Skip to content
GitLab
Commit 2dd5aae6 authored by Evgeny Kusmenko's avatar Evgeny Kusmenko
Browse files

Merge branch 'move-generated-train-files' into 'master' 

Move generated training files

See merge request !13
parents af4a9cb2 e5d1c8d6
Pipeline #125343 canceled with stages
Hide whitespace changes
Inline Side-by-side
pom.xml
View file @ 2dd5aae6
......@@ -8,7 +8,7 @@
<groupId>de.monticore.lang.monticar</groupId>
<artifactId>cnnarch-gluon-generator</artifactId>
<version>0.1.5</version>
<version>0.1.6</version>
<!-- == PROJECT DEPENDENCIES ============================================= -->
......
src/main/java/de/monticore/lang/monticar/cnnarch/gluongenerator/CNNArch2Gluon.java
View file @ 2dd5aae6
......@@ -47,6 +47,9 @@ public class CNNArch2Gluon extends CNNArch2MxNet {
temp = archTc.process("CNNNet", Target.PYTHON);
fileContentMap.put(temp.getKey(), temp.getValue());
temp = archTc.process("CNNDataLoader", Target.PYTHON);
fileContentMap.put(temp.getKey(), temp.getValue());
temp = archTc.process("CNNCreator", Target.PYTHON);
fileContentMap.put(temp.getKey(), temp.getValue());
......
src/main/java/de/monticore/lang/monticar/cnnarch/gluongenerator/CNNTrain2Gluon.java
View file @ 2dd5aae6
......@@ -21,7 +21,14 @@ public class CNNTrain2Gluon extends CNNTrain2MxNet {
configDataList.add(configData);
Map<String, Object> ftlContext = Collections.singletonMap("configurations", configDataList);
String templateContent = templateConfiguration.processTemplate(ftlContext, "CNNTrainer.ftl");
return Collections.singletonMap("CNNTrainer_" + getInstanceName() + ".py", templateContent);
Map<String, String> fileContentMap = new HashMap<>();
String cnnTrainTemplateContent = templateConfiguration.processTemplate(ftlContext, "CNNTrainer.ftl");
fileContentMap.put("CNNTrainer_" + getInstanceName() + ".py", cnnTrainTemplateContent);
String cnnSupervisedTrainerContent = templateConfiguration.processTemplate(ftlContext, "CNNSupervisedTrainer.ftl");
fileContentMap.put("supervised_trainer.py", cnnSupervisedTrainerContent);
return fileContentMap;
}
}
\ No newline at end of file
src/main/resources/templates/gluon/CNNCreator.ftl
View file @ 2dd5aae6
import mxnet as mx
import logging
import os
import errno
import shutil
import h5py
import sys
import numpy as np
import time
from mxnet import gluon, autograd, nd
from CNNNet_${tc.fullArchitectureName} import Net
@mx.init.register
class MyConstant(mx.init.Initializer):
def __init__(self, value):
super(MyConstant, self).__init__(value=value)
self.value = value
def _init_weight(self, _, arr):
arr[:] = mx.nd.array(self.value)
class ${tc.fileNameWithoutEnding}:
_data_dir_ = "${tc.dataPath}/"
_model_dir_ = "model/${tc.componentName}/"
_model_prefix_ = "model"
_input_names_ = [${tc.join(tc.architectureInputs, ",", "'", "'")}]
_input_shapes_ = [<#list tc.architecture.inputs as input>(${tc.join(input.definition.type.dimensions, ",")})</#list>]
_output_names_ = [${tc.join(tc.architectureOutputs, ",", "'", "_label'")}]
def __init__(self):
self.weight_initializer = mx.init.Normal()
......@@ -60,176 +41,6 @@ class ${tc.fileNameWithoutEnding}:
return lastEpoch
def load_data(self, batch_size):
train_h5, test_h5 = self.load_h5_files()
data_mean = train_h5[self._input_names_[0]][:].mean(axis=0)
data_std = train_h5[self._input_names_[0]][:].std(axis=0) + 1e-5
train_iter = mx.io.NDArrayIter(train_h5[self._input_names_[0]],
train_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
test_iter = None
if test_h5 != None:
test_iter = mx.io.NDArrayIter(test_h5[self._input_names_[0]],
test_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
return train_iter, test_iter, data_mean, data_std
def load_h5_files(self):
train_h5 = None
test_h5 = None
train_path = self._data_dir_ + "train.h5"
test_path = self._data_dir_ + "test.h5"
if os.path.isfile(train_path):
train_h5 = h5py.File(train_path, 'r')
if not (self._input_names_[0] in train_h5 and self._output_names_[0] in train_h5):
logging.error("The HDF5 file '" + os.path.abspath(train_path) + "' has to contain the datasets: "
+ "'" + self._input_names_[0] + "', '" + self._output_names_[0] + "'")
sys.exit(1)
test_iter = None
if os.path.isfile(test_path):
test_h5 = h5py.File(test_path, 'r')
if not (self._input_names_[0] in test_h5 and self._output_names_[0] in test_h5):
logging.error("The HDF5 file '" + os.path.abspath(test_path) + "' has to contain the datasets: "
+ "'" + self._input_names_[0] + "', '" + self._output_names_[0] + "'")
sys.exit(1)
else:
logging.warning("Couldn't load test set. File '" + os.path.abspath(test_path) + "' does not exist.")
return train_h5, test_h5
else:
logging.error("Data loading failure. File '" + os.path.abspath(train_path) + "' does not exist.")
sys.exit(1)
def train(self, batch_size=64,
num_epoch=10,
eval_metric='acc',
optimizer='adam',
optimizer_params=(('learning_rate', 0.001),),
load_checkpoint=True,
context='gpu',
checkpoint_period=5,
normalize=True):
if context == 'gpu':
mx_context = mx.gpu()
elif context == 'cpu':
mx_context = mx.cpu()
else:
logging.error("Context argument is '" + context + "'. Only 'cpu' and 'gpu are valid arguments'.")
if 'weight_decay' in optimizer_params:
optimizer_params['wd'] = optimizer_params['weight_decay']
del optimizer_params['weight_decay']
if 'learning_rate_decay' in optimizer_params:
min_learning_rate = 1e-08
if 'learning_rate_minimum' in optimizer_params:
min_learning_rate = optimizer_params['learning_rate_minimum']
del optimizer_params['learning_rate_minimum']
optimizer_params['lr_scheduler'] = mx.lr_scheduler.FactorScheduler(
optimizer_params['step_size'],
factor=optimizer_params['learning_rate_decay'],
stop_factor_lr=min_learning_rate)
del optimizer_params['step_size']
del optimizer_params['learning_rate_decay']
train_iter, test_iter, data_mean, data_std = self.load_data(batch_size)
if self.net == None:
if normalize:
self.construct(context=mx_context, data_mean=nd.array(data_mean), data_std=nd.array(data_std))
else:
self.construct(context=mx_context)
begin_epoch = 0
if load_checkpoint:
begin_epoch = self.load(mx_context)
else:
if os.path.isdir(self._model_dir_):
shutil.rmtree(self._model_dir_)
try:
os.makedirs(self._model_dir_)
except OSError:
if not os.path.isdir(self._model_dir_):
raise
trainer = mx.gluon.Trainer(self.net.collect_params(), optimizer, optimizer_params)
if self.net.last_layer == 'softmax':
loss_function = mx.gluon.loss.SoftmaxCrossEntropyLoss()
elif self.net.last_layer == 'sigmoid':
loss_function = mx.gluon.loss.SigmoidBinaryCrossEntropyLoss()
elif self.net.last_layer == 'linear':
loss_function = mx.gluon.loss.L2Loss()
else: # TODO: Change default?
loss_function = mx.gluon.loss.L2Loss()
logging.warning("Invalid last_layer, defaulting to L2 loss")
speed_period = 50
tic = None
for epoch in range(begin_epoch, begin_epoch + num_epoch):
train_iter.reset()
for batch_i, batch in enumerate(train_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
with autograd.record():
output = self.net(data)
loss = loss_function(output, label)
loss.backward()
trainer.step(batch_size)
if tic is None:
tic = time.time()
else:
if batch_i % speed_period == 0:
try:
speed = speed_period * batch_size / (time.time() - tic)
except ZeroDivisionError:
speed = float("inf")
logging.info("Epoch[%d] Batch[%d] Speed: %.2f samples/sec" % (epoch, batch_i, speed))
tic = time.time()
tic = None
train_iter.reset()
metric = mx.metric.create(eval_metric)
for batch_i, batch in enumerate(train_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
output = self.net(data)
predictions = mx.nd.argmax(output, axis=1)
metric.update(preds=predictions, labels=label)
train_metric_score = metric.get()[1]
test_iter.reset()
metric = mx.metric.create(eval_metric)
for batch_i, batch in enumerate(test_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
output = self.net(data)
predictions = mx.nd.argmax(output, axis=1)
metric.update(preds=predictions, labels=label)
test_metric_score = metric.get()[1]
logging.info("Epoch[%d] Train: %f, Test: %f" % (epoch, train_metric_score, test_metric_score))
if (epoch - begin_epoch) % checkpoint_period == 0:
self.net.save_parameters(self._model_dir_ + self._model_prefix_ + '-' + str(epoch).zfill(4) + '.params')
self.net.save_parameters(self._model_dir_ + self._model_prefix_ + '-'
+ str(num_epoch + begin_epoch).zfill(4) + '.params')
self.net.export(self._model_dir_ + self._model_prefix_ + '_newest', epoch=0)
def construct(self, context, data_mean=None, data_std=None):
self.net = Net(data_mean=data_mean, data_std=data_std)
self.net.collect_params().initialize(self.weight_initializer, ctx=context)
......
src/main/resources/templates/gluon/CNNDataLoader.ftl 0 → 100644
View file @ 2dd5aae6
import os
import h5py
import mxnet as mx
import logging
import sys
class ${tc.fullArchitectureName}DataLoader:
_input_names_ = [${tc.join(tc.architectureInputs, ",", "'", "'")}]
_output_names_ = [${tc.join(tc.architectureOutputs, ",", "'", "_label'")}]
def __init__(self):
self._data_dir = "${tc.dataPath}/"
def load_data(self, batch_size):
train_h5, test_h5 = self.load_h5_files()
data_mean = train_h5[self._input_names_[0]][:].mean(axis=0)
data_std = train_h5[self._input_names_[0]][:].std(axis=0) + 1e-5
train_iter = mx.io.NDArrayIter(train_h5[self._input_names_[0]],
train_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
test_iter = None
if test_h5 != None:
test_iter = mx.io.NDArrayIter(test_h5[self._input_names_[0]],
test_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
return train_iter, test_iter, data_mean, data_std
def load_h5_files(self):
train_h5 = None
test_h5 = None
train_path = self._data_dir + "train.h5"
test_path = self._data_dir + "test.h5"
if os.path.isfile(train_path):
train_h5 = h5py.File(train_path, 'r')
if not (self._input_names_[0] in train_h5 and self._output_names_[0] in train_h5):
logging.error("The HDF5 file '" + os.path.abspath(train_path) + "' has to contain the datasets: "
+ "'" + self._input_names_[0] + "', '" + self._output_names_[0] + "'")
sys.exit(1)
test_iter = None
if os.path.isfile(test_path):
test_h5 = h5py.File(test_path, 'r')
if not (self._input_names_[0] in test_h5 and self._output_names_[0] in test_h5):
logging.error("The HDF5 file '" + os.path.abspath(test_path) + "' has to contain the datasets: "
+ "'" + self._input_names_[0] + "', '" + self._output_names_[0] + "'")
sys.exit(1)
else:
logging.warning("Couldn't load test set. File '" + os.path.abspath(test_path) + "' does not exist.")
return train_h5, test_h5
else:
logging.error("Data loading failure. File '" + os.path.abspath(train_path) + "' does not exist.")
sys.exit(1)
\ No newline at end of file
src/main/resources/templates/gluon/CNNSupervisedTrainer.ftl 0 → 100644
View file @ 2dd5aae6
import mxnet as mx
import logging
import numpy as np
import time
import os
import shutil
from mxnet import gluon, autograd, nd
class CNNSupervisedTrainer(object):
def __init__(self, data_loader, net_constructor, net=None):
self._data_loader = data_loader
self._net_creator = net_constructor
self._net = net
def train(self, batch_size=64,
num_epoch=10,
eval_metric='acc',
optimizer='adam',
optimizer_params=(('learning_rate', 0.001),),
load_checkpoint=True,
context='gpu',
checkpoint_period=5,
normalize=True):
if context == 'gpu':
mx_context = mx.gpu()
elif context == 'cpu':
mx_context = mx.cpu()
else:
logging.error("Context argument is '" + context + "'. Only 'cpu' and 'gpu are valid arguments'.")
if 'weight_decay' in optimizer_params:
optimizer_params['wd'] = optimizer_params['weight_decay']
del optimizer_params['weight_decay']
if 'learning_rate_decay' in optimizer_params:
min_learning_rate = 1e-08
if 'learning_rate_minimum' in optimizer_params:
min_learning_rate = optimizer_params['learning_rate_minimum']
del optimizer_params['learning_rate_minimum']
optimizer_params['lr_scheduler'] = mx.lr_scheduler.FactorScheduler(
optimizer_params['step_size'],
factor=optimizer_params['learning_rate_decay'],
stop_factor_lr=min_learning_rate)
del optimizer_params['step_size']
del optimizer_params['learning_rate_decay']
train_iter, test_iter, data_mean, data_std = self._data_loader.load_data(batch_size)
if self._net is None:
if normalize:
self._net_creator.construct(
context=mx_context, data_mean=nd.array(data_mean), data_std=nd.array(data_std))
else:
self._net_creator.construct(context=mx_context)
begin_epoch = 0
if load_checkpoint:
begin_epoch = self._net_creator.load(mx_context)
else:
if os.path.isdir(self._net_creator._model_dir_):
shutil.rmtree(self._net_creator._model_dir_)
self._net = self._net_creator.net
try:
os.makedirs(self._net_creator._model_dir_)
except OSError:
if not os.path.isdir(self._net_creator._model_dir_):
raise
trainer = mx.gluon.Trainer(self._net.collect_params(), optimizer, optimizer_params)
if self._net.last_layer == 'softmax':
loss_function = mx.gluon.loss.SoftmaxCrossEntropyLoss()
elif self._net.last_layer == 'sigmoid':
loss_function = mx.gluon.loss.SigmoidBinaryCrossEntropyLoss()
elif self._net.last_layer == 'linear':
loss_function = mx.gluon.loss.L2Loss()
else: # TODO: Change default?
loss_function = mx.gluon.loss.L2Loss()
logging.warning("Invalid last_layer, defaulting to L2 loss")
speed_period = 50
tic = None
for epoch in range(begin_epoch, begin_epoch + num_epoch):
train_iter.reset()
for batch_i, batch in enumerate(train_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
with autograd.record():
output = self._net(data)
loss = loss_function(output, label)
loss.backward()
trainer.step(batch_size)
if tic is None:
tic = time.time()
else:
if batch_i % speed_period == 0:
try:
speed = speed_period * batch_size / (time.time() - tic)
except ZeroDivisionError:
speed = float("inf")
logging.info("Epoch[%d] Batch[%d] Speed: %.2f samples/sec" % (epoch, batch_i, speed))
tic = time.time()
tic = None
train_iter.reset()
metric = mx.metric.create(eval_metric)
for batch_i, batch in enumerate(train_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
output = self._net(data)
predictions = mx.nd.argmax(output, axis=1)
metric.update(preds=predictions, labels=label)
train_metric_score = metric.get()[1]
test_iter.reset()
metric = mx.metric.create(eval_metric)
for batch_i, batch in enumerate(test_iter):
data = batch.data[0].as_in_context(mx_context)
label = batch.label[0].as_in_context(mx_context)
output = self._net(data)
predictions = mx.nd.argmax(output, axis=1)
metric.update(preds=predictions, labels=label)
test_metric_score = metric.get()[1]
logging.info("Epoch[%d] Train: %f, Test: %f" % (epoch, train_metric_score, test_metric_score))
if (epoch - begin_epoch) % checkpoint_period == 0:
self._net.save_parameters(self.parameter_path() + '-' + str(epoch).zfill(4) + '.params')
self._net.save_parameters(self.parameter_path() + '-' + str(num_epoch + begin_epoch).zfill(4) + '.params')
self._net.export(self.parameter_path() + '_newest', epoch=0)
def parameter_path(self):
return self._net_creator._model_dir_ + self._net_creator._model_prefix_
\ No newline at end of file
src/main/resources/templates/gluon/CNNTrainer.ftl
View file @ 2dd5aae6
import logging
import mxnet as mx
import supervised_trainer
<#list configurations as config>
import CNNCreator_${config.instanceName}
import CNNDataLoader_${config.instanceName}
</#list>
if __name__ == "__main__":
......@@ -11,8 +13,12 @@ if __name__ == "__main__":
logger.addHandler(handler)
<#list configurations as config>
${config.instanceName} = CNNCreator_${config.instanceName}.CNNCreator_${config.instanceName}()
${config.instanceName}.train(
${config.instanceName}_creator = CNNCreator_${config.instanceName}.CNNCreator_${config.instanceName}()
${config.instanceName}_loader = CNNDataLoader_${config.instanceName}.${config.instanceName}DataLoader()
${config.instanceName}_trainer = supervised_trainer.CNNSupervisedTrainer(${config.instanceName}_loader,
${config.instanceName}_creator)
${config.instanceName}_trainer.train(
<#if (config.batchSize)??>
batch_size=${config.batchSize},
</#if>
......
src/test/java/de/monticore/lang/monticar/cnnarch/gluongenerator/GenerationTest.java
View file @ 2dd5aae6
......@@ -54,6 +54,7 @@ public class GenerationTest extends AbstractSymtabTest {
Arrays.asList(
"CNNCreator_CifarClassifierNetwork.py",
"CNNNet_CifarClassifierNetwork.py",
"CNNDataLoader_CifarClassifierNetwork.py",
"CNNPredictor_CifarClassifierNetwork.h",
"execute_CifarClassifierNetwork",
"CNNBufferFile.h"));
......@@ -72,6 +73,7 @@ public class GenerationTest extends AbstractSymtabTest {
Arrays.asList(
"CNNCreator_Alexnet.py",
"CNNNet_Alexnet.py",
"CNNDataLoader_Alexnet.py",
"CNNPredictor_Alexnet.h",
"execute_Alexnet"));
}
......@@ -89,6 +91,7 @@ public class GenerationTest extends AbstractSymtabTest {
Arrays.asList(
"CNNCreator_VGG16.py",
"CNNNet_VGG16.py",
"CNNDataLoader_VGG16.py",
"CNNPredictor_VGG16.h",
"execute_VGG16"));
}
......@@ -130,7 +133,8 @@ public class GenerationTest extends AbstractSymtabTest {
Paths.get("./target/generated-sources-cnnarch"),
Paths.get("./src/test/resources/target_code"),
Arrays.asList(
"CNNTrainer_fullConfig.py"));
"CNNTrainer_fullConfig.py",
"supervised_trainer.py"));
}
@Test
......@@ -146,7 +150,8 @@ public class GenerationTest extends AbstractSymtabTest {
Paths.get("./target/generated-sources-cnnarch"),
Paths.get("./src/test/resources/target_code"),
Arrays.asList(
"CNNTrainer_simpleConfig.py"));
"CNNTrainer_simpleConfig.py",
"supervised_trainer.py"));
}
@Test
......@@ -161,7 +166,8 @@ public class GenerationTest extends AbstractSymtabTest {
Paths.get("./target/generated-sources-cnnarch"),
Paths.get("./src/test/resources/target_code"),
Arrays.asList(
"CNNTrainer_emptyConfig.py"));
"CNNTrainer_emptyConfig.py",
"supervised_trainer.py"));
}
......
src/test/resources/target_code/CNNCreator_Alexnet.py
View file @ 2dd5aae6
import mxnet as mx
import logging
import os
import errno
import shutil
import h5py
import sys
import numpy as np
import time
from mxnet import gluon, autograd, nd
from CNNNet_Alexnet import Net
@mx.init.register
class MyConstant(mx.init.Initializer):
def __init__(self, value):
super(MyConstant, self).__init__(value=value)
self.value = value
def _init_weight(self, _, arr):
arr[:] = mx.nd.array(self.value)
class CNNCreator_Alexnet:
_data_dir_ = "data/Alexnet/"
_model_dir_ = "model/Alexnet/"
_model_prefix_ = "model"
_input_names_ = ['data']
_input_shapes_ = [(3,224,224)]
_output_names_ = ['predictions_label']
def __init__(self):
self.weight_initializer = mx.init.Normal()
......@@ -60,176 +41,6 @@ class CNNCreator_Alexnet:
return lastEpoch
def load_data(self, batch_size):
train_h5, test_h5 = self.load_h5_files()
data_mean = train_h5[self._input_names_[0]][:].mean(axis=0)
data_std = train_h5[self._input_names_[0]][:].std(axis=0) + 1e-5
train_iter = mx.io.NDArrayIter(train_h5[self._input_names_[0]],
train_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
test_iter = None
if test_h5 != None:
test_iter = mx.io.NDArrayIter(test_h5[self._input_names_[0]],
test_h5[self._output_names_[0]],
batch_size=batch_size,
data_name=self._input_names_[0],
label_name=self._output_names_[0])
return train_iter, test_iter, data_mean, data_std
def load_h5_files(self):
train_h5 = None
test_h5 = None
train_path = self._data_dir_ + "train.h5"
test_path = self._data_dir_ + "test.h5"
if os.path.isfile(train_path):
train_h5 = h5py.File(train_path, 'r')
if not (self._input_names_[0] in train_h5 and self._output_names_[0] in train_h5):
logging.error("The HDF5 file '" + os.path.abspath(train_path) + "' has to contain the datasets: "
+ "'" + self._input_names_[0] + "', '" + self._output_names_[0] + "'")
sys.exit(1)
test_iter = None
if os.path.isfile(test_path):
test_h5 = h5py.File(test_path, 'r')
if not (self._input_names_[0] in test_h5 and self._output_names_[0]