0_min_x_mean_u: 0.0697232989866
train_h0_min_x_min_u: 0.000107248355934
train_h0_range_x_max_u: 0.993503615767
train_h0_range_x_mean_u: 0.840877935674
train_h0_range_x_min_u: 0.432142549731
train_h0_row_norms_max: 5.89326124667
train_h0_row_norms_mean: 2.98549156744
train_h0_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
training_seconds_this_epoch: 0.0
valid_h0_col_norms_max: 6.23503405999
valid_h0_col_norms_mean: 3.82355643971
valid_h0_col_norms_min: 2.06193996111
valid_h0_max_x_max_u: 0.999902364459
valid_h0_max_x_mean_u: 0.910734674045
valid_h0_max_x_min_u: 0.505713638328
valid_h0_mean_x_max_u: 0.897212634566
valid_h0_mean_x_mean_u: 0.477113329951
valid_h0_mean_x_min_u: 0.159442692765
valid_h0_min_x_max_u: 0.474104176772
valid_h0_min_x_mean_u: 0.07068185398
valid_h0_min_x_min_u: 0.000110276493931
valid_h0_range_x_max_u: 0.994406994152
valid_h0_range_x_mean_u: 0.840052820065
valid_h0_range_x_min_u: 0.445501338425
valid_h0_row_norms_max: 5.89326124667
valid_h0_row_norms_mean: 2.98549156744
valid_h0_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
Saving to ./mlp_best.pkl...
Saving to ./mlp_best.pkl done. Time elapsed: 0.621315 seconds
Time this epoch: 0:03:22.669563
Monitoring step:
Epochs seen: 1
Batches seen: 5
Examples seen: 50000
ave_grad_mult: 0.568428376745
ave_grad_size: 0.569275215102
ave_step_size: 0.293164906817
test_h0_col_norms_max: 6.24084816402
test_h0_col_norms_mean: 3.8330191565
test_h0_col_norms_min: 2.07277098332
test_h0_max_x_max_u: 0.999797012523
test_h0_max_x_mean_u: 0.930507070205
test_h0_max_x_min_u: 0.600885181612
test_h0_mean_x_max_u: 0.86138560511
test_h0_mean_x_mean_u: 0.47684242763
test_h0_mean_x_min_u: 0.171815715135
test_h0_min_x_max_u: 0.410199041785
test_h0_min_x_mean_u: 0.0532412819482
test_h0_min_x_min_u: 0.000194870876317
test_h0_range_x_max_u: 0.995852544072
test_h0_range_x_mean_u: 0.877265788257
test_h0_range_x_min_u: 0.548945839167
test_h0_row_norms_max: 5.89793230281
test_h0_row_norms_mean: 2.99315610991
test_h0_row_norms_min: 0.00719804802815
test_objective: 0.345809614411
test_y_col_norms_max: 2.78234106666
test_y_col_norms_mean: 2.59701149502
test_y_col_norms_min: 2.3810874603
test_y_max_max_class: 0.999821373414
test_y_mean_max_class: 0.844709547442
test_y_min_max_class: 0.206097493724
test_y_misclass: 0.0964
test_y_nll: 0.345809614411
test_y_row_norms_max: 0.705822478407
test_y_row_norms_mean: 0.347877919902
test_y_row_norms_min: 0.0778698200526
total_seconds_last_epoch: 0.0
train_h0_col_norms_max: 6.24084816402
train_h0_col_norms_mean: 3.8330191565
train_h0_col_norms_min: 2.07277098332
train_h0_max_x_max_u: 0.999829597379
train_h0_max_x_mean_u: 0.931275661933
train_h0_max_x_min_u: 0.618205979121
train_h0_mean_x_max_u: 0.858717658701
train_h0_mean_x_mean_u: 0.477121657696
train_h0_mean_x_min_u: 0.178341485107
train_h0_min_x_max_u: 0.385012327626
train_h0_min_x_mean_u: 0.0521292482027
train_h0_min_x_min_u: 0.000150238486259
train_h0_range_x_max_u: 0.996723214144
train_h0_range_x_mean_u: 0.879146413731
train_h0_range_x_min_u: 0.547978559446
train_h0_row_norms_max: 5.89793230281
train_h0_row_norms_mean: 2.99315610991
train_h0_row_norms_min: 0.00719804802815
train_objective: 0.367122860086
train_y_col_norms_max: 2.78234106666
train_y_col_norms_mean: 2.59701149502
train_y_col_norms_min: 2.3810874603
train_y_max_max_class: 0.999852802841
train_y_mean_max_class: 0.837913061583
train_y_min_max_class: 0.200456685509
train_y_misclass: 0.10438
train_y_nll: 0.367122860086
train_y_row_norms_max: 0.705822478407
train_y_row_norms_mean: 0.347877919902
train_y_row_norms_min: 0.0778698200526
training_seconds_this_epoch: 202.669563
valid_h0_col_norms_max: 6.24084816402
valid_h0_col_norms_mean: 3.8330191565
valid_h0_col_norms_min: 2.07277098332
valid_h0_max_x_max_u: 0.999862677883
valid_h0_max_x_mean_u: 0.930968702242
valid_h0_max_x_min_u: 0.640350398959
valid_h0_mean_x_max_u: 0.856678213378
valid_h0_mean_x_mean_u: 0.477206979816
valid_h0_mean_x_min_u: 0.178252463979
valid_h0_min_x_max_u: 0.360575213125
valid_h0_min_x_mean_u: 0.0527645351181
valid_h0_min_x_min_u: 0.000214541742634
valid_h0_range_x_max_u: 0.997314378604
valid_h0_range_x_mean_u: 0.878204167123
valid_h0_range_x_min_u: 0.521885364154
valid_h0_row_norms_max: 5.89793230281
valid_h0_row_norms_mean: 2.99315610991
valid_h0_row_norms_min: 0.00719804802815
valid_objective: 0.334305279604
valid_y_col_norms_max: 2.78234106666
valid_y_col_norms_mean: 2.59701149502
valid_y_col_norms_min: 2.3810874603
valid_y_max_max_class: 0.999953240738
valid_y_mean_max_class: 0.84881891044
valid_y_min_max_class: 0.193943289318
valid_y_misclass: 0.0947
valid_y_nll: 0.334305279604
valid_y_row_norms_max: 0.705822478407
valid_y_row_norms_mean: 0.347877919902
valid_y_row_norms_min: 0.0778698200526
Saving to ./mlp_best.pkl...
Saving to ./mlp_best.pkl done. Time elapsed: 0.342858 seconds
In [5]:
ls
README mlp_tutorial_part_2.yaml mlp_tutorial_part_4.yaml tests/
mlp_best.pkl mlp_tutorial_part_3.yaml multilayer_perceptron.ipynb
In [9]:
%%bash
pylearn2-print-monitor mlp_best.pkl
epochs seen: 1
time trained: 218.477574825
ave_grad_mult : 0.568428376745
ave_grad_size : 0.569275215102
ave_step_size : 0.293164906817
test_h0_col_norms_max : 6.24084816402
test_h0_col_norms_mean : 3.8330191565
test_h0_col_norms_min : 2.07277098332
test_h0_max_x_max_u : 0.999797012523
test_h0_max_x_mean_u : 0.930507070205
test_h0_max_x_min_u : 0.600885181612
test_h0_mean_x_max_u : 0.86138560511
test_h0_mean_x_mean_u : 0.47684242763
test_h0_mean_x_min_u : 0.171815715135
test_h0_min_x_max_u : 0.410199041785
test_h0_min_x_mean_u : 0.0532412819482
test_h0_min_x_min_u : 0.000194870876317
test_h0_range_x_max_u : 0.995852544072
test_h0_range_x_mean_u : 0.877265788257
test_h0_range_x_min_u : 0.548945839167
test_h0_row_norms_max : 5.89793230281
test_h0_row_norms_mean : 2.99315610991
test_h0_row_norms_min : 0.00719804802815
test_objective : 0.345809614411
test_y_col_norms_max : 2.78234106666
test_y_col_norms_mean : 2.59701149502
test_y_col_norms_min : 2.3810874603
test_y_max_max_class : 0.999821373414
test_y_mean_max_class : 0.844709547442
test_y_min_max_class : 0.206097493724
test_y_misclass : 0.0964
test_y_nll : 0.345809614411
test_y_row_norms_max : 0.705822478407
test_y_row_norms_mean : 0.347877919902
test_y_row_norms_min : 0.0778698200526
total_seconds_last_epoch : 0.0
train_h0_col_norms_max : 6.24084816402
train_h0_col_norms_mean : 3.8330191565
train_h0_col_norms_min : 2.07277098332
train_h0_max_x_max_u : 0.999829597379
train_h0_max_x_mean_u : 0.931275661933
train_h0_max_x_min_u : 0.618205979121
train_h0_mean_x_max_u : 0.858717658701
train_h0_mean_x_mean_u : 0.477121657696
train_h0_mean_x_min_u : 0.178341485107
train_h0_min_x_max_u : 0.385012327626
train_h0_min_x_mean_u : 0.0521292482027
train_h0_min_x_min_u : 0.000150238486259
train_h0_range_x_max_u : 0.996723214144
train_h0_range_x_mean_u : 0.879146413731
train_h0_range_x_min_u : 0.547978559446
train_h0_row_norms_max : 5.89793230281
train_h0_row_norms_mean : 2.99315610991
train_h0_row_norms_min : 0.00719804802815
train_objective : 0.367122860086
train_y_col_norms_max : 2.78234106666
train_y_col_norms_mean : 2.59701149502
train_y_col_norms_min : 2.3810874603
train_y_max_max_class : 0.999852802841
train_y_mean_max_class : 0.837913061583
train_y_min_max_class : 0.200456685509
train_y_misclass : 0.10438
train_y_nll : 0.367122860086
train_y_row_norms_max : 0.705822478407
train_y_row_norms_mean : 0.347877919902
train_y_row_norms_min : 0.0778698200526
training_seconds_this_epoch : 202.669563
valid_h0_col_norms_max : 6.24084816402
valid_h0_col_norms_mean : 3.8330191565
valid_h0_col_norms_min : 2.07277098332
valid_h0_max_x_max_u : 0.999862677883
valid_h0_max_x_mean_u : 0.930968702242
valid_h0_max_x_min_u : 0.640350398959
valid_h0_mean_x_max_u : 0.856678213378
valid_h0_mean_x_mean_u : 0.477206979816
valid_h0_mean_x_min_u : 0.178252463979
valid_h0_min_x_max_u : 0.360575213125
valid_h0_min_x_mean_u : 0.0527645351181
valid_h0_min_x_min_u : 0.000214541742634
valid_h0_range_x_max_u : 0.997314378604
valid_h0_range_x_mean_u : 0.878204167123
valid_h0_range_x_min_u : 0.521885364154
valid_h0_row_norms_max : 5.89793230281
valid_h0_row_norms_mean : 2.99315610991
valid_h0_row_norms_min : 0.00719804802815
valid_objective : 0.334305279604
valid_y_col_norms_max : 2.78234106666
valid_y_col_norms_mean : 2.59701149502
valid_y_col_norms_min : 2.3810874603
valid_y_max_max_class : 0.999953240738
valid_y_mean_max_class : 0.84881891044
valid_y_min_max_class : 0.193943289318
valid_y_misclass : 0.0947
valid_y_nll : 0.334305279604
valid_y_row_norms_max : 0.705822478407
valid_y_row_norms_mean : 0.347877919902
valid_y_row_norms_min : 0.0778698200526
In [10]:
%%bash
pylearn2-show-weights mlp_best.pkl
making weights report
loading model
loading done
loading dataset...
...done
smallest enc weight magnitude: 0.0
mean enc weight magnitude: 0.0182802173879
max enc weight magnitude: 4.66034334324
min norm: 2.07277098332
mean norm: 3.8330191565
max norm: 6.24084816402
/bin/sh: eog: command not found
In [14]:
with open("mlp_tutorial_part_2.yaml", 'r') as f:
train = f.read()
hyper_params = {'train_stop' : 50000,
'valid_stop' : 60000,
'dim_h0' : 500,
'max_epochs' : 1, # 10000
'save_path' : '.'}
train = train % (hyper_params)
print train
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: 50000
},
model: !obj:pylearn2.models.mlp.MLP {
layers: [
!obj:pylearn2.models.mlp.Sigmoid {
layer_name: 'h0',
dim: 500,
sparse_init: 15,
}, !obj:pylearn2.models.mlp.Softmax {
layer_name: 'y',
n_classes: 10,
irange: 0.
}
],
nvis: 784,
},
algorithm: !obj:pylearn2.training_algorithms.bgd.BGD {
batch_size: 10000,
line_search_mode: 'exhaustive',
conjugate: 1,
updates_per_batch: 10,
monitoring_dataset:
{
'train' : *train,
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 50000,
stop: 60000
},
'test' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'test',
}
},
termination_criterion: !obj:pylearn2.termination_criteria.And {
criteria: [
!obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass"
},
!obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: 1
}
]
}
},
extensions: [
!obj:pylearn2.train_extensions.best_params.MonitorBasedSaveBest {
channel_name: 'valid_y_misclass',
save_path: "./mlp_best.pkl"
},
]
}
In [15]:
train = yaml_parse.load(train)
train.main_loop()
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.309946 seconds
Monitored channels:
ave_grad_mult
ave_grad_size
ave_step_size
test_h0_col_norms_max
test_h0_col_norms_mean
test_h0_col_norms_min
test_h0_max_x_max_u
test_h0_max_x_mean_u
test_h0_max_x_min_u
test_h0_mean_x_max_u
test_h0_mean_x_mean_u
test_h0_mean_x_min_u
test_h0_min_x_max_u
test_h0_min_x_mean_u
test_h0_min_x_min_u
test_h0_range_x_max_u
test_h0_range_x_mean_u
test_h0_range_x_min_u
test_h0_row_norms_max
test_h0_row_norms_mean
test_h0_row_norms_min
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
total_seconds_last_epoch
train_h0_col_norms_max
train_h0_col_norms_mean
train_h0_col_norms_min
train_h0_max_x_max_u
train_h0_max_x_mean_u
train_h0_max_x_min_u
train_h0_mean_x_max_u
train_h0_mean_x_mean_u
train_h0_mean_x_min_u
train_h0_min_x_max_u
train_h0_min_x_mean_u
train_h0_min_x_min_u
train_h0_range_x_max_u
train_h0_range_x_mean_u
train_h0_range_x_min_u
train_h0_row_norms_max
train_h0_row_norms_mean
train_h0_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
training_seconds_this_epoch
valid_h0_col_norms_max
valid_h0_col_norms_mean
valid_h0_col_norms_min
valid_h0_max_x_max_u
valid_h0_max_x_mean_u
valid_h0_max_x_min_u
valid_h0_mean_x_max_u
valid_h0_mean_x_mean_u
valid_h0_mean_x_min_u
valid_h0_min_x_max_u
valid_h0_min_x_mean_u
valid_h0_min_x_min_u
valid_h0_range_x_max_u
valid_h0_range_x_mean_u
valid_h0_range_x_min_u
valid_h0_row_norms_max
valid_h0_row_norms_mean
valid_h0_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: 118
graph size: 113
graph size: 113
Compiling accum done. Time elapsed: 3.557186 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
test_h0_col_norms_max: 6.23503405999
test_h0_col_norms_mean: 3.82355643971
test_h0_col_norms_min: 2.06193996111
test_h0_max_x_max_u: 0.999900672858
test_h0_max_x_mean_u: 0.909941495671
test_h0_max_x_min_u: 0.508436836559
test_h0_mean_x_max_u: 0.901069905001
test_h0_mean_x_mean_u: 0.476713326581
test_h0_mean_x_min_u: 0.152832768345
test_h0_min_x_max_u: 0.480607664972
test_h0_min_x_mean_u: 0.0718067763455
test_h0_min_x_min_u: 0.000174344384626
test_h0_range_x_max_u: 0.98963074706
test_h0_range_x_mean_u: 0.838134719326
test_h0_range_x_min_u: 0.461663761987
test_h0_row_norms_max: 5.89326124667
test_h0_row_norms_mean: 2.98549156744
test_h0_row_norms_min: 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
total_seconds_last_epoch: 0.0
train_h0_col_norms_max: 6.23503405999
train_h0_col_norms_mean: 3.82355643971
train_h0_col_norms_min: 2.06193996111
train_h0_max_x_max_u: 0.999884207079
train_h0_max_x_mean_u: 0.910601234661
train_h0_max_x_min_u: 0.542480235261
train_h0_mean_x_max_u: 0.899177645344
train_h0_mean_x_mean_u: 0.477026786605
train_h0_mean_x_min_u: 0.158626428409
train_h0_min_x_max_u: 0.458495451967
train_h0_min_x_mean_u: 0.0697232989866
train_h0_min_x_min_u: 0.000107248355934
train_h0_range_x_max_u: 0.993503615767
train_h0_range_x_mean_u: 0.840877935674
train_h0_range_x_min_u: 0.432142549731
train_h0_row_norms_max: 5.89326124667
train_h0_row_norms_mean: 2.98549156744
train_h0_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
training_seconds_this_epoch: 0.0
valid_h0_col_norms_max: 6.23503405999
valid_h0_col_norms_mean: 3.82355643971
valid_h0_col_norms_min: 2.06193996111
valid_h0_max_x_max_u: 0.999902364459
valid_h0_max_x_mean_u: 0.910734674045
valid_h0_max_x_min_u: 0.505713638328
valid_h0_mean_x_max_u: 0.897212634566
valid_h0_mean_x_mean_u: 0.477113329951
valid_h0_mean_x_min_u: 0.159442692765
valid_h0_min_x_max_u: 0.474104176772
valid_h0_min_x_mean_u: 0.07068185398
valid_h0_min_x_min_u: 0.000110276493931
valid_h0_range_x_max_u: 0.994406994152
valid_h0_range_x_mean_u: 0.840052820065
valid_h0_range_x_min_u: 0.445501338425
valid_h0_row_norms_max: 5.89326124667
valid_h0_row_norms_mean: 2.98549156744
valid_h0_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
Saving to ./mlp_best.pkl...
Saving to ./mlp_best.pkl done. Time elapsed: 0.650340 seconds
Time this epoch: 0:03:24.065674
Monitoring step:
Epochs seen: 1
Batches seen: 5
Examples seen: 50000
ave_grad_mult: 0.568428376745
ave_grad_size: 0.569275215102
ave_step_size: 0.293164906817
test_h0_col_norms_max: 6.24084816402
test_h0_col_norms_mean: 3.8330191565
test_h0_col_norms_min: 2.07277098332
test_h0_max_x_max_u: 0.999797012523
test_h0_max_x_mean_u: 0.930507070205
test_h0_max_x_min_u: 0.600885181612
test_h0_mean_x_max_u: 0.86138560511
test_h0_mean_x_mean_u: 0.47684242763
test_h0_mean_x_min_u: 0.171815715135
test_h0_min_x_max_u: 0.410199041785
test_h0_min_x_mean_u: 0.0532412819482
test_h0_min_x_min_u: 0.000194870876317
test_h0_range_x_max_u: 0.995852544072
test_h0_range_x_mean_u: 0.877265788257
test_h0_range_x_min_u: 0.548945839167
test_h0_row_norms_max: 5.89793230281
test_h0_row_norms_mean: 2.99315610991
test_h0_row_norms_min: 0.00719804802815
test_objective: 0.345809614411
test_y_col_norms_max: 2.78234106666
test_y_col_norms_mean: 2.59701149502
test_y_col_norms_min: 2.3810874603
test_y_max_max_class: 0.999821373414
test_y_mean_max_class: 0.844709547442
test_y_min_max_class: 0.206097493724
test_y_misclass: 0.0964
test_y_nll: 0.345809614411
test_y_row_norms_max: 0.705822478407
test_y_row_norms_mean: 0.347877919902
test_y_row_norms_min: 0.0778698200526
total_seconds_last_epoch: 0.0
train_h0_col_norms_max: 6.24084816402
train_h0_col_norms_mean: 3.8330191565
train_h0_col_norms_min: 2.07277098332
train_h0_max_x_max_u: 0.999829597379
train_h0_max_x_mean_u: 0.931275661933
train_h0_max_x_min_u: 0.618205979121
train_h0_mean_x_max_u: 0.858717658701
train_h0_mean_x_mean_u: 0.477121657696
train_h0_mean_x_min_u: 0.178341485107
train_h0_min_x_max_u: 0.385012327626
train_h0_min_x_mean_u: 0.0521292482027
train_h0_min_x_min_u: 0.000150238486259
train_h0_range_x_max_u: 0.996723214144
train_h0_range_x_mean_u: 0.879146413731
train_h0_range_x_min_u: 0.547978559446
train_h0_row_norms_max: 5.89793230281
train_h0_row_norms_mean: 2.99315610991
train_h0_row_norms_min: 0.00719804802815
train_objective: 0.367122860086
train_y_col_norms_max: 2.78234106666
train_y_col_norms_mean: 2.59701149502
train_y_col_norms_min: 2.3810874603
train_y_max_max_class: 0.999852802841
train_y_mean_max_class: 0.837913061583
train_y_min_max_class: 0.200456685509
train_y_misclass: 0.10438
train_y_nll: 0.367122860086
train_y_row_norms_max: 0.705822478407
train_y_row_norms_mean: 0.347877919902
train_y_row_norms_min: 0.0778698200526
training_seconds_this_epoch: 204.065674
valid_h0_col_norms_max: 6.24084816402
valid_h0_col_norms_mean: 3.8330191565
valid_h0_col_norms_min: 2.07277098332
valid_h0_max_x_max_u: 0.999862677883
valid_h0_max_x_mean_u: 0.930968702242
valid_h0_max_x_min_u: 0.640350398959
valid_h0_mean_x_max_u: 0.856678213378
valid_h0_mean_x_mean_u: 0.477206979816
valid_h0_mean_x_min_u: 0.178252463979
valid_h0_min_x_max_u: 0.360575213125
valid_h0_min_x_mean_u: 0.0527645351181
valid_h0_min_x_min_u: 0.000214541742634
valid_h0_range_x_max_u: 0.997314378604
valid_h0_range_x_mean_u: 0.878204167123
valid_h0_range_x_min_u: 0.521885364154
valid_h0_row_norms_max: 5.89793230281
valid_h0_row_norms_mean: 2.99315610991
valid_h0_row_norms_min: 0.00719804802815
valid_objective: 0.334305279604
valid_y_col_norms_max: 2.78234106666
valid_y_col_norms_mean: 2.59701149502
valid_y_col_norms_min: 2.3810874603
valid_y_max_max_class: 0.999953240738
valid_y_mean_max_class: 0.84881891044
valid_y_min_max_class: 0.193943289318
valid_y_misclass: 0.0947
valid_y_nll: 0.334305279604
valid_y_row_norms_max: 0.705822478407
valid_y_row_norms_mean: 0.347877919902
valid_y_row_norms_min: 0.0778698200526
Saving to ./mlp_best.pkl...
Saving to ./mlp_best.pkl done. Time elapsed: 0.323518 seconds
In [ ]:
with open("mlp_tutorial_part_3.yaml", 'r') as f:
train = f.read()
hyper_params = {'train_stop' : 50000,
'valid_stop' : 60000,
'dim_h0' : 500,
'max_epochs' : 1, # 10000
'save_path' : '.'}
train = train % (hyper_params)
print train
train = yaml_parse.load(train)
train.main_loop()
In [ ]:
with open("mlp_tutorial_part_4.yaml", 'r') as f:
train = f.read()
hyper_params = {'train_stop' : 50000,
'valid_stop' : 60000,
'dim_h0' : 500,
'max_epochs' : 1, # 10000
'save_path' : '.'}
train = train % (hyper_params)
print train
train = yaml_parse.load(train)
train.main_loop()
Content source: dikien/personnel-study
Similar notebooks: