def test_22(self):
layers = [
InputLayer(3, 4),
Conv2d(8, 7),
BN(),
Dense(n=32),
OutputLayer()
]
Sequential(self.s, layers=layers, model_table='table22')
def test_mix_cnn_rnn_network(self):
from dlpy.applications import ResNet50_Caffe
from dlpy import Sequential
from dlpy.blocks import Bidirectional
# the case is to test if CNN and RNN model can be connect using functional api
# the model_type is expected to be RNN in 19w47.
# CNN
model = ResNet50_Caffe(self.s)
cnn_head = model.to_functional_model(stop_layers=model.layers[-1])
# RNN
model_rnn = Sequential(conn=self.s, model_table='rnn')
model_rnn.add(Bidirectional(n=100, n_blocks=2))
model_rnn.add(OutputLayer('fixed'))
f_rnn = model_rnn.to_functional_model()
# connecting
inp = Input(**cnn_head.layers[0].config)
x = cnn_head(inp)
y = f_rnn(x)
cnn_rnn = Model(self.s, inp, y)
cnn_rnn.compile()
# check type
self.assertTrue(cnn_rnn.model_type == 'RNN')
self.assertTrue(cnn_rnn.layers[-1].name == 'fixed')
f_rnn = model_rnn.to_functional_model()
# connecting
inp = Input(**cnn_head.layers[0].config)
x = cnn_head(inp)
y = f_rnn(x)
cnn_rnn = Model(self.s, inp, y)
cnn_rnn.compile()
# it should be fixed if I create f_rnn again.
self.assertTrue(cnn_rnn.layers[-1].name == 'fixed')
inp = Input(**cnn_head.layers[0].config)
x = cnn_head(inp)
y = f_rnn(x)
cnn_rnn = Model(self.s, inp, y)
cnn_rnn.compile()
# it should be fixed if I create f_rnn again.
self.assertTrue(cnn_rnn.layers[-1].name == 'fixed_2')
def SequenceLabeling(conn,
model_table='sequence_labeling_model',
neurons=10,
n_blocks=3,
rnn_type='gru'):
'''
Generates a sequence labeling model.
Parameters
----------
conn : CAS
Specifies the CAS connection object.
model_table : string, optional
Specifies the name of CAS table to store the model.
neurons : int, optional
Specifies the number of neurons to be in each layer.
Default: 10
n_blocks : int, optional
Specifies the number of bidirectional blocks to be added to the model.
Default: 3
rnn_type : string, optional
Specifies the type of the rnn layer.
Default: GRU
Valid Values: RNN, LSTM, GRU
Returns
-------
:class:`Sequential`
'''
conn.retrieve('loadactionset',
_messagelevel='error',
actionset='deeplearn')
if n_blocks >= 1:
model = Sequential(conn=conn, model_table=model_table)
model.add(
Bidirectional(n=neurons,
n_blocks=n_blocks,
rnn_type=rnn_type,
name='bi_' + rnn_type + '_layer_'))
model.add(OutputLayer())
else:
raise DLPyError(
'The number of blocks for a sequence labeling model should be at least 1.'
)
return model
def VGG19(conn,
model_table='VGG19',
n_classes=1000,
n_channels=3,
width=224,
height=224,
scale=1,
random_flip=None,
random_crop=None,
offsets=(103.939, 116.779, 123.68),
pre_trained_weights=False,
pre_trained_weights_file=None,
include_top=False,
random_mutation=None):
'''
Generates a deep learning model with the VGG19 architecture.
Parameters
----------
conn : CAS
Specifies the CAS connection object.
model_table : string, optional
Specifies the name of CAS table to store the model.
n_classes : int, optional
Specifies the number of classes. If None is assigned, the model will
automatically detect the number of classes based on the training set.
Default: 1000
n_channels : int, optional
Specifies the number of the channels (i.e., depth) of the input layer.
Default: 3
width : int, optional
Specifies the width of the input layer.
Default: 224
height : int, optional
Specifies the height of the input layer.
Default: 224
scale : double, optional
Specifies a scaling factor to be applied to each pixel intensity values.
Default: 1
random_flip : string, optional
Specifies how to flip the data in the input layer when image data is
used. Approximately half of the input data is subject to flipping.
Valid Values: 'h', 'hv', 'v', 'none'
random_crop : string, optional
Specifies how to crop the data in the input layer when image data is
used. Images are cropped to the values that are specified in the width
and height parameters. Only the images with one or both dimensions
that are larger than those sizes are cropped.
Valid Values: 'none', 'unique', 'randomresized', 'resizethencrop'
offsets : double or iter-of-doubles, optional
Specifies an offset for each channel in the input data. The final input
data is set after applying scaling and subtracting the specified offsets.
Default: (103.939, 116.779, 123.68)
pre_trained_weights : bool, optional
Specifies whether to use the pre-trained weights trained on the ImageNet data set.
Default: False
pre_trained_weights_file : string, optional
Specifies the file name for the pre-trained weights.
Must be a fully qualified file name of SAS-compatible file (e.g., *.caffemodel.h5)
Note: Required when pre_trained_weights=True.
include_top : bool, optional
Specifies whether to include pre-trained weights of the top layers (i.e., the FC layers).
Default: False
random_mutation : string, optional
Specifies how to apply data augmentations/mutations to the data in the input layer.
Valid Values: 'none', 'random'
Returns
-------
:class:`Sequential`
If `pre_trained_weights` is False
:class:`Model`
If `pre_trained_weights` is True
References
----------
https://arxiv.org/pdf/1409.1556.pdf
'''
conn.retrieve('loadactionset',
_messagelevel='error',
actionset='deeplearn')
# get all the parms passed in
parameters = locals()
if not pre_trained_weights:
model = Sequential(conn=conn, model_table=model_table)
# get the input parameters
input_parameters = get_layer_options(input_layer_options, parameters)
model.add(InputLayer(**input_parameters))
model.add(Conv2d(n_filters=64, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=64, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=128, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=128, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Dense(n=4096, dropout=0.5))
model.add(Dense(n=4096, dropout=0.5))
model.add(OutputLayer(n=n_classes))
return model
else:
if pre_trained_weights_file is None:
raise DLPyError(
'\nThe pre-trained weights file is not specified.\n'
'Please follow the steps below to attach the pre-trained weights:\n'
'1. Go to the website https://support.sas.com/documentation/prod-p/vdmml/zip/ '
'and download the associated weight file.\n'
'2. Upload the *.h5 file to '
'a server side directory which the CAS session has access to.\n'
'3. Specify the pre_trained_weights_file using the fully qualified server side path.'
)
model_cas = model_vgg19.VGG19_Model(s=conn,
model_table=model_table,
n_channels=n_channels,
width=width,
height=height,
random_crop=random_crop,
offsets=offsets,
random_flip=random_flip,
random_mutation=random_mutation)
if include_top:
if n_classes != 1000:
warnings.warn(
'If include_top = True, n_classes will be set to 1000.',
RuntimeWarning)
model = Model.from_table(model_cas)
model.load_weights(path=pre_trained_weights_file, labels=True)
return model
else:
model = Model.from_table(model_cas, display_note=False)
model.load_weights(path=pre_trained_weights_file)
weight_table_options = model.model_weights.to_table_params()
weight_table_options.update(dict(where='_LayerID_<22'))
model._retrieve_('table.partition',
table=weight_table_options,
casout=dict(
replace=True,
**model.model_weights.to_table_params()))
model._retrieve_('deeplearn.removelayer',
model=model_table,
name='fc8')
model._retrieve_('deeplearn.addlayer',
model=model_table,
name='fc8',
layer=dict(type='output',
n=n_classes,
act='softmax'),
srcLayers=['fc7'])
model = Model.from_table(conn.CASTable(model_table))
return model
def VGG11(conn,
model_table='VGG11',
n_classes=1000,
n_channels=3,
width=224,
height=224,
scale=1,
random_flip=None,
random_crop=None,
offsets=(103.939, 116.779, 123.68),
random_mutation=None):
'''
Generates a deep learning model with the VGG11 architecture.
Parameters
----------
conn : CAS
Specifies the CAS connection object.
model_table : string, optional
Specifies the name of CAS table to store the model.
n_classes : int, optional
Specifies the number of classes. If None is assigned, the model will
automatically detect the number of classes based on the training set.
Default: 1000
n_channels : int, optional
Specifies the number of the channels (i.e., depth) of the input layer.
Default: 3
width : int, optional
Specifies the width of the input layer.
Default: 224
height : int, optional
Specifies the height of the input layer.
Default: 224
scale : double, optional
Specifies a scaling factor to be applied to each pixel intensity values.
Default: 1
random_flip : string, optional
Specifies how to flip the data in the input layer when image data is
used. Approximately half of the input data is subject to flipping.
Valid Values: 'h', 'hv', 'v', 'none'
random_crop : string, optional
Specifies how to crop the data in the input layer when image data is
used. Images are cropped to the values that are specified in the width
and height parameters. Only the images with one or both dimensions
that are larger than those sizes are cropped.
Valid Values: 'none', 'unique', 'randomresized', 'resizethencrop'
offsets : double or iter-of-doubles, optional
Specifies an offset for each channel in the input data. The final
input data is set after applying scaling and subtracting the
specified offsets.
Default: (103.939, 116.779, 123.68)
random_mutation : string, optional
Specifies how to apply data augmentations/mutations to the data in the input layer.
Valid Values: 'none', 'random'
Returns
-------
:class:`Sequential`
References
----------
https://arxiv.org/pdf/1409.1556.pdf
'''
conn.retrieve('loadactionset',
_messagelevel='error',
actionset='deeplearn')
# get all the parms passed in
parameters = locals()
model = Sequential(conn=conn, model_table=model_table)
# get the input parameters
input_parameters = get_layer_options(input_layer_options, parameters)
model.add(InputLayer(**input_parameters))
model.add(Conv2d(n_filters=64, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=128, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=256, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Conv2d(n_filters=512, width=3, height=3, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
model.add(Dense(n=4096, dropout=0.5))
model.add(Dense(n=4096, dropout=0.5))
model.add(OutputLayer(n=n_classes))
return model
def test_2(self):
layers = [InputLayer(), Dense(n=32), OutputLayer()]
Sequential(self.s, layers=layers, model_table='table2')
def test_model13a(self):
model = Sequential(self.s, model_table='simple_cnn')
model.add(InputLayer(3, 224, 224))
model.add(Conv2d(2, 3))
model.add(Pooling(2))
model.add(Dense(4))
model.add(OutputLayer(n=2))
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
model.save_to_table(self.data_dir)
def test_new_bidirectional3(self):
model = Sequential(self.s, model_table='new_table3')
model.add(Bidirectional(n=[10, 20, 30], n_blocks=3))
model.add(OutputLayer())
model.print_summary()
def test_1(self):
with self.assertRaises(DLPyError):
Sequential(self.s, layers='', model_table='table1')
def test_plot_ticks(self):
model1 = Sequential(self.s, model_table='Simple_CNN1')
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
caslib, path, tmp_caslib = caslibify(self.s, path=self.data_dir+'images.sashdat', task='load')
self.s.table.loadtable(caslib=caslib,
casout={'name': 'eee', 'replace': True},
path=path)
r = model1.fit(data='eee', inputs='_image_', target='_label_', lr=0.001, max_epochs=5)
# Test default tick_frequency value of 1
ax = model1.plot_training_history()
self.assertEqual(len(ax.xaxis.majorTicks), model1.n_epochs)
# Test even
tick_frequency = 2
ax = model1.plot_training_history(tick_frequency=tick_frequency)
self.assertEqual(len(ax.xaxis.majorTicks), model1.n_epochs // tick_frequency + 1)
# Test odd
tick_frequency = 3
ax = model1.plot_training_history(tick_frequency=tick_frequency)
self.assertEqual(len(ax.xaxis.majorTicks), model1.n_epochs // tick_frequency + 1)
# Test max
tick_frequency = model1.n_epochs
ax = model1.plot_training_history(tick_frequency=tick_frequency)
self.assertEqual(len(ax.xaxis.majorTicks), model1.n_epochs // tick_frequency + 1)
# Test 0
tick_frequency = 0
ax = model1.plot_training_history(tick_frequency=tick_frequency)
self.assertEqual(len(ax.xaxis.majorTicks), model1.n_epochs)
if (caslib is not None) and tmp_caslib:
self.s.retrieve('table.dropcaslib', message_level = 'error', caslib = caslib)
def test_stride(self):
model = Sequential(self.s, model_table = 'Simple_CNN_3classes_cropped')
model.add(InputLayer(1, width = 36, height = 144, #offsets = myimage.channel_means,
name = 'input1',
random_mutation = 'random',
random_flip = 'HV'))
model.add(Conv2d(64, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(64, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(64, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Pooling(height = 2, width = 2, stride_vertical = 2, stride_horizontal = 1, pool = 'max')) # 72, 36
model.add(Conv2d(128, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(128, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(128, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Pooling(height = 2, width = 2, stride_vertical = 2, stride_horizontal = 1, pool = 'max')) # 36*36
model.add(Conv2d(256, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(256, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(256, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Pooling(2, pool = 'max')) # 18 * 18
model.add(Conv2d(512, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(512, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(512, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Pooling(2, pool = 'max')) # 9 * 9
model.add(Conv2d(1024, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(1024, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Conv2d(1024, 3, 3, include_bias = False, act = 'identity'))
model.add(BN(act = 'relu'))
model.add(Pooling(9))
model.add(Dense(256, dropout = 0.5))
model.add(OutputLayer(act = 'softmax', n = 3, name = 'output1'))
self.assertEqual(model.summary['Output Size'].values[-3], (1, 1, 1024))
model.print_summary()
# 2d print summary numerical check
self.assertEqual(model.summary.iloc[1, -1], 2985984)
def test_model1(self):
model1 = Sequential(self.s, model_table='Simple_CNN1')
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
caslib, path, tmp_caslib = caslibify(self.s, path=self.data_dir+'images.sashdat', task='load')
self.s.table.loadtable(caslib=caslib,
casout={'name': 'eee', 'replace': True},
path=path)
r = model1.fit(data='eee', inputs='_image_', target='_label_', lr=0.001)
if r.severity > 0:
for msg in r.messages:
print(msg)
self.assertTrue(r.severity <= 1)
if (caslib is not None) and tmp_caslib:
self.s.retrieve('table.dropcaslib', message_level = 'error', caslib = caslib)
def test_model_forecast3(self):
import datetime
try:
import pandas as pd
except:
unittest.TestCase.skipTest(self, "pandas not found in the libraries")
import numpy as np
filename1 = os.path.join(os.path.dirname(__file__), 'datasources', 'timeseries_exp1.csv')
importoptions1 = dict(filetype='delimited', delimiter=',')
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
self.table3 = TimeseriesTable.from_localfile(self.s, filename1, importoptions=importoptions1)
self.table3.timeseries_formatting(timeid='datetime',
timeseries=['series', 'covar'],
timeid_informat='ANYDTDTM19.',
timeid_format='DATETIME19.')
self.table3.timeseries_accumlation(acc_interval='day',
groupby=['id1var', 'id2var'])
self.table3.prepare_subsequences(seq_len=2,
target='series',
predictor_timeseries=['series', 'covar'],
missing_handling='drop')
valid_start = datetime.date(2015, 1, 4)
test_start = datetime.date(2015, 1, 7)
traintbl, validtbl, testtbl = self.table3.timeseries_partition(
validation_start=valid_start, testing_start=test_start)
sascode = '''
data {};
set {};
drop series_lag1;
run;
'''.format(validtbl.name, validtbl.name)
self.s.retrieve('dataStep.runCode', _messagelevel='error', code=sascode)
sascode = '''
data {};
set {};
drop series_lag1;
run;
'''.format(testtbl.name, testtbl.name)
self.s.retrieve('dataStep.runCode', _messagelevel='error', code=sascode)
model1 = Sequential(self.s, model_table='lstm_rnn')
model1.add(InputLayer(std='STD'))
model1.add(Recurrent(rnn_type='LSTM', output_type='encoding', n=15, reversed_=False))
model1.add(OutputLayer(act='IDENTITY'))
optimizer = Optimizer(algorithm=AdamSolver(learning_rate=0.01), mini_batch_size=32,
seed=1234, max_epochs=10)
seq_spec = Sequence(**traintbl.sequence_opt)
result = model1.fit(traintbl, optimizer=optimizer,
sequence=seq_spec, **traintbl.inputs_target)
self.assertTrue(result.severity == 0)
resulttbl1 = model1.forecast(validtbl, horizon=1)
self.assertTrue(isinstance(resulttbl1, CASTable))
self.assertTrue(resulttbl1.shape[0]==15)
local_resulttbl1 = resulttbl1.to_frame()
unique_time = local_resulttbl1.datetime.unique()
self.assertTrue(len(unique_time)==1)
self.assertTrue(pd.Timestamp(unique_time[0])==datetime.datetime(2015,1,4))
resulttbl2 = model1.forecast(validtbl, horizon=3)
self.assertTrue(isinstance(resulttbl2, CASTable))
self.assertTrue(resulttbl2.shape[0]==45)
local_resulttbl2 = resulttbl2.to_frame()
local_resulttbl2.sort_values(by=['id1var', 'id2var', 'datetime'], inplace=True)
unique_time = local_resulttbl2.datetime.unique()
self.assertTrue(len(unique_time)==3)
for i in range(3):
self.assertTrue(pd.Timestamp(unique_time[i])==datetime.datetime(2015,1,4+i))
series_lag1 = local_resulttbl2.loc[(local_resulttbl2.id1var==1) & (local_resulttbl2.id2var==1),
'series_lag1'].values
series_lag2 = local_resulttbl2.loc[(local_resulttbl2.id1var==1) & (local_resulttbl2.id2var==1),
'series_lag2'].values
DL_Pred = local_resulttbl2.loc[(local_resulttbl2.id1var==1) & (local_resulttbl2.id2var==1),
'_DL_Pred_'].values
self.assertTrue(np.array_equal(series_lag1[1:3], DL_Pred[0:2]))
self.assertTrue(series_lag2[2]==DL_Pred[0])
with self.assertRaises(RuntimeError):
resulttbl3 = model1.forecast(testtbl, horizon=3)
def test_model16(self):
model = Sequential(self.s, model_table='Simple_CNN')
model.add(layer=InputLayer(n_channels=1, height=10, width=10))
model.add(layer=Keypoints(n=10))
self.assertTrue(model.summary.loc[1, 'Number of Parameters'] == (1000, 10))
def test_model14(self):
model = Sequential(self.s, model_table='Simple_CNN')
model.add(layer=InputLayer(n_channels=1, height=10, width=10))
model.add(layer=OutputLayer())
model.summary
def test_model13b(self):
model = Sequential(self.s, model_table='simple_cnn')
model.add(layer=InputLayer(n_channels=1, height=10, width=10))
model.add(layer=OutputLayer(n=10, full_connect=False))
self.assertTrue(model.summary.loc[1, 'Number of Parameters'] == (0, 0))
model1 = Sequential(self.s, model_table='simple_cnn')
model1.add(layer=InputLayer(n_channels=1, height=10, width=10))
model1.add(layer=OutputLayer(n=10, full_connect=True))
self.assertTrue(model1.summary.loc[1, 'Number of Parameters'] == (1000, 10))
model2 = Sequential(self.s, model_table='Simple_CNN')
model2.add(layer=InputLayer(n_channels=1, height=10, width=10))
model2.add(layer=OutputLayer(n=10, full_connect=True, include_bias=False))
self.assertTrue(model2.summary.loc[1, 'Number of Parameters'] == (1000, 0))
model3 = Sequential(self.s, model_table='Simple_CNN')
model3.add(layer=InputLayer(n_channels=1, height=10, width=10))
model3.add(layer=Conv2d(4, 3))
model3.add(layer=OutputLayer(n=10))
self.assertTrue(model3.summary.loc[2, 'Number of Parameters'] == (4000, 10))
model4 = Sequential(self.s, model_table='Simple_CNN')
model4.add(layer=InputLayer(n_channels=1, height=10, width=10))
model4.add(layer=Conv2d(4, 3))
model4.add(layer=OutputLayer(n=10, full_connect=False))
self.assertTrue(model4.summary.loc[2, 'Number of Parameters'] == (0, 0))
def test_simple_cnn_seq2(self):
model1 = Sequential(self.s, model_table='table8')
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
model1.print_summary()
def test_conv1d_model(self):
# a model from https://blog.goodaudience.com/introduction-to-1d-convolutional-neural-networks-in-keras-for-time-sequences-3a7ff801a2cf
Conv1D = Conv1d
MaxPooling1D=Pooling
model_m = Sequential(self.s)
model_m.add(InputLayer(width=80*3, height=1, n_channels=1))
model_m.add(Conv1D(100, 10, act='relu'))
model_m.add(Conv1D(100, 10, act='relu'))
model_m.add(MaxPooling1D(3))
model_m.add(Conv1D(160, 10, act='relu'))
model_m.add(Conv1D(160, 10, act='relu'))
model_m.add(GlobalAveragePooling1D(dropout=0.5))
model_m.add(OutputLayer(n=6, act='softmax'))
# use assertEqual to check whether the layer output size matches the expected value for MaxPooling1D
self.assertEqual(model_m.layers[3].output_size, (1, 80, 100))
model_m.print_summary()
# 1d print summary numerical check
self.assertEqual(model_m.summary.iloc[1, -1], 240000)
def test_new_bidirectional1(self):
model = Sequential(self.s, model_table='new_table1')
model.add(Bidirectional(n=10))
model.add(OutputLayer())
model.print_summary()
def test_sequential_conversion(self):
from dlpy.sequential import Sequential
model1 = Sequential(self.s)
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
func_model = model1.to_functional_model()
func_model.compile()
func_model.print_summary()
def test_new_bidirectional6(self):
model = Sequential(self.s, model_table='new_table5')
model.add(InputLayer())
r1 = Recurrent(n=10, name='rec1')
model.add(r1)
model.add(Bidirectional(n=20, src_layers=[r1]))
model.add(Recurrent(n=10))
model.add(OutputLayer())
model.print_summary()
def test_3(self):
model1 = Sequential(self.s, model_table='table3')
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.pop()
def test_11(self):
with self.assertRaises(DLPyError):
model1 = Sequential(self.s, model_table='table11')
model1.add(Conv2d(8, 7))
model1.compile()
def test_5(self):
with self.assertRaises(DLPyError):
model1 = Sequential(self.s, model_table='table5')
model1.compile()
def test_stop_layers(self):
from dlpy.sequential import Sequential
model1 = Sequential(self.s)
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
inputlayer = model1.layers[0]
inp = Input(**inputlayer.config)
func_model = model1.to_functional_model(
stop_layers=[model1.layers[-1]])
x = func_model(inp)
out = Keypoints(n=10)(x)
func_model_keypoints = Model(self.s, inp, out)
func_model_keypoints.compile()
func_model_keypoints.print_summary()
def test_model12(self):
model1 = Sequential(self.s, model_table='Simple_CNN1')
model1.add(InputLayer(3, 224, 224))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Conv2d(8, 7))
model1.add(Pooling(2))
model1.add(Dense(16))
model1.add(OutputLayer(act='softmax', n=2))
if self.data_dir is None:
unittest.TestCase.skipTest(self, "DLPY_DATA_DIR is not set in the environment variables")
caslib, path, tmp_caslib = caslibify(self.s, path=self.data_dir+'images.sashdat', task='load')
self.s.table.loadtable(caslib=caslib,
casout={'name': 'eee', 'replace': True},
path=path)
r = model1.fit(data='eee', inputs='_image_', target='_label_', save_best_weights=True)
self.assertTrue(r.severity == 0)
r1 = model1.fit(data='eee', inputs='_image_', target='_label_', max_epochs=3)
self.assertTrue(r1.severity == 0)
r2 = model1.fit(data='eee', inputs='_image_', target='_label_', max_epochs=2, save_best_weights=True)
self.assertTrue(r2.severity == 0)
r3 = model1.predict(data='eee', use_best_weights=True)
self.assertTrue(r3.severity == 0)
if (caslib is not None) and tmp_caslib:
self.s.retrieve('table.dropcaslib', message_level = 'error', caslib = caslib)
def test_4(self):
model1 = Sequential(self.s, model_table='table4')
model1.add(Conv2d(8, 7))
model1.add(InputLayer(3, 224, 224))
model1.switch(0, 1)
def Tiny_YoloV2(conn,
anchors,
model_table='Tiny-Yolov2',
n_channels=3,
width=416,
height=416,
scale=1.0 / 255,
random_mutation=None,
act='leaky',
act_detection='AUTO',
softmax_for_class_prob=True,
coord_type='YOLO',
max_label_per_image=30,
max_boxes=30,
n_classes=20,
predictions_per_grid=5,
do_sqrt=True,
grid_number=13,
coord_scale=None,
object_scale=None,
prediction_not_a_object_scale=None,
class_scale=None,
detection_threshold=None,
iou_threshold=None,
random_boxes=False,
match_anchor_size=None,
num_to_force_coord=None,
random_flip=None,
random_crop=None):
'''
Generate a deep learning model with the Tiny Yolov2 architecture.
Tiny Yolov2 is a very small model of Yolov2, so that it includes fewer
numbers of convolutional layer and batch normalization layer.
Parameters
----------
conn : CAS
Specifies the connection of the CAS connection.
anchors : list
Specifies the anchor box values.
model_table : string, optional
Specifies the name of CAS table to store the model.
n_channels : int, optional
Specifies the number of the channels (i.e., depth) of the input layer.
Default: 3
width : int, optional
Specifies the width of the input layer.
Default: 416
height : int, optional
Specifies the height of the input layer.
Default: 416
scale : double, optional
Specifies a scaling factor to be applied to each pixel intensity values.
Default: 1.0 / 255
random_mutation : string, optional
Specifies how to apply data augmentations/mutations to the data in the
input layer.
Valid Values: 'none', 'random'
act : string, optional
Specifies the activation function for the batch normalization layers.
Default: 'leaky'
act_detection : string, optional
Specifies the activation function for the detection layer.
Valid Values: AUTO, IDENTITY, LOGISTIC, SIGMOID, TANH, RECTIFIER, RELU, SOFPLUS, ELU, LEAKY, FCMP
Default: AUTO
softmax_for_class_prob : bool, optional
Specifies whether to perform Softmax on class probability per
predicted object.
Default: True
coord_type : string, optional
Specifies the format of how to represent bounding boxes. For example,
a bounding box can be represented with the x and y locations of the
top-left point as well as width and height of the rectangle.
This format is the 'rect' format. We also support coco and yolo formats.
Valid Values: 'rect', 'yolo', 'coco'
Default: 'yolo'
max_label_per_image : int, optional
Specifies the maximum number of labels per image in the training.
Default: 30
max_boxes : int, optional
Specifies the maximum number of overall predictions allowed in the
detection layer.
Default: 30
n_classes : int, optional
Specifies the number of classes. If None is assigned, the model will
automatically detect the number of classes based on the training set.
Default: 20
predictions_per_grid : int, optional
Specifies the amount of predictions will be done per grid.
Default: 5
do_sqrt : bool, optional
Specifies whether to apply the SQRT function to width and height of
the object for the cost function.
Default: True
grid_number : int, optional
Specifies the amount of cells to be analyzed for an image. For example,
if the value is 5, then the image will be divided into a 5 x 5 grid.
Default: 13
coord_scale : float, optional
Specifies the weight for the cost function in the detection layer,
when objects exist in the grid.
object_scale : float, optional
Specifies the weight for object detected for the cost function in
the detection layer.
prediction_not_a_object_scale : float, optional
Specifies the weight for the cost function in the detection layer,
when objects do not exist in the grid.
class_scale : float, optional
Specifies the weight for the class of object detected for the cost
function in the detection layer.
detection_threshold : float, optional
Specifies the threshold for object detection.
iou_threshold : float, optional
Specifies the IOU Threshold of maximum suppression in object detection.
random_boxes : bool, optional
Randomizing boxes when loading the bounding box information.
Default: False
match_anchor_size : bool, optional
Whether to force the predicted box match the anchor boxes in sizes for all predictions
num_to_force_coord : int, optional
The number of leading chunk of images in training when the algorithm forces predicted objects
in each grid to be equal to the anchor box sizes, and located at the grid center
random_flip : string, optional
Specifies how to flip the data in the input layer when image data is
used. Approximately half of the input data is subject to flipping.
Valid Values: 'h', 'hv', 'v', 'none'
random_crop : string, optional
Specifies how to crop the data in the input layer when image data is
used. Images are cropped to the values that are specified in the width
and height parameters. Only the images with one or both dimensions
that are larger than those sizes are cropped.
Valid Values: 'none', 'unique', 'randomresized', 'resizethencrop'
Returns
-------
:class:`Sequential`
References
----------
https://arxiv.org/pdf/1612.08242.pdf
'''
model = Sequential(conn=conn, model_table=model_table)
parameters = locals()
input_parameters = get_layer_options(input_layer_options, parameters)
model.add(InputLayer(**input_parameters))
# conv1 416 448
model.add(
Conv2d(n_filters=16,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv2 208 224
model.add(
Conv2d(n_filters=32,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv3 104 112
model.add(
Conv2d(n_filters=64,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv4 52 56
model.add(
Conv2d(n_filters=128,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv5 26 28
model.add(
Conv2d(n_filters=256,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv6 13 14
model.add(
Conv2d(n_filters=512,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(Pooling(width=2, height=2, stride=1, pool='max'))
# conv7 13
model.add(
Conv2d(n_filters=1024,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
# conv8 13
model.add(
Conv2d(n_filters=512,
width=3,
act='identity',
include_bias=False,
stride=1))
model.add(BN(act=act))
model.add(
Conv2d((n_classes + 5) * predictions_per_grid,
width=1,
act='identity',
include_bias=False,
stride=1))
model.add(
Detection(act=act_detection,
detection_model_type='yolov2',
anchors=anchors,
softmax_for_class_prob=softmax_for_class_prob,
coord_type=coord_type,
class_number=n_classes,
grid_number=grid_number,
predictions_per_grid=predictions_per_grid,
do_sqrt=do_sqrt,
coord_scale=coord_scale,
object_scale=object_scale,
prediction_not_a_object_scale=prediction_not_a_object_scale,
class_scale=class_scale,
detection_threshold=detection_threshold,
iou_threshold=iou_threshold,
random_boxes=random_boxes,
max_label_per_image=max_label_per_image,
max_boxes=max_boxes,
match_anchor_size=match_anchor_size,
num_to_force_coord=num_to_force_coord))
return model
def test_6(self):
model1 = Sequential(self.s, model_table='table6')
model1.add(Bidirectional(n=10, n_blocks=3))
model1.add(OutputLayer())
def YoloV1(conn,
model_table='YoloV1',
n_channels=3,
width=448,
height=448,
scale=1.0 / 255,
random_mutation=None,
act='leaky',
dropout=0,
act_detection='AUTO',
softmax_for_class_prob=True,
coord_type='YOLO',
max_label_per_image=30,
max_boxes=30,
n_classes=20,
predictions_per_grid=2,
do_sqrt=True,
grid_number=7,
coord_scale=None,
object_scale=None,
prediction_not_a_object_scale=None,
class_scale=None,
detection_threshold=None,
iou_threshold=None,
random_boxes=False,
random_flip=None,
random_crop=None):
'''
Generates a deep learning model with the Yolo V1 architecture.
Parameters
----------
conn : CAS
Specifies the connection of the CAS connection.
model_table : string, optional
Specifies the name of CAS table to store the model.
n_channels : int, optional
Specifies the number of the channels (i.e., depth) of the input layer.
Default: 3
width : int, optional
Specifies the width of the input layer.
Default: 448
height : int, optional
Specifies the height of the input layer.
Default: 448
scale : double, optional
Specifies a scaling factor to be applied to each pixel intensity values.
Default: 1.0 / 255
random_mutation : string, optional
Specifies how to apply data augmentations/mutations to the data in
the input layer.
Valid Values: 'none', 'random'
act: String, optional
Specifies the activation function to be used in the convolutional layer
layers and the final convolution layer.
Default: 'leaky'
dropout: double, optional
Specifies the drop out rate.
Default: 0
act_detection : string, optional
Specifies the activation function for the detection layer.
Valid Values: AUTO, IDENTITY, LOGISTIC, SIGMOID, TANH, RECTIFIER, RELU, SOFPLUS, ELU, LEAKY, FCMP
Default: AUTO
softmax_for_class_prob : bool, optional
Specifies whether to perform Softmax on class probability per
predicted object.
Default: True
coord_type : string, optional
Specifies the format of how to represent bounding boxes. For example,
a bounding box can be represented with the x and y locations of the
top-left point as well as width and height of the rectangle.
This format is the 'rect' format. We also support coco and yolo formats.
Valid Values: 'rect', 'yolo', 'coco'
Default: 'yolo'
max_label_per_image : int, optional
Specifies the maximum number of labels per image in the training.
Default: 30
max_boxes : int, optional
Specifies the maximum number of overall predictions allowed in the
detection layer.
Default: 30
n_classes : int, optional
Specifies the number of classes. If None is assigned, the model will
automatically detect the number of classes based on the training set.
Default: 20
predictions_per_grid : int, optional
Specifies the amount of predictions will be done per grid.
Default: 2
do_sqrt : bool, optional
Specifies whether to apply the SQRT function to width and height of
the object for the cost function.
Default: True
grid_number : int, optional
Specifies the amount of cells to be analyzed for an image. For example,
if the value is 5, then the image will be divided into a 5 x 5 grid.
Default: 7
coord_scale : float, optional
Specifies the weight for the cost function in the detection layer,
when objects exist in the grid.
object_scale : float, optional
Specifies the weight for object detected for the cost function in
the detection layer.
prediction_not_a_object_scale : float, optional
Specifies the weight for the cost function in the detection layer,
when objects do not exist in the grid.
class_scale : float, optional
Specifies the weight for the class of object detected for the cost
function in the detection layer.
detection_threshold : float, optional
Specifies the threshold for object detection.
iou_threshold : float, optional
Specifies the IOU Threshold of maximum suppression in object detection.
random_boxes : bool, optional
Randomizing boxes when loading the bounding box information.
Default: False
random_flip : string, optional
Specifies how to flip the data in the input layer when image data is
used. Approximately half of the input data is subject to flipping.
Valid Values: 'h', 'hv', 'v', 'none'
random_crop : string, optional
Specifies how to crop the data in the input layer when image data is
used. Images are cropped to the values that are specified in the width
and height parameters. Only the images with one or both dimensions
that are larger than those sizes are cropped.
Valid Values: 'none', 'unique', 'randomresized', 'resizethencrop'
Returns
-------
:class:`Sequential`
References
----------
https://arxiv.org/pdf/1506.02640.pdf
'''
model = Sequential(conn=conn, model_table=model_table)
parameters = locals()
input_parameters = get_layer_options(input_layer_options, parameters)
model.add(InputLayer(**input_parameters))
# conv1 448
model.add(Conv2d(32, width=3, act=act, include_bias=False, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv2 224
model.add(Conv2d(64, width=3, act=act, include_bias=False, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv3 112
model.add(Conv2d(128, width=3, act=act, include_bias=False, stride=1))
# conv4 112
model.add(Conv2d(64, width=1, act=act, include_bias=False, stride=1))
# conv5 112
model.add(Conv2d(128, width=3, act=act, include_bias=False, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv6 56
model.add(Conv2d(256, width=3, act=act, include_bias=False, stride=1))
# conv7 56
model.add(Conv2d(128, width=1, act=act, include_bias=False, stride=1))
# conv8 56
model.add(Conv2d(256, width=3, act=act, include_bias=False, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv9 28
model.add(Conv2d(512, width=3, act=act, include_bias=False, stride=1))
# conv10 28
model.add(Conv2d(256, width=1, act=act, include_bias=False, stride=1))
# conv11 28
model.add(Conv2d(512, width=3, act=act, include_bias=False, stride=1))
# conv12 28
model.add(Conv2d(256, width=1, act=act, include_bias=False, stride=1))
# conv13 28
model.add(Conv2d(512, width=3, act=act, include_bias=False, stride=1))
model.add(Pooling(width=2, height=2, stride=2, pool='max'))
# conv14 14
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv15 14
model.add(Conv2d(512, width=1, act=act, include_bias=False, stride=1))
# conv16 14
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv17 14
model.add(Conv2d(512, width=1, act=act, include_bias=False, stride=1))
# conv18 14
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv19 14
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv20 7
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=2))
# conv21 7
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv22 7
model.add(Conv2d(1024, width=3, act=act, include_bias=False, stride=1))
# conv23 7
model.add(
Conv2d(256,
width=3,
act=act,
include_bias=False,
stride=1,
dropout=dropout))
model.add(
Dense(n=(n_classes + (5 * predictions_per_grid)) * grid_number *
grid_number,
act='identity'))
model.add(
Detection(act=act_detection,
detection_model_type='yolov1',
softmax_for_class_prob=softmax_for_class_prob,
coord_type=coord_type,
class_number=n_classes,
grid_number=grid_number,
predictions_per_grid=predictions_per_grid,
do_sqrt=do_sqrt,
coord_scale=coord_scale,
object_scale=object_scale,
prediction_not_a_object_scale=prediction_not_a_object_scale,
class_scale=class_scale,
detection_threshold=detection_threshold,
iou_threshold=iou_threshold,
random_boxes=random_boxes,
max_label_per_image=max_label_per_image,
max_boxes=max_boxes))
return model
