def test_sequential_lstm_mxnet_model_saving():
max_features = 1000
maxlen = 80
batch_size = 32
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
model.add(LSTM(128, unroll=True))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
# Generate random data
x = np.random.random((1000, maxlen))
y = np.random.random((1000, 128))
print("X shape - ", x.shape)
print("Y shape - ", y.shape)
model.fit(x, y, batch_size=batch_size, epochs=2)
save_mxnet_model(model, prefix='test_lstm', epoch=0)
# Import with MXNet and try to perform inference
import mxnet as mx
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix='test_lstm', epoch=0)
mod = mx.mod.Module(symbol=sym, data_names=['/embedding_1_input1'], context=mx.cpu(), label_names=None)
mod.bind(for_training=False, data_shapes=[('/embedding_1_input1', (1, 80))], label_shapes=mod._label_shapes)
mod.set_params(arg_params, aux_params, allow_missing=True)
data_iter = mx.io.NDArrayIter([mx.nd.random.normal(shape=(1, 80))], label=None, batch_size=1)
mod.predict(data_iter)
os.remove('test_lstm-symbol.json')
os.remove('test_lstm-0000.params')
def test_sequential_mxnet_model_saving_no_compile():
model = Sequential()
model.add(Dense(2, input_shape=(3, )))
model.add(RepeatVector(3))
model.add(TimeDistributed(Dense(3)))
with pytest.raises(AssertionError):
save_mxnet_model(model, prefix='test', epoch=0)
def test_sequential_mxnet_model_not_compiled():
model = Sequential()
model.add(Dense(8, input_shape=(32, )))
model.add(Dense(4, input_shape=(8, )))
model_prefix = 'test_dense'
with pytest.raises(AssertionError):
save_mxnet_model(model, model_prefix, epoch=0)
def test_sequential_mxnet_model_saving():
model = Sequential()
model.add(Dense(2, input_shape=(3, )))
model.add(RepeatVector(3))
model.add(TimeDistributed(Dense(3)))
model.compile(loss=losses.MSE,
optimizer=optimizers.RMSprop(lr=0.0001),
metrics=[metrics.categorical_accuracy],
sample_weight_mode='temporal')
x = np.random.random((1, 3))
y = np.random.random((1, 3, 3))
model.train_on_batch(x, y)
data_names, _ = save_mxnet_model(model, prefix='test', epoch=0)
# Import with MXNet and try to perform inference
import mxnet as mx
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix='test',
epoch=0)
mod = mx.mod.Module(symbol=sym,
data_names=data_names,
context=mx.cpu(),
label_names=None)
mod.bind(for_training=False,
data_shapes=[(data_names[0], (1, 3))],
label_shapes=mod._label_shapes)
mod.set_params(arg_params, aux_params, allow_missing=True)
data_iter = mx.io.NDArrayIter([mx.nd.random.normal(shape=(1, 3))],
label=None,
batch_size=1)
mod.predict(data_iter)
os.remove('test-symbol.json')
os.remove('test-0000.params')
def save_model(model, model_dir):
prefix = 'mnist_cnn'
params_filename = '{}-0000.params'.format(prefix)
symbol_filename = '{}-symbol.json'.format(prefix)
data_names, data_shapes = save_mxnet_model(model=model,
prefix=prefix,
epoch=0)
shutil.copy(src=str(Path('.', params_filename)),
dst=str(Path(model_dir, params_filename)))
shutil.copy(src=str(Path('.', symbol_filename)),
dst=str(Path(model_dir, symbol_filename)))
def test_sequential_lstm_mxnet_model_saving():
maxlen = 80
model = Sequential()
model.add(Embedding(1000, 128, input_length=maxlen))
model.add(LSTM(128, unroll=True))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
# Generate data for dummy network
X = np.random.random((1000, 80))
Y = np.random.random((1000, 128))
model.fit(X, Y, batch_size=32, nb_epoch=2)
model_prefix = 'test_lstm'
data_names, data_shapes = save_mxnet_model(model,
prefix=model_prefix,
epoch=0)
# Import with MXNet and try to perform inference
import mxnet as mx
X_dummy_for_pred = mx.nd.random.normal(shape=(1, 80))
pred_keras = model.predict([X_dummy_for_pred.asnumpy()], batch_size=1)
sym, arg_params, aux_params = mx.model.load_checkpoint(model_prefix,
epoch=0)
mod = mx.mod.Module(symbol=sym,
data_names=[data_names[0]],
context=mx.cpu(),
label_names=None)
mod.bind(for_training=False,
data_shapes=[(data_names[0], (1, 80))],
label_shapes=mod._label_shapes)
mod.set_params(arg_params, aux_params, allow_missing=True)
data_iter = mx.io.NDArrayIter([X_dummy_for_pred], label=None, batch_size=1)
pred_mxnet = mod.predict(data_iter)
# Check if predictions made through mxnet and keras model are same
assert_allclose(pred_mxnet.asnumpy(), pred_keras, rtol=1e-03)
os.remove(model_prefix + "-symbol.json")
os.remove(model_prefix + "-0000.params")
def test_sequential_get_mxnet_model_info():
model = Sequential()
model.add(Dense(2, input_shape=(3, )))
model.add(RepeatVector(3))
model.add(TimeDistributed(Dense(3)))
model.compile(loss=losses.MSE,
optimizer=optimizers.RMSprop(lr=0.0001),
metrics=[metrics.categorical_accuracy],
sample_weight_mode='temporal')
x = np.random.random((1, 3))
y = np.random.random((1, 3, 3))
model.train_on_batch(x, y)
data_names, data_shapes = K.get_mxnet_model_info(model)
data_names_saved_model, data_shapes_saved_model = save_mxnet_model(
model, prefix='test', epoch=0)
# Only one input
assert len(data_names) == 1
# Example data_names = ['/dense_8_input1']
assert data_names[0].startswith('/dense_')
# Example data_shape = [DataDesc[/dense_8_input1,(1, 3),float32,NCHW]]
assert len(data_shapes) == 1
assert data_shapes[0].name == data_names[0]
# In this example, we are passing x as input with shape (1,3)
assert data_shapes[0].shape == (1, 3)
# Compare with returned values from Save MXNet Model API. They should be the same.
assert len(data_names) == len(data_names_saved_model)
assert data_names[0] == data_names_saved_model[0]
assert len(data_shapes) == len(data_shapes_saved_model)
assert data_shapes[0].name == data_shapes_saved_model[0].name
assert data_shapes[0].shape == data_shapes_saved_model[0].shape
os.remove('test-symbol.json')
os.remove('test-0000.params')
def test_sequential_dense_mxnet_model_saving():
model = Sequential()
model.add(Dense(8, input_shape=(32, )))
model.add(Dense(4, input_shape=(8, )))
model.compile(loss='mean_squared_error', optimizer='sgd')
# Generate data for dummy network
X = np.random.random((8, 32))
Y = np.random.random((8, 4))
model.fit(X, Y, batch_size=8, nb_epoch=5)
model_prefix = 'test_dense'
data_names, data_shapes = save_mxnet_model(model, model_prefix, epoch=1)
# Import with MXNet and try to perform inference
import mxnet as mx
X_dummy_for_pred = mx.nd.random.normal(shape=(4, 32))
pred_keras = model.predict([X_dummy_for_pred.asnumpy()], batch_size=4)
sym, arg_params, aux_params = mx.model.load_checkpoint(model_prefix,
epoch=1)
mod = mx.mod.Module(symbol=sym,
data_names=[data_names[0]],
context=mx.cpu(),
label_names=None)
mod.bind(for_training=False,
data_shapes=[(data_names[0], (4, 32))],
label_shapes=mod._label_shapes)
mod.set_params(arg_params, aux_params, allow_missing=True)
data_iter = mx.io.NDArrayIter([X_dummy_for_pred], label=None, batch_size=1)
pred_mxnet = mod.predict(data_iter)
# Check if predictions made through mxnet and keras model are same
assert_allclose(pred_mxnet.asnumpy(), pred_keras, rtol=1e-03)
os.remove(model_prefix + "-symbol.json")
os.remove(model_prefix + "-0001.params")
trainable=False,
name="embed"))
model.add(
Conv1D(filters=128, kernel_size=3, activation='relu', name="conv_1"))
model.add(MaxPooling1D(pool_size=5, name="maxpool_1"))
model.add(Flatten(name="flat_1"))
model.add(Dropout(0.3, name="dropout_1"))
model.add(Dense(128, activation='relu', name="dense_1"))
model.add(Dense(args.num_classes, activation='softmax', name="out_1"))
# compile the model
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
model.summary()
model.fit(x_train, y_train, batch_size=16, epochs=args.epochs, verbose=2)
model.evaluate(x_test, y_test, verbose=2)
model_prefix = os.path.join(args.model_dir, 'model')
model.save(model_prefix + '.hd5')
data_name, data_shapes = save_mxnet_model(model=model,
prefix=model_prefix,
epoch=0)
signature = [{
'name': data_name[0],
'shape': [dim for dim in data_desc.shape]
} for data_desc in data_shapes]
with open(os.path.join(args.model_dir, 'model-shapes.json'), 'w') as f:
json.dump(signature, f)
model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model_name = 'mnist-cnn-' + str(epochs)
model.save(model_path + '/' + model_name + '.hd5') # Keras model
print("Saved Keras model")
save_mxnet_model(model=model,
prefix=model_path + '/' + model_name) # MXNet model
print("Saved MXNet model")
sys.exit(0)
except Exception as e:
# Write out an error file. This will be returned as the failureReason in the
# DescribeTrainingJob result.
trc = traceback.format_exc()
with open(os.path.join(output_path, 'failure'), 'w') as s:
s.write('Exception during training: ' + str(e) + '\n' + trc)
# Printing this causes the exception to be in the training job logs, as well.
print('Exception during training: ' + str(e) + '\n' + trc, file=sys.stderr)
# A non-zero exit code causes the training job to be marked as Failed.
sys.exit(255)
model = Sequential()
model.add(
Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
# Step 2: Save the model in MXNet model format.
# data_names and data_shapes are values of the parameters to be used when loading the Model in MXNet.
data_names, data_shapes = save_mxnet_model(model=model,
prefix='mnist_cnn',
epoch=0)
out = new_classification_layer(base_model.layers[-2].output)
# create a new network between inp and out
model_new = Model(inp, out)
model_new.summary()
# make all layers untrainable by freezing weights (except for last layer)
for layer in model_new.layers[:-1]:
layer.trainable = False
# ensure the last layer is trainable/not frozen
for layer in model_new.layers[-1:]:
layer.trainable = True
# check to see it is correct:
for layer in model_new.layers:
print(layer.trainable)
model_new.compile(Adam(lr=.0001), loss="categorical_crossentropy", metrics=['accuracy'])
model_new.summary()
# We train the model, in this case using a low size of epochs, since the model learns the data quite quickly
model_new.fit_generator(train_batches, steps_per_epoch=101,
validation_data=valid_batches, validation_steps=106, epochs=25, verbose=2)
model_new.fit_generator(train_batches, steps_per_epoch=101,
validation_data=valid_batches, validation_steps=106, epochs=5, verbose=2)
#model_new.save("VGG16signature.h5")
data_names, data_shapes = save_mxnet_model(model=model_new, prefix='signature_cnn', epoch=0)
