In [14]:
from pylearn2.config import yaml_parse
In [11]:
!ls /Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/stacked_autoencoders/
%cd /Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/stacked_autoencoders/
README dae_l2.yaml stacked_autoencoders.ipynb
dae_l1.yaml dae_mlp.yaml tests
/Users/dikien/Downloads/pylearn2/pylearn2/scripts/tutorials/stacked_autoencoders
In [24]:
with open('dae_l1.yaml', 'r') as f:
layer1_yaml = f.read()
print layer1_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: %(train_stop)i
},
model: !obj:pylearn2.models.autoencoder.DenoisingAutoencoder {
nvis : 784,
nhid : %(nhid)i,
irange : 0.05,
corruptor: !obj:pylearn2.corruption.BinomialCorruptor {
corruption_level: .2,
},
act_enc: "tanh",
act_dec: null, # Linear activation on the decoder side.
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate : 1e-3,
batch_size : %(batch_size)i,
monitoring_batches : %(monitoring_batches)i,
monitoring_dataset : *train,
cost : !obj:pylearn2.costs.autoencoder.MeanSquaredReconstructionError {},
termination_criterion : !obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: %(max_epochs)i,
},
},
save_path: "%(save_path)s/dae_l1.pkl",
save_freq: 1
}
In [25]:
hyper_params_l1 = {'train_stop' : 50000,
'batch_size' : 100,
'monitoring_batches' : 5,
'nhid' : 500,
'max_epochs' : 10,
'save_path' : '.'}
layer1_yaml = layer1_yaml % (hyper_params_l1)
print layer1_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: 50000
},
model: !obj:pylearn2.models.autoencoder.DenoisingAutoencoder {
nvis : 784,
nhid : 500,
irange : 0.05,
corruptor: !obj:pylearn2.corruption.BinomialCorruptor {
corruption_level: .2,
},
act_enc: "tanh",
act_dec: null, # Linear activation on the decoder side.
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate : 1e-3,
batch_size : 100,
monitoring_batches : 5,
monitoring_dataset : *train,
cost : !obj:pylearn2.costs.autoencoder.MeanSquaredReconstructionError {},
termination_criterion : !obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: 10,
},
},
save_path: "./dae_l1.pkl",
save_freq: 1
}
In [26]:
train = yaml_parse.load(layer1_yaml)
train.main_loop()
Parameter and initial learning rate summary:
vb: 0.001
hb: 0.001
W: 0.001
Wprime: 0.001
Compiling sgd_update...
Compiling sgd_update done. Time elapsed: 8.535399 seconds
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.041074 seconds
Monitored channels:
learning_rate
objective
total_seconds_last_epoch
training_seconds_this_epoch
Compiling accum...
graph size: 19
Compiling accum done. Time elapsed: 1.713480 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
learning_rate: 0.001
objective: 92.111948471
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 0.0
Time this epoch: 10.570406 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 500
Examples seen: 50000
learning_rate: 0.001
objective: 26.4766793624
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 10.570406
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.046847 seconds
Time this epoch: 10.761591 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 1000
Examples seen: 100000
learning_rate: 0.001
objective: 20.0324420641
total_seconds_last_epoch: 16.675167
training_seconds_this_epoch: 10.761591
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.416973 seconds
Time this epoch: 10.619281 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 1500
Examples seen: 150000
learning_rate: 0.001
objective: 16.9526632246
total_seconds_last_epoch: 18.241106
training_seconds_this_epoch: 10.619281
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 0.904373 seconds
Time this epoch: 11.538486 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 2000
Examples seen: 200000
learning_rate: 0.001
objective: 15.1179329275
total_seconds_last_epoch: 16.58631
training_seconds_this_epoch: 11.538486
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.273636 seconds
Time this epoch: 10.053852 seconds
Monitoring step:
Epochs seen: 5
Batches seen: 2500
Examples seen: 250000
learning_rate: 0.001
objective: 13.8935779578
total_seconds_last_epoch: 19.899654
training_seconds_this_epoch: 10.053852
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.236007 seconds
Time this epoch: 14.470846 seconds
Monitoring step:
Epochs seen: 6
Batches seen: 3000
Examples seen: 300000
learning_rate: 0.001
objective: 13.0115734208
total_seconds_last_epoch: 16.380132
training_seconds_this_epoch: 14.470846
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.553399 seconds
Time this epoch: 11.414060 seconds
Monitoring step:
Epochs seen: 7
Batches seen: 3500
Examples seen: 350000
learning_rate: 0.001
objective: 12.354534632
total_seconds_last_epoch: 22.618751
training_seconds_this_epoch: 11.41406
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.122237 seconds
Time this epoch: 10.201545 seconds
Monitoring step:
Epochs seen: 8
Batches seen: 4000
Examples seen: 400000
learning_rate: 0.001
objective: 11.8151804812
total_seconds_last_epoch: 17.347741
training_seconds_this_epoch: 10.201545
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.305958 seconds
Time this epoch: 11.302759 seconds
Monitoring step:
Epochs seen: 9
Batches seen: 4500
Examples seen: 450000
learning_rate: 0.001
objective: 11.3887492443
total_seconds_last_epoch: 17.157322
training_seconds_this_epoch: 11.302759
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 0.965640 seconds
Time this epoch: 10.481926 seconds
Monitoring step:
Epochs seen: 10
Batches seen: 5000
Examples seen: 500000
learning_rate: 0.001
objective: 11.0457817733
total_seconds_last_epoch: 17.000882
training_seconds_this_epoch: 10.481926
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 0.981587 seconds
Saving to ./dae_l1.pkl...
Saving to ./dae_l1.pkl done. Time elapsed: 1.001528 seconds
In [27]:
with open('dae_l2.yaml', 'r') as f:
layer2_yaml = f.read()
print layer2_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.transformer_dataset.TransformerDataset {
raw: !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: %(train_stop)i
},
transformer: !pkl: "%(save_path)s/dae_l1.pkl"
},
model: !obj:pylearn2.models.autoencoder.DenoisingAutoencoder {
nvis : %(nvis)i,
nhid : %(nhid)i,
irange : 0.05,
corruptor: !obj:pylearn2.corruption.BinomialCorruptor {
corruption_level: .3,
},
act_enc: "tanh",
act_dec: null, # Linear activation on the decoder side.
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate : 1e-3,
batch_size : %(batch_size)i,
monitoring_batches : %(monitoring_batches)i,
monitoring_dataset : *train,
cost : !obj:pylearn2.costs.autoencoder.MeanSquaredReconstructionError {},
termination_criterion : !obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: %(max_epochs)i,
},
},
save_path: "%(save_path)s/dae_l2.pkl",
save_freq: 1
}
In [28]:
hyper_params_l2 = {'train_stop' : 50000,
'batch_size' : 100,
'monitoring_batches' : 5,
'nvis' : hyper_params_l1['nhid'],
'nhid' : 500,
'max_epochs' : 10,
'save_path' : '.'}
layer2_yaml = layer2_yaml % (hyper_params_l2)
print layer2_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.transformer_dataset.TransformerDataset {
raw: !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: 50000
},
transformer: !pkl: "./dae_l1.pkl"
},
model: !obj:pylearn2.models.autoencoder.DenoisingAutoencoder {
nvis : 500,
nhid : 500,
irange : 0.05,
corruptor: !obj:pylearn2.corruption.BinomialCorruptor {
corruption_level: .3,
},
act_enc: "tanh",
act_dec: null, # Linear activation on the decoder side.
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate : 1e-3,
batch_size : 100,
monitoring_batches : 5,
monitoring_dataset : *train,
cost : !obj:pylearn2.costs.autoencoder.MeanSquaredReconstructionError {},
termination_criterion : !obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: 10,
},
},
save_path: "./dae_l2.pkl",
save_freq: 1
}
In [29]:
train = yaml_parse.load(layer2_yaml)
train.main_loop()
Parameter and initial learning rate summary:
vb: 0.001
hb: 0.001
W: 0.001
Wprime: 0.001
Compiling sgd_update...
Compiling sgd_update done. Time elapsed: 0.424942 seconds
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.037834 seconds
Monitored channels:
learning_rate
objective
total_seconds_last_epoch
training_seconds_this_epoch
Compiling accum...
graph size: 19
Compiling accum done. Time elapsed: 0.308717 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
learning_rate: 0.001
objective: 64.294005807
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 0.0
Time this epoch: 9.479954 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 500
Examples seen: 50000
learning_rate: 0.001
objective: 20.2072944723
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 9.479954
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.734012 seconds
Time this epoch: 9.795702 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 1000
Examples seen: 100000
learning_rate: 0.001
objective: 13.7861076018
total_seconds_last_epoch: 15.329416
training_seconds_this_epoch: 9.795702
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.663375 seconds
Time this epoch: 10.952850 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 1500
Examples seen: 150000
learning_rate: 0.001
objective: 10.906734586
total_seconds_last_epoch: 15.883912
training_seconds_this_epoch: 10.95285
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.973954 seconds
Time this epoch: 11.765567 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 2000
Examples seen: 200000
learning_rate: 0.001
objective: 9.32353813901
total_seconds_last_epoch: 17.924495
training_seconds_this_epoch: 11.765567
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.752700 seconds
Time this epoch: 10.033027 seconds
Monitoring step:
Epochs seen: 5
Batches seen: 2500
Examples seen: 250000
learning_rate: 0.001
objective: 8.33108113852
total_seconds_last_epoch: 18.197243
training_seconds_this_epoch: 10.033027
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.859218 seconds
Time this epoch: 11.996140 seconds
Monitoring step:
Epochs seen: 6
Batches seen: 3000
Examples seen: 300000
learning_rate: 0.001
objective: 7.67753543515
total_seconds_last_epoch: 16.316979
training_seconds_this_epoch: 11.99614
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.783568 seconds
Time this epoch: 9.533927 seconds
Monitoring step:
Epochs seen: 7
Batches seen: 3500
Examples seen: 350000
learning_rate: 0.001
objective: 7.21219009382
total_seconds_last_epoch: 18.45656
training_seconds_this_epoch: 9.533927
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.547828 seconds
Time this epoch: 9.571927 seconds
Monitoring step:
Epochs seen: 8
Batches seen: 4000
Examples seen: 400000
learning_rate: 0.001
objective: 6.86433605747
total_seconds_last_epoch: 14.951676
training_seconds_this_epoch: 9.571927
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.669331 seconds
Time this epoch: 9.597112 seconds
Monitoring step:
Epochs seen: 9
Batches seen: 4500
Examples seen: 450000
learning_rate: 0.001
objective: 6.58669781282
total_seconds_last_epoch: 15.541953
training_seconds_this_epoch: 9.597112
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 0.636326 seconds
Time this epoch: 9.409799 seconds
Monitoring step:
Epochs seen: 10
Batches seen: 5000
Examples seen: 500000
learning_rate: 0.001
objective: 6.36710589611
total_seconds_last_epoch: 15.173992
training_seconds_this_epoch: 9.409799
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 1.723690 seconds
Saving to ./dae_l2.pkl...
Saving to ./dae_l2.pkl done. Time elapsed: 1.487059 seconds
In [30]:
with open('dae_mlp.yaml', 'r') as f:
mlp_yaml = f.read()
print mlp_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: %(train_stop)i
},
model: !obj:pylearn2.models.mlp.MLP {
batch_size: %(batch_size)i,
layers: [
!obj:pylearn2.models.mlp.PretrainedLayer {
layer_name: 'h1',
layer_content: !pkl: "%(save_path)s/dae_l1.pkl"
},
!obj:pylearn2.models.mlp.PretrainedLayer {
layer_name: 'h2',
layer_content: !pkl: "%(save_path)s/dae_l2.pkl"
},
!obj:pylearn2.models.mlp.Softmax {
max_col_norm: 1.9365,
layer_name: 'y',
n_classes: 10,
irange: .005
}
],
nvis: 784
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate: .05,
learning_rule: !obj:pylearn2.training_algorithms.learning_rule.Momentum {
init_momentum: .5,
},
monitoring_dataset:
{
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 50000,
stop: %(valid_stop)i
},
},
cost: !obj:pylearn2.costs.mlp.Default {},
termination_criterion: !obj:pylearn2.termination_criteria.And {
criteria: [
!obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass",
prop_decrease: 0.,
N: 100
},
!obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: %(max_epochs)i
}
]
},
update_callbacks: !obj:pylearn2.training_algorithms.sgd.ExponentialDecay {
decay_factor: 1.00004,
min_lr: .000001
}
},
extensions: [
!obj:pylearn2.training_algorithms.learning_rule.MomentumAdjustor {
start: 1,
saturate: 250,
final_momentum: .7
}
]
}
In [31]:
hyper_params_mlp = {'train_stop' : 50000,
'valid_stop' : 60000,
'batch_size' : 100,
'max_epochs' : 50,
'save_path' : '.'}
mlp_yaml = mlp_yaml % (hyper_params_mlp)
print mlp_yaml
!obj:pylearn2.train.Train {
dataset: &train !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 0,
stop: 50000
},
model: !obj:pylearn2.models.mlp.MLP {
batch_size: 100,
layers: [
!obj:pylearn2.models.mlp.PretrainedLayer {
layer_name: 'h1',
layer_content: !pkl: "./dae_l1.pkl"
},
!obj:pylearn2.models.mlp.PretrainedLayer {
layer_name: 'h2',
layer_content: !pkl: "./dae_l2.pkl"
},
!obj:pylearn2.models.mlp.Softmax {
max_col_norm: 1.9365,
layer_name: 'y',
n_classes: 10,
irange: .005
}
],
nvis: 784
},
algorithm: !obj:pylearn2.training_algorithms.sgd.SGD {
learning_rate: .05,
learning_rule: !obj:pylearn2.training_algorithms.learning_rule.Momentum {
init_momentum: .5,
},
monitoring_dataset:
{
'valid' : !obj:pylearn2.datasets.mnist.MNIST {
which_set: 'train',
start: 50000,
stop: 60000
},
},
cost: !obj:pylearn2.costs.mlp.Default {},
termination_criterion: !obj:pylearn2.termination_criteria.And {
criteria: [
!obj:pylearn2.termination_criteria.MonitorBased {
channel_name: "valid_y_misclass",
prop_decrease: 0.,
N: 100
},
!obj:pylearn2.termination_criteria.EpochCounter {
max_epochs: 50
}
]
},
update_callbacks: !obj:pylearn2.training_algorithms.sgd.ExponentialDecay {
decay_factor: 1.00004,
min_lr: .000001
}
},
extensions: [
!obj:pylearn2.training_algorithms.learning_rule.MomentumAdjustor {
start: 1,
saturate: 250,
final_momentum: .7
}
]
}
In [ ]:
train = yaml_parse.load(mlp_yaml)
train.main_loop()
Parameter and initial learning rate summary:
vb: 0.05
hb: 0.05
W: 0.05
Wprime: 0.05
vb: 0.05
hb: 0.05
W: 0.05
Wprime: 0.05
softmax_b: 0.05
softmax_W: 0.05
Compiling sgd_update...
Compiling sgd_update done. Time elapsed: 6.700774 seconds
compiling begin_record_entry...
compiling begin_record_entry done. Time elapsed: 0.062979 seconds
Monitored channels:
learning_rate
momentum
total_seconds_last_epoch
training_seconds_this_epoch
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: 63
Compiling accum done. Time elapsed: 0.931920 seconds
Monitoring step:
Epochs seen: 0
Batches seen: 0
Examples seen: 0
learning_rate: 0.05
momentum: 0.5
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 0.0
valid_objective: 2.30021407389
valid_y_col_norms_max: 0.0650027130649
valid_y_col_norms_mean: 0.064174585385
valid_y_col_norms_min: 0.0624680393697
valid_y_max_max_class: 0.106719216561
valid_y_mean_max_class: 0.103229796303
valid_y_min_max_class: 0.101238149481
valid_y_misclass: 0.888
valid_y_nll: 2.30021407389
valid_y_row_norms_max: 0.0125483740983
valid_y_row_norms_mean: 0.00897719438947
valid_y_row_norms_min: 0.00411556576876
Time this epoch: 13.158766 seconds
Monitoring step:
Epochs seen: 1
Batches seen: 500
Examples seen: 50000
learning_rate: 0.0490099532688
momentum: 0.5
total_seconds_last_epoch: 0.0
training_seconds_this_epoch: 13.158766
valid_objective: 0.278234405165
valid_y_col_norms_max: 1.36132717813
valid_y_col_norms_mean: 1.24750458117
valid_y_col_norms_min: 1.07665625258
valid_y_max_max_class: 0.99967042039
valid_y_mean_max_class: 0.89333202731
valid_y_min_max_class: 0.372069926787
valid_y_misclass: 0.0793
valid_y_nll: 0.278234405165
valid_y_row_norms_max: 0.319150639671
valid_y_row_norms_mean: 0.171802208732
valid_y_row_norms_min: 0.0399207885787
Time this epoch: 10.836096 seconds
Monitoring step:
Epochs seen: 2
Batches seen: 1000
Examples seen: 100000
learning_rate: 0.0480395103882
momentum: 0.500803212851
total_seconds_last_epoch: 14.150889
training_seconds_this_epoch: 10.836096
valid_objective: 0.23955092492
valid_y_col_norms_max: 1.52508033886
valid_y_col_norms_mean: 1.4035044461
valid_y_col_norms_min: 1.23748044277
valid_y_max_max_class: 0.99983407061
valid_y_mean_max_class: 0.915776109011
valid_y_min_max_class: 0.402919864137
valid_y_misclass: 0.0682
valid_y_nll: 0.23955092492
valid_y_row_norms_max: 0.367833987248
valid_y_row_norms_mean: 0.192808127063
valid_y_row_norms_min: 0.050357193377
Time this epoch: 9.756829 seconds
Monitoring step:
Epochs seen: 3
Batches seen: 1500
Examples seen: 150000
learning_rate: 0.0470882831836
momentum: 0.501606425703
total_seconds_last_epoch: 11.831991
training_seconds_this_epoch: 9.756829
valid_objective: 0.200217975394
valid_y_col_norms_max: 1.71952750842
valid_y_col_norms_mean: 1.53547645863
valid_y_col_norms_min: 1.42110335836
valid_y_max_max_class: 0.999881443313
valid_y_mean_max_class: 0.928128320653
valid_y_min_max_class: 0.414282991949
valid_y_misclass: 0.0576
valid_y_nll: 0.200217975394
valid_y_row_norms_max: 0.40888443791
valid_y_row_norms_mean: 0.210184773429
valid_y_row_norms_min: 0.0545657088062
Time this epoch: 11.896243 seconds
Monitoring step:
Epochs seen: 4
Batches seen: 2000
Examples seen: 200000
learning_rate: 0.0461558911667
momentum: 0.502409638554
total_seconds_last_epoch: 10.798661
training_seconds_this_epoch: 11.896243
valid_objective: 0.17415213553
valid_y_col_norms_max: 1.9365
valid_y_col_norms_mean: 1.65811471015
valid_y_col_norms_min: 1.47460838036
valid_y_max_max_class: 0.999914969629
valid_y_mean_max_class: 0.936481031968
valid_y_min_max_class: 0.414629329458
valid_y_misclass: 0.0492
valid_y_nll: 0.17415213553
valid_y_row_norms_max: 0.456000087118
valid_y_row_norms_mean: 0.226211775318
valid_y_row_norms_min: 0.0622331039523
Time this epoch: 10.715199 seconds
Monitoring step:
Epochs seen: 5
Batches seen: 2500
Examples seen: 250000
learning_rate: 0.0452419613832
momentum: 0.503212851406
total_seconds_last_epoch: 13.013633
training_seconds_this_epoch: 10.715199
valid_objective: 0.152688460444
valid_y_col_norms_max: 1.93623806534
valid_y_col_norms_mean: 1.75543161873
valid_y_col_norms_min: 1.505661121
valid_y_max_max_class: 0.999913916954
valid_y_mean_max_class: 0.942628733883
valid_y_min_max_class: 0.431397100703
valid_y_misclass: 0.0418
valid_y_nll: 0.152688460444
valid_y_row_norms_max: 0.505858250232
valid_y_row_norms_mean: 0.238653730688
valid_y_row_norms_min: 0.0713204364606
Time this epoch: 10.744419 seconds
Monitoring step:
Epochs seen: 6
Batches seen: 3000
Examples seen: 300000
learning_rate: 0.0443461282636
momentum: 0.504016064257
total_seconds_last_epoch: 11.791187
training_seconds_this_epoch: 10.744419
valid_objective: 0.136227230503
valid_y_col_norms_max: 1.93504255675
valid_y_col_norms_mean: 1.82769291328
valid_y_col_norms_min: 1.55100667642
valid_y_max_max_class: 0.99994637086
valid_y_mean_max_class: 0.950290047894
valid_y_min_max_class: 0.452767477444
valid_y_misclass: 0.038
valid_y_nll: 0.136227230503
valid_y_row_norms_max: 0.535950736363
valid_y_row_norms_mean: 0.247734854542
valid_y_row_norms_min: 0.0761420530836
Time this epoch: 12.423846 seconds
Monitoring step:
Epochs seen: 7
Batches seen: 3500
Examples seen: 350000
learning_rate: 0.043468033477
momentum: 0.504819277108
total_seconds_last_epoch: 11.836817
training_seconds_this_epoch: 12.423846
valid_objective: 0.124043755506
valid_y_col_norms_max: 1.9365
valid_y_col_norms_mean: 1.86859504013
valid_y_col_norms_min: 1.59509095666
valid_y_max_max_class: 0.999940355648
valid_y_mean_max_class: 0.953919201627
valid_y_min_max_class: 0.460544308006
valid_y_misclass: 0.0359
valid_y_nll: 0.124043755506
valid_y_row_norms_max: 0.539856465789
valid_y_row_norms_mean: 0.252841057904
valid_y_row_norms_min: 0.0774112465944
Content source: dikien/personnel-study
Similar notebooks: