How to import this model from pytorch to keras? I write model from post bottom but Keras and pytorch models give different results.
class net_pytorch(torch.nn.Module):
def __init__(self,Nin=6,Nout=1,Nlinear=112*60):
super(vel_regressor, self).__init__()
self.model1 = torch.nn.Sequential(
torch.nn.Conv1d(Nin,60,kernel_size=3,stride=1,groups=Nin),
torch.nn.ReLU(),
torch.nn.Conv1d(60,120,kernel_size=3,stride=1,groups=Nin),
torch.nn.ReLU(),
torch.nn.Conv1d(120,240,kernel_size=3,stride=1),
torch.nn.ReLU(),
torch.nn.MaxPool1d(10, stride=6),
)
self.model2=model2=torch.nn.Sequential(
torch.nn.Linear(Nlinear, 10*40),
torch.nn.ReLU(),
torch.nn.Linear(10*40, 100),
torch.nn.ReLU(),
torch.nn.Linear(100, Nout)
)
def forward(self, x):
x = self.model1(x)
x = x.view(x.size(0), -1)
x = self.model2(x)
return x
How I write it in keras:
def net_keras():
model2 = Sequential()
model2.add(layers.SeparableConv1D(60, 3, strides=1, activation='relu', depth_multiplier = 6 , name = 'model1.0', input_shape=(200, 6)))
model2.add(layers.SeparableConv1D(120, 3, strides=1, activation='relu', depth_multiplier = 6, name = 'model1.2'))
model2.add(layers.SeparableConv1D(240, 3, strides=1, activation='relu', name = 'model1.4'))
model2.add(layers.GlobalAveragePooling1D())
model2.add(layers.Dense(6720, activation='relu', name = 'model2.0'))
model2.add(layers.Dense(400, activation='relu', name = 'model2.2'))
model2.add(layers.Dense(100, activation='relu', name = 'model2.4'))
model2.add(layers.Dense(3))
model2.compile(optimizer=Adam(), loss='mae')
return model2
I try to use nn-transfer to convert but have error:
Layer names in PyTorch state_dict ['model1.0', 'model1.2', 'model1.4', 'model2.0', 'model2.2', 'model2.4']
Layer names in Keras HDF5 ['dense_1', 'global_average_pooling1d_1', 'model1.0', 'model1.2', 'model1.4', 'model2.0', 'model2.2', 'model2.4']
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-49-a3986379ed2b> in <module>()
----> 1 transfer.pytorch_to_keras(pytorch_network, model2)
/content/nn-transfer/nn_transfer/transfer.py in pytorch_to_keras(pytorch_model, keras_model, flip_filters, flip_channels, verbose)
122 for layer in pytorch_layer_names:
123
--> 124 params = util.dig_to_params(model_weights[layer])
125
126 weight_key = layer + '.weight'
/content/nn-transfer/nn_transfer/util.py in dig_to_params(keras_h5_layer)
23 # ['dense_2']['dense_3']['conv2d_7']['dense_4']['conv1']
24 while not _contains_weights(keras_h5_layer):
---> 25 keras_h5_layer = keras_h5_layer[list(keras_h5_layer.keys())[0]]
26
27 return keras_h5_layer
AttributeError: 'Dataset' object has no attribute 'keys'
Also I try to use pytorch2keras but it dont work with groups != 1.
MMdnn also dont work with this model (error in image).
MMdnn error
Here is the error place :
model.add(layers.Conv1D(60, 3, strides=1, activation='relu', input_shape=(None, 200), name='model1.0'))
You should use input_shape=(None,6) unless your input is always BatchSizex200x6.
In addition, there are tools to convert models between different architectures, e.g. https://github.com/Microsoft/MMdnn.
Related
I am making multi input cnn model using keras functional api but it
is giving error... data:
trainset1 = trainset.flow_from_directory(
'/content/',
target_size=(404,410),
batch_size=32,
#seed=50,
class_mode='categorical') print('In Training Set..Entropy....') trainset12 = trainset.flow_from_directory(
'/content/',
target_size=(404,410),
batch_size=32,
#seed=50,
class_mode='categorical')
model: input1 = Input(shape=(404,410,3)) input2 = Input(shape =
(404,410,3))
# x = layers.Dense(128, activation= 'relu')
x = layers.Conv2D(25, (5, 5), activation='relu',
padding='same')(input1) x = layers.MaxPool2D(pool_size=(2, 2),
padding='same')(x)
x1 = layers.Conv2D(25, (5, 5), activation='relu',
padding='same')(input2) x1 = layers.MaxPool2D(pool_size=(2, 2),
padding='same')(x1) flat_layer1 = Flatten()(x) flat_layer2 =
Flatten()(x1)
print(flat_layer1.shape)
print(flat_layer2.shape) concat_layer= Concatenate()([flat_layer1,flat_layer2])
concat_layer= concatenate([flat_layer1,flat_layer2])
x = layers.Dense(16, activation= 'relu')(flat_layer1) #(concat_layer) outputs = layers.Dense(2, activation='softmax')(concat_layer) model =
keras.Model(inputs=[input1,input2], outputs = outputs)
model.compile(
loss = keras.losses.BinaryCrossentropy(),
optimizer=keras.optimizers.Adam(learning_rate=0.001),
metrics=["accuracy"] )
model.fit([trainset1,trainset12] ,batch_size=32,epochs=5, verbose=2)
GIVING ERROR:
--------------------------------------------------------------------------- ValueError Traceback (most recent
call last) in ()
----> 1 model.fit([trainset1,trainset12] ,batch_size=32,epochs=5, verbose=2)
1 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/data_adapter.py
in select_data_adapter(x, y)
989 "Failed to find data adapter that can handle "
990 "input: {}, {}".format(
--> 991 _type_name(x), _type_name(y)))
992 elif len(adapter_cls) > 1:
993 raise RuntimeError(
ValueError: Failed to find data adapter that can handle input:
(<class 'list'> containing values of types {"<class
'keras.preprocessing.image.DirectoryIterator'>"}), <class
'NoneType'"""
what should i do now?
So, here is a sample code for the domain adaptation model, and all I want to do is to save the model and load it,
#tf.custom_gradient
def grad_reverse(x):
y = tf.identity(x)
def custom_grad(dy):
return -dy
return y, custom_grad
class GradReverse(tf.keras.layers.Layer):
def __init__(self):
super().__init__(name="grl")
def call(self, x):
return grad_reverse(x)
def get_adaptable_network(input_shape=x_source_train.shape[1:]):
inputs = Input(shape=input_shape)
x = Conv2D(32, 5, padding='same', activation='relu', name='conv2d_1')(inputs)
x = MaxPool2D(pool_size=2, strides=2, name='max_pooling2d_1')(x)
x = Conv2D(48, 5, padding='same', activation='relu', name='conv2d_2')(x)
x = MaxPool2D(pool_size=2, strides=2, name='max_pooling2d_2')(x)
features = Flatten(name='flatten_1')(x)
x = Dense(100, activation='relu', name='dense_digits_1')(features)
x = Dense(100, activation='relu', name='dense_digits_2')(x)
digits_classifier = Dense(10, activation="softmax", name="digits_classifier")(x)
domain_branch = Dense(100, activation="relu", name="dense_domain")(GradReverse()(features))
domain_classifier = Dense(1, activation="sigmoid", name="domain_classifier")(domain_branch)
return Model(inputs=inputs, outputs=[digits_classifier, domain_classifier])
model = get_adaptable_network()
model.summary()
# download the model in computer for later use
model.save('DA_MNIST_to_MNIST_m.h5')
from tensorflow import keras
model = keras.models.load_model('DA_MNIST_to_MNIST_m.h5',custom_objects={'?':? })
I am not sure what to put on the custom_objects part, since there is a custom gradient reversal layer implemented for domain adaptation in tensorflow. When I do load the model, it gives an error:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/utils/generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
294 cls = get_registered_object(class_name, custom_objects, module_objects)
295 if cls is None:
--> 296 raise ValueError('Unknown ' + printable_module_name + ': ' + class_name)
297
298 cls_config = config['config']
ValueError: Unknown layer: GradReverse
I am doing MNIST to MNIST_M domain adaptation, and any help would be useful!
I figured it out, I needed to change the GradReverse layer's init function with **kwargs, This object will then accept any other keyword argument that i haven't included.
class GradReverse(tf.keras.layers.Layer):
def __init__(self, **kwargs):
super().__init__(name="grl")
def call(self, x):
return grad_reverse(x)
In load model, we can use this,
from tensorflow import keras
model = keras.models.load_model('DA_MNIST_to_MNIST_m.h5',custom_objects={'GradReverse':GradReverse})
I'm trying to run a simple autoencoder model. I'm reading training data from a csv which consists of word embeddings. I have this code, but the error in the title is raised in model.fit() function and connected with my validation data. I tried many things however the error remained. I'm new in NLP and maybe my logic is totally wrong I don't know. So, I'd be appreciated if anybody can help. Here is my code:
def train_predict(df):
X_train, X_validation = train_test_split(df, test_size=0.3, random_state=42, shuffle=True)
X = X_train.iloc[:, :-1].to_numpy() #shape is (1880,220) in here
X = tf.expand_dims(X, axis=-1) #shape is (1880,220,1)
X_val = X_validation.iloc[:,:-1].to_numpy() #shape is (300,220)
X_val= tf.expand_dims(X_val, axis=-1) #shape is (300,220,1)
inputs, decoder_output, visualization = autoEncoder(X)
model = Model(inputs=inputs, outputs=decoder_output)
encoder_model = Model(inputs=inputs, outputs=visualization)
batch_size = 128
train_steps = len(X) // batch_size
val_steps = len(X_val) // batch_size
model.summary()
model.compile(optimizer='adam', metrics=['accuracy'], loss='mean_squared_error')
model.fit(X, steps_per_epoch=train_steps, validation_data=X_val, validation_steps=val_steps,epochs=100)
result = model.evaluate(X_val, steps=10)
Also the detail of my autoEncoder function code is as follows:
def autoEncoder(X_train):
inputs = tf.keras.layers.Input(shape=(X_train.shape[1],1))
# parameters
conv_1 = Conv1D(filters=64, kernel_size=3, activation='relu', padding='same')(inputs)
max_pool_1 = MaxPool1D(pool_size=2)(conv_1)
conv_2 = Conv1D(filters=128, kernel_size=3, activation='relu', padding='same')(max_pool_1)
max_pool_2 = MaxPool1D(pool_size=2)(conv_2)
# BOTTLE NECK
bottle_neck = Conv1D(filters=256, kernel_size=3, activation='relu', padding='same')(max_pool_2)
visualization = Conv1D(filters=1, kernel_size=3, activation='sigmoid', padding='same')(bottle_neck)
# DECODER
conv_3 = Conv1D(filters=128, kernel_size=3, activation='relu', padding='same')(bottle_neck)
upsample_1 = UpSampling1D(size=2)(conv_3)
conv_4 = Conv1D(filters=64, kernel_size=3, activation='relu', padding='same')(upsample_1)
upsample_2 = UpSampling1D(size=2)(conv_4)
decoder_output = Conv1D(filters=1, kernel_size=3, activation='sigmoid', padding='same')(upsample_2)
return inputs, decoder_output, visualization
It'd be excellent if you could copy-paste the entire stack of error that your code produces, something that everyone should follow for error-related questions because that makes debugging that much easier.
Here's an attempt to reproduce the same error using a dummy dataset:
import numpy as np
import tensorflow as tf
np.random.seed(11)
np.set_printoptions(precision=2)
def autoEncoder(X_train):
inputs = tf.keras.layers.Input(shape=(X_train.shape[1], 1))
conv_1 = tf.keras.layers.Conv1D(filters=64, kernel_size=3, activation='relu', padding='same')(inputs)
max_pool_1 = tf.keras.layers.MaxPool1D(pool_size=2)(conv_1)
conv_2 = tf.keras.layers.Conv1D(filters=128, kernel_size=3, activation='relu', padding='same')(max_pool_1)
max_pool_2 = tf.keras.layers.MaxPool1D(pool_size=2)(conv_2)
bottle_neck = tf.keras.layers.Conv1D(filters=256, kernel_size=3, activation='relu', padding='same')(max_pool_2)
visualization = tf.keras.layers.Conv1D(filters=1, kernel_size=3, activation='sigmoid', padding='same')(bottle_neck)
conv_3 = tf.keras.layers.Conv1D(filters=128, kernel_size=3, activation='relu', padding='same')(bottle_neck)
upsample_1 = tf.keras.layers.UpSampling1D(size=2)(conv_3)
conv_4 = tf.keras.layers.Conv1D(filters=64, kernel_size=3, activation='relu', padding='same')(upsample_1)
upsample_2 = tf.keras.layers.UpSampling1D(size=2)(conv_4)
decoder_output = tf.keras.layers.Conv1D(filters=1, kernel_size=3, activation='sigmoid', padding='same')(upsample_2)
return inputs, decoder_output, visualization
X = np.random.randn(1880, 220)
X_val = np.random.randn(300, 220)
X = np.expand_dims(X, axis=-1)
X = tf.convert_to_tensor(X) # (1880, 220, 1)
X_val = np.expand_dims(X_val, axis=-1)
X_val = tf.convert_to_tensor(X_val) # (300, 220, 1)
inputs, decoder_output, visualization = autoEncoder(X)
model = tf.keras.Model(inputs=inputs, outputs=decoder_output)
encoder_model = tf.keras.Model(inputs=inputs, outputs=visualization)
batch_size = 128
train_steps = len(X) // batch_size
val_steps = len(X_val) // batch_size
model.compile(optimizer='adam', metrics=['accuracy'], loss='mean_squared_error')
model.fit(X, steps_per_epoch=train_steps, validation_data = X_val, validation_steps=val_steps, epochs=100)
On google-colab this gives the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-29-a889c5a46f35> in <module>()
3 val_steps = len(X_val) // batch_size
4 model.compile(optimizer='adam', metrics=['accuracy'], loss='mean_squared_error')
----> 5 model.fit(X, steps_per_epoch=train_steps, validation_data = X_val, validation_steps=val_steps, epochs=100)
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1041 (x, y, sample_weight), validation_split=validation_split))
1042
-> 1043 if validation_data:
1044 val_x, val_y, val_sample_weight = (
1045 data_adapter.unpack_x_y_sample_weight(validation_data))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in __bool__(self)
990
991 def __bool__(self):
--> 992 return bool(self._numpy())
993
994 __nonzero__ = __bool__
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
which is identical to your OP. The reason it'd be better to post the error stack is because the answer is hidden in these lines, specifically:
1043 if validation_data:
1044 val_x, val_y, val_sample_weight = (
1045 data_adapter.unpack_x_y_sample_weight(validation_data))
The format of validation_data is identical to (x, y, sample_weight). Here's what fit method documentation has to say:
validation_data will override validation_split. validation_data could be: - tuple (x_val, y_val) of Numpy arrays or tensors - tuple (x_val, y_val, val_sample_weights) of Numpy arrays - dataset For the first two cases, batch_size must be provided. For the last case, validation_steps could be provided.
I think you now understand why you're getting an error, there's no Y for the your autoencoder. Which shouldn't be of any concern since your X itself is your Y. Here's a line from an encoder tutorial that would help us in this situation:
Train the model using x_train as both the input and the target. The encoder will learn to compress the dataset from 784 dimensions to the latent space, and the decoder will learn to reconstruct the original images.
So, what you were expected to do is to write the following:
model.fit(X, X, steps_per_epoch=train_steps, validation_data=(X_val, X_val), validation_steps=val_steps, epochs=100)
which indeed starts the training!
I'm having trouble adapting an existing Keras model to work with TenforFlow Federated.
The existing model is a 1D convolutional autoencoder (details shown below)
Existing Model:
input_window = Input(shape=(window_length,1))
x = Conv1D(16, 3, activation="relu", padding="same")(input_window)
x = MaxPooling1D(2, padding="same")(x)
x = Conv1D(1, 3, activation="relu", padding="same")(x)
encoded = MaxPooling1D(2, padding="same")(x)
encoder = Model(input_window, encoded)
x = Conv1D(1, 3, activation="relu", padding="same")(encoded)
x = UpSampling1D(2)(x)
x = Conv1D(16, 1, activation='relu')(x)
x = UpSampling1D(2)(x)
decoded = Conv1D(1, 3, activation='sigmoid', padding='same')(x)
autoencoder = Model(input_window, decoded)
Training data is passed as a numpy.ndarray of shape (102, 48, 1).
Conceptually, this represents 102 days worth of data, each containg 48 values. I can provide an example of this if it would assist in answering.
My attempt to convert the model is shown below.
Converted Model:
def create_compiled_keras_model():
input_window = tf.keras.layers.Input(shape=(window_length,1))
x = tf.keras.layers.Conv1D(16, 3, activation="relu", padding="same")(input_window)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x = tf.keras.layers.Conv1D(1, 3, activation="relu", padding="same")(x)
encoded = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
encoder = tf.keras.Model(input_window, encoded)
x = tf.keras.layers.Conv1D(1, 3, activation="relu", padding="same")(encoded)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(16, 1, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
decoded = tf.keras.layers.Conv1D(1, 3, activation='sigmoid', padding='same')(x)
autoencoder = tf.keras.Model(input_window, decoded)
autoencoder.compile(optimizer='adam', loss='MSE')
return autoencoder
sample_batch = train // numpy.ndarray of shape (102, 48, 1)
def model_fn():
keras_model = create_compiled_keras_model()
return tff.learning.from_compiled_keras_model(keras_model, train)
This produces the error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-397-9bed171c79be> in <module>
----> 1 model = model_fn()
<ipython-input-396-13bc1955a7f2> in model_fn()
1 def model_fn():
2 keras_model = create_compiled_keras_model()
----> 3 return tff.learning.from_compiled_keras_model(keras_model, train)
~/miniconda3/lib/python3.6/site-packages/tensorflow_federated/python/learning/model_utils.py in from_compiled_keras_model(keras_model, dummy_batch)
190 raise ValueError('`keras_model` must be compiled. Use from_keras_model() '
191 'instead.')
--> 192 return enhance(_TrainableKerasModel(keras_model, dummy_batch))
193
194
~/miniconda3/lib/python3.6/site-packages/tensorflow_federated/python/learning/model_utils.py in __init__(self, inner_model, dummy_batch)
434 # until the model has been called on input. The work-around is to call
435 # Model.test_on_batch() once before asking for metrics.
--> 436 inner_model.test_on_batch(**dummy_batch)
437 # This must occur after test_on_batch()
438 if len(inner_model.loss_functions) != 1:
TypeError: test_on_batch() argument after ** must be a mapping, not numpy.ndarray
So far I have been unable to resolve this.
Is this an issue relating to my model not being compiled correctly, or due to the way I'm passing data?
Any help in resolving this would be greatly appreciated, thanks!
The sample batch should be something that can be passed to batch_input argument of tff.learning.Model.forward_pass.
For wrapped Keras models, this must be a dict with keys matching the arguments to tf.keras.models.Model.test_on_batch.
For this case, I think you may be able to simply wrap the sample batch in a dict with a single key of x:
numpy_sample_batch = train // numpy.ndarray
sample_batch = {'x': numpy_sample_batch}
I am using the Keras functional API to build a model with multiple (five) outputs and the same input, in order to simultaneously predict different properties of the data (images in my case).
The summary of that model is the following (with capitals are the layers that have been added on top of the pre-trained VGG16) :
The shape of the data being fed to the CNN are the following:
# input images
('x_train shape:', (23706, 224, 224, 3))
('Head_1 shape:', (23706, 26))
('Head_2 shape:', (23706,))
('Head_3 shape:', (23706,))
('Head_4 shape:', (23706,))
('Head_5 shape:', (23706,))
When I put only a single output to my network the training is carried out without problems, but when all the outputs (or even 2 of them) are present, I am receiving the following error:
Traceback (most recent call last):
history = model.fit_generator(datagen.flow(x_train, train_targets_list, batch_size=batch_size)
.
.
.
.
ValueError: could not broadcast input array from shape (23706,26) into shape (23706)
Any idea what I am doing wrong?
Also is there any working example in the documentation that describes a similar case for multi-output models?
# dimensions of our images.
img_width, img_height = 224, 224
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
input_tensor = Input(shape=input_shape, name='IMAGES')
base_model = VGG16(weights='imagenet', include_top=False, input_tensor=input_tensor)
x = base_model.output
x = GlobalAveragePooling2D(name='GAP')(x)
x = Dense(256, activation='relu', name='FC1')(x)
x = Dropout(0.5, name='DROPOUT')(x)
head_1 = Dense(26, activation='sigmoid', name='PREDICTION1') (x)
head_2 = Dense (1, name='PREDICTION2')(x)
head_3 = Dense (1, name='PREDICTION3')(x)
head_4 = Dense (1, name='PREDICTION4')(x)
head_5 = Dense (1, name='PREDICTION5')(x)
outputs_list = [head_1, head_2, head_3, head_4, head_5]
model = Model(inputs=input_tensor, outputs=outputs_list)
for layer in base_model.layers:
layer.trainable = False
losses_list = ['binary_crossentropy','mse','mse','mse', 'mse']
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
loss=losses_list,
metrics=['accuracy'])
print x_train.shape -> (23706, 224, 224, 3)
for y in train_targets_list:
print len(y)
23706
23706
23706
23706
23706