implement tensorflow bi-directional code to pytorch - tensorflow

def encoder():
enc = keras.Sequential()
enc.add(Input(shape=(maxlen,), name='Encoder-Input'))
enc.add(Embedding(num_words, embed_dim,input_length = maxlen, name='Body-Word-Embedding', mask_zero=False))
enc.add(Bidirectional(LSTM(128, activation='relu', name='Encoder-Last-LSTM')))
return enc
Here in the final layer I get output shape of Batchx256.
On pytorch:
class EncoderRNN(nn.Module):
def __init__(self):
super(EncoderRNN, self).__init__()
self.embedding = nn.Embedding(vocab_size, embed_dim)
self.lstm = nn.LSTM(embed_dim, embed_dim, 2, bidirectional=True, batch_first=False)
self.relu = nn.ReLU()
def forward(self, input_, hidden, c):
embedded = self.embedding(input_).transpose(0, 1)
output, (hn, cn) = self.lstm(embedded, (hidden, c))
return output, hn, cn
def initHidden(self):
return torch.zeros(2*2, 16, 128, device=device), torch.zeros(2*2, 16, 128, device=device)
Here I get output of shape sequence_length x batch x 256 but I want to get batchx256
How can I get the same model in pytorch? I know LSTM in pytorch has bidirectional parameter but the way it handles input seems different

Related

implement tensorflow bi-directional code to pytorch to get same output

def encoder():
enc = keras.Sequential()
enc.add(Input(shape=(maxlen,), name='Encoder-Input'))
enc.add(Embedding(num_words, embed_dim,input_length = maxlen, name='Body-Word-Embedding', mask_zero=False))
enc.add(Bidirectional(LSTM(128, activation='relu', name='Encoder-Last-LSTM')))
return enc
Here I get output of shape Batch x 256
In pytorch:
class EncoderRNN(nn.Module):
def __init__(self):
super(EncoderRNN, self).__init__()
self.embedding = nn.Embedding(vocab_size, embed_dim)
self.lstm = nn.LSTM(embed_dim, embed_dim, 2, bidirectional=True, batch_first=False)
self.relu = nn.ReLU()
def forward(self, input_, hidden, c):
embedded = self.embedding(input_).transpose(0, 1)
output, (hn, cn) = self.lstm(embedded, (hidden, c))
output = self.relu(output)
return out, hn, cn
def initHidden(self):
return torch.zeros(2*2, 16, 128, device=device), torch.zeros(2*2, 16, 128, device=device)
But here I get output of shape: sequence length x batch x 256 and I want to get batch x 256
How to implement the exact code of tensorflow to pytorch?

How to make a Keras Dense Layer deal with 3D tensor as input for this Softmax Fully Connected Layer?

I am working on a custom problem, and i have to change the fully connected layer (Dense with softmax), My model code is something like this (with Keras Framework):
.......
batch_size = 8
inputs = tf.random.uniform(shape=[batch_size,1024,256],dtype=tf.dtypes.float32)
preds = Dense(num_classes,activation='softmax')(x) #final layer with softmax activation
....
model = Model(inputs=base_model.input,outputs=preds)
So, i have to change the Code of Dense Layer to output a Tensor of probabilities with the shape of [batch_size, 1024, num_classes], without using a for loop, i need it to be optimized and not a consuming time function
The Dense code version that i want to change:
class Dense(Layer):
"""Just your regular densely-connected NN layer.
`Dense` implements the operation:
`output = activation(dot(input, kernel) + bias)`
where `activation` is the element-wise activation function
passed as the `activation` argument, `kernel` is a weights matrix
created by the layer, and `bias` is a bias vector created by the layer
(only applicable if `use_bias` is `True`).
Note: if the input to the layer has a rank greater than 2, then
it is flattened prior to the initial dot product with `kernel`.
# Example
```python
# as first layer in a sequential model:
model = Sequential()
model.add(Dense(32, input_shape=(16,)))
# now the model will take as input arrays of shape (*, 16)
# and output arrays of shape (*, 32)
# after the first layer, you don't need to specify
# the size of the input anymore:
model.add(Dense(32))
```
# Arguments
units: Positive integer, dimensionality of the output space.
activation: Activation function to use
(see [activations](../activations.md)).
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
(see [initializers](../initializers.md)).
bias_initializer: Initializer for the bias vector
(see [initializers](../initializers.md)).
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
(see [regularizer](../regularizers.md)).
bias_regularizer: Regularizer function applied to the bias vector
(see [regularizer](../regularizers.md)).
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
(see [regularizer](../regularizers.md)).
kernel_constraint: Constraint function applied to
the `kernel` weights matrix
(see [constraints](../constraints.md)).
bias_constraint: Constraint function applied to the bias vector
(see [constraints](../constraints.md)).
# Input shape
nD tensor with shape: `(batch_size, ..., input_dim)`.
The most common situation would be
a 2D input with shape `(batch_size, input_dim)`.
# Output shape
nD tensor with shape: `(batch_size, ..., units)`.
For instance, for a 2D input with shape `(batch_size, input_dim)`,
the output would have shape `(batch_size, units)`.
"""
def __init__(self, units,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
if 'input_shape' not in kwargs and 'input_dim' in kwargs:
kwargs['input_shape'] = (kwargs.pop('input_dim'),)
super(Dense, self).__init__(**kwargs)
self.units = units
self.activation = activations.get(activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.bias_constraint = constraints.get(bias_constraint)
self.input_spec = InputSpec(min_ndim=2)
self.supports_masking = True
def build(self, input_shape):
assert len(input_shape) >= 2
input_dim = input_shape[-1]
self.kernel = self.add_weight(shape=(input_dim, self.units),
initializer=self.kernel_initializer,
name='kernel',
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
if self.use_bias:
self.bias = self.add_weight(shape=(self.units,),
initializer=self.bias_initializer,
name='bias',
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
else:
self.bias = None
self.input_spec = InputSpec(min_ndim=2, axes={-1: input_dim})
self.built = True
def call(self, inputs):
output = K.dot(inputs, self.kernel)
if self.use_bias:
output = K.bias_add(output, self.bias)
if self.activation is not None:
output = self.activation(output)
return output
def compute_output_shape(self, input_shape):
assert input_shape and len(input_shape) >= 2
assert input_shape[-1]
output_shape = list(input_shape)
output_shape[-1] = self.units
return tuple(output_shape)
def get_config(self):
config = {
'units': self.units,
'activation': activations.serialize(self.activation),
'use_bias': self.use_bias,
'kernel_initializer': initializers.serialize(self.kernel_initializer),
'bias_initializer': initializers.serialize(self.bias_initializer),
'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
'bias_regularizer': regularizers.serialize(self.bias_regularizer),
'activity_regularizer': regularizers.serialize(self.activity_regularizer),
'kernel_constraint': constraints.serialize(self.kernel_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(Dense, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
There are three different ways in which this can be done (that I can think of). If you want to have a single dense layer, that maps a vector of 256 elements to a vector of num_classes elements, and apply it all across your batch of data (that is, use the same 256 x num_classes matrix of weights for every sample), then you don't need to do anything special, just use a regular Dense layer:
import tensorflow as tf
from tensorflow.keras import Input
from tensorflow.keras.layers import Dense
batch_size = 8
num_classes = 10
inp = Input(shape=(1024, 256))
layer = Dense(num_classes, activation='softmax')
out = layer(inp)
print(out.shape)
# (None, 1024, 10)
print(layer.count_params())
# 2570
Another way would be to have a single huge Dense layer that takes all 1024 * 256 values in at the same time and produces all 1024 * num_classes values at the output, that is, a layer with a matrix of weights with shape (1024 * 256) x (1024 * num_classes) (in the order if gigabytes of memory!). This is easy to do too, although it seems unlikely to be what you need:
import tensorflow as tf
from tensorflow.keras import Input
from tensorflow.keras.layers import Flatten, Dense, Reshape, Softmax
batch_size = 8
num_classes = 10
inp = Input(shape=(1024, 256))
res = Flatten()(inp)
# This takes _a lot_ of memory!
layer = Dense(1024 * num_classes, activation=None)
out_res = layer(res)
# Apply softmax after reshaping
out_preact = Reshape((-1, num_classes))(out_res)
out = Softmax()(out_preact)
print(out.shape)
# (None, 1024, 10)
print(layer.count_params())
# 2684364800
Finally, you may want to have a set of 1024 weight matrices, each one applied to the corresponding sample in the input, which would imply an array of weights with shape (1024, 256, num_classes). I don't think this can be done with one of the standard Keras layers (or don't know how to)1, but it's easy enough to write a custom layer based on Dense to do that:
import tensorflow as tf
from tensorflow.keras.layers import Dense, InputSpec
class Dense2D(Dense):
def __init__(self, *args, **kwargs):
super(Dense2D, self).__init__(*args, **kwargs)
def build(self, input_shape):
assert len(input_shape) >= 3
input_dim1 = input_shape[-2]
input_dim2 = input_shape[-1]
self.kernel = self.add_weight(shape=(input_dim1, input_dim2, self.units),
initializer=self.kernel_initializer,
name='kernel',
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
if self.use_bias:
self.bias = self.add_weight(shape=(input_dim1, self.units),
initializer=self.bias_initializer,
name='bias',
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
else:
self.bias = None
self.input_spec = InputSpec(min_ndim=3, axes={-2: input_dim1, -1: input_dim2})
self.built = True
def call(self, inputs):
# Multiply each set of weights with each input element
output = tf.einsum('...ij,ijk->...ik', inputs, self.kernel)
if self.use_bias:
output += self.bias
if self.activation is not None:
output = self.activation(output)
return output
def compute_output_shape(self, input_shape):
assert input_shape and len(input_shape) >= 3
assert input_shape[-1]
output_shape = list(input_shape)
output_shape[-1] = self.units
return tuple(output_shape)
You would then use it like this:
import tensorflow as tf
from tensorflow.keras import Input
batch_size = 8
num_classes = 10
inp = Input(shape=(1024, 256))
layer = Dense2D(num_classes, activation='softmax')
out = layer(inp)
print(out.shape)
# (None, 1024, 10)
print(layer.count_params())
# 2631680
1: As today points out in the comments, you can actually use a LocallyConnected1D layer to do the same that I tried to do with my Dense2D layer. It is as simple as this:
import tensorflow as tf
from tensorflow.keras import Input
from tensorflow.keras.layers import LocallyConnected1D
batch_size = 8
num_classes = 10
inp = Input(shape=(1024, 256))
layer = LocallyConnected1D(num_classes, 1, activation='softmax')
out = layer(inp)
print(out.shape)
# (None, 1024, 10)
print(layer.count_params())
# 2631680

Custom Attention Layer using in Keras

I want to create a custom attention layer that for input at any time this layer returns the weighted mean of inputs at all time inputs.
For Example, I want that input tensor with shape [32,100,2048] goes to layer and I get the tensor with the shape [32,100,2048]. I wrote the Layer as follow:
import tensorflow as tf
from keras.layers import Layer, Dense
#or
from tensorflow.keras.layers import Layer, Dense
class Attention(Layer):
def __init__(self, units_att):
self.units_att = units_att
self.W = Dense(units_att)
self.V = Dense(1)
super().__init__()
def __call__(self, values):
t = tf.constant(0, dtype= tf.int32)
time_steps = tf.shape(values)[1]
initial_outputs = tf.TensorArray(dtype=tf.float32, size=time_steps)
initial_att = tf.TensorArray(dtype=tf.float32, size=time_steps)
def should_continue(t, *args):
return t < time_steps
def iteration(t, values, outputs, atts):
score = self.V(tf.nn.tanh(self.W(values)))
# attention_weights shape == (batch_size, time_step, 1)
attention_weights = tf.nn.softmax(score, axis=1)
# context_vector shape after sum == (batch_size, hidden_size)
context_vector = attention_weights * values
context_vector = tf.reduce_sum(context_vector, axis=1)
outputs = outputs.write(t, context_vector)
atts = atts.write(t, attention_weights)
return t + 1, values, outputs, atts
t, values, outputs, atts = tf.while_loop(should_continue, iteration,
[t, values, initial_outputs, initial_att])
outputs = outputs.stack()
outputs = tf.transpose(outputs, [1,0,2])
atts = atts.stack()
atts = tf.squeeze(atts, -1)
atts = tf.transpose(atts, [1,0,2])
return t, values, outputs, atts
For input= tf.constant(2, shape= [32, 100, 2048], dtype= tf.float32) I get the
output with shape = [32,100,2048] in tf2 and [32,None, 2048] in tf1.
For Input input= Input(shape= (None, 2048)) I get the output with shape = [None, None, 2048] in tf1 and I get error
TypeError: 'Tensor' object cannot be interpreted as an integer
in tf2.
Finally, in both cases, I can't use this layer in my model because my model input is Input(shape= (None, 2048)) and I get the error
AttributeError: 'NoneType' object has no attribute '_inbound_nodes'
in tf1 and in tf2 I get the same error as said in above, I create my model with Keras functional method.
From the code you have shared, looks like you want to implement Bahdanau's attention layer in your code. You want to attend to all the 'values' (prev layer output - all its hidden states) and your 'query' would be the last hidden state of the decoder. Your code should actually be very simple and should look like:
class Bahdanau(tf.keras.layers.Layer):
def __init__(self, n):
super(Bahdanau, self).__init__()
self.w = tf.keras.layers.Dense(n)
self.u = tf.keras.layers.Dense(n)
self.v = tf.keras.layers.Dense(1)
def call(self, query, values):
query = tf.expand_dims(query, 1)
e = self.v(tf.nn.tanh(self.w(query) + self.u(values)))
a = tf.nn.softmax(e, axis=1)
c = a * values
c = tf.reduce_sum(c, axis=1)
return a,c
##Say we want 10 units in the single layer MLP determining w,u
attentionlayer = Bahdanau(10)
##Call with i/p: decoderstate # t-1 and all encoder hidden states
a, c = attentionlayer(stminus1, hj)
We are not specifying the tensor shape anywhere in the code. This code will return you a context tensor of same size as 'stminus1' which is the 'query'. It does this after attending to all the 'values' (all output states of decoder) using Bahdanau's attention mechanism.
So assuming your batch size is 32, timesteps=100 and embedding dimension=2048, the shape of stminus1 should be (32,2048) and the shape of the hj should be (32,100,2048). The shape of the output context would be (32,2048). We also returned the 100 attention weights just in case you want to route them to a nice display.
This is the simplest version of 'Attention'. If you have any other intent, please let me know and I will reformat my answer. For more specific details, please refer https://towardsdatascience.com/create-your-own-custom-attention-layer-understand-all-flavours-2201b5e8be9e

Gradients are None for Custom Convolution Layer

I have implemented the Basic MNIST model with Custom convolution layer as shown below. The problem is that the Gradients are always 'None' for the Custom Layer and so the learning does not happens during back propagation, as the Grad has None values.
I have debugged the outputs of the layers during forward pass and they are OK.
Here is the sample code, for simplicity I have passed image of 'Ones' and have just returned the matrix from the custom layer.
I have tried my best but could make it work any help is very much appreciated in advance
following code is executable and raises the
warning
:tensorflow:Gradients do not exist for variables ['cnn/custom_conv2d/kernel:0', 'cnn/custom_conv2d/bias:0', 'cnn/custom_conv2d_1/kernel:0', 'cnn/custom_conv2d_1/bias:0', 'cnn/custom_conv2d_2/kernel:0', 'cnn/custom_conv2d_2/bias:0'] when minimizing the loss.
import numpy as np
import tensorflow as tf
from grpc.beta import interfaces
class CustomConv2D(tf.keras.layers.Conv2D):
def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
data_format=None,
dilation_rate=(1, 1),
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='glorot_uniform',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
__name__ = 'CustomConv2D',
**kwargs
):
super(CustomConv2D, self).__init__(
filters=filters,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
dilation_rate=dilation_rate,
activation=activation,
use_bias=use_bias,
kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
kernel_constraint=kernel_constraint,
bias_constraint=bias_constraint,
**kwargs )
def call(self, input):
(unrolled_mat, filters, shape) = self.prepare(input)
#unrolled_mat=unrolled inputs
#filters=unrolled kernels of the lAYER
#convolution through unrolling
conv_result = tf.tensordot(unrolled_mat, filters, axes=1)
result=tf.convert_to_tensor(tf.reshape(conv_result, shape))
return result
def prepare(self, matrix):
batches,rows,cols,channels=matrix.shape
kernel_size = self.kernel_size[0]
unrolled_matrices=None
# start = timer()
for batch in range(batches):
unrolled_maps=None
for chanel in range(channels):
unrolled_map = self.unroll(batch, cols, kernel_size, matrix, rows,chanel)
if unrolled_maps is None:
unrolled_maps = unrolled_map
else:
unrolled_maps=np.append(unrolled_maps,unrolled_map,axis=1)
unrolled_maps = np.reshape(unrolled_maps,(-1,unrolled_maps.shape[0],unrolled_maps.shape[1]))
if unrolled_matrices is None:
unrolled_matrices = unrolled_maps
else:
unrolled_matrices = np.concatenate((unrolled_matrices, unrolled_maps))
kernels=self.get_weights()
kernels=np.reshape(kernels[0],(unrolled_matrices[0].shape[1],-1))
shp=(batches,rows-(kernel_size-1),cols-(kernel_size-1),self.filters)
matrix=unrolled_matrices
return (matrix, kernels, shp)
def unroll(self, batch, cols, kernel_size, matrix, rows, chanel):
# a=np.zeros((shape))
unrolled_feature_map = None
for x in range(0, rows - (kernel_size - 1)):
for y in range(0, (cols - (kernel_size - 1))):
temp_row = None # flattened kernal at single position
for k in range(kernel_size):
for l in range(kernel_size):
if temp_row is None:
temp_row = matrix[batch, x + k, y + l, chanel]
# print(matrix[batch, x + k, y + l])
else:
temp_row = np.append(temp_row, matrix[batch, x + k, y + l, chanel])
# print(matrix[batch, x + k, y + l])
if unrolled_feature_map is None:
unrolled_feature_map = np.reshape(temp_row,
(-1, kernel_size * kernel_size)) # first row of unrolled matrix added
else:
unrolled_feature_map = np.concatenate((unrolled_feature_map, np.reshape(temp_row,
(-1, kernel_size * kernel_size)))) # concatinate subsequent row to un_mat
unrolled_feature_map = np.reshape(unrolled_feature_map,( unrolled_feature_map.shape[0], unrolled_feature_map.shape[1]))
# print(unrolled_feature_map.shape)
matrix=unrolled_feature_map
return matrix
class CNN(tf.keras.Model):
def __init__(self):
super(CNN, self).__init__()
self.learning_rate = 0.001
self.momentum = 0.9
self.optimizer = tf.keras.optimizers.Adam(self.learning_rate, self.momentum)
self.conv1 = CustomConv2D(filters = 6, kernel_size= 3, activation = 'relu') ## valid means no padding
self.pool1 = tf.keras.layers.MaxPool2D(pool_size=2) # default stride??-
self.conv2 = CustomConv2D(filters = 16, kernel_size = 3, activation = 'relu')
self.pool2 = tf.keras.layers.MaxPool2D(pool_size = 2)
self.conv3 = CustomConv2D(filters=120, kernel_size=3, activation='relu')
self.flatten = tf.keras.layers.Flatten()
self.fc1 = tf.keras.layers.Dense(units=82,kernel_initializer='glorot_uniform')
self.fc2 = tf.keras.layers.Dense(units=10, activation = 'softmax',kernel_initializer='glorot_uniform')
def call(self, x):
x = self.conv1(x) # shap(32,26,26,6) all (6s 3s 6s 3s)
x = self.pool1(x) # shap(32,13,13,6) all (6s)
x = self.conv2(x) # shap(32,11,11,16) all(324s)
x = self.pool2(x) # shap(32,5,5,16)
x = self.conv3(x) # shap(32,3,3,120)all(46656)
x = self.flatten(x) # shap(32,1080)
x = self.fc1(x) # shap(32,82)
x = self.fc2(x) # shap(32,10)
return x
def feedForward(self, image, label):
accuracy_object = tf.metrics.Accuracy()
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
with tf.GradientTape() as tape:
feedForwardCompuation = self(image, training=True)
self.loss_value = loss_object(label, feedForwardCompuation)
grads = tape.gradient(self.loss_value, self.variables)
self.optimizer.apply_gradients(zip(grads, self.variables))
accuracy = accuracy_object(tf.argmax(feedForwardCompuation, axis=1, output_type=tf.int32), label)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train=x_train.astype('float32')
y_train = y_train.astype('float32')
image=x_train[0].reshape((1,28,28,1))
label=y_train[0]
cnn=CNN()
cnn.feedForward(image,label)
UPDATE: I am not using the builtin TF conv fucntion rather I am implementing my own custom convolution operation via Matrix unrolling method(unrolled map*unrolled filters). But the Tap.gradient returns "None" for the custom layers however when I use the builtin conv2d function of TF then it works fine!
I have Added the actual code of the operation
Snapshot of grads while debugging
Problem is that the Convolution Operation is not happening in the Class, CustomConv2D. Neither the call Method, nor the customConv Method is performing Convolution Operation, but it is just returning the Input, as it is.
Replacing the line, return self.customConv(matrix) in the call method of CustomConv2D Class with return super(tf.keras.layers.Conv2D, self).call(matrix) will perform the actual Convolutional Operation.
One more change is to invoke the call method of CNN class by including the line, _ = cnn(X_reshaped) before the line, cnn.feedForward(image,label)
By doing the above 2 changes, Gradients will be added.

Converting keras functional model to keras class in tensorflow 2

I am trying to convert a Keras functional model into class derived from tensorflow.keras.models.Model and I'm facing 2 issues.
1. I need to multiply 2 layers using tensorflow.keras.layers.multiply, but it returns a ValueError: A merge layer should be called on a list of inputs.
2. If I remove this layern thus working with a classical CNN, it returns a tensorflow.python.eager.core._SymbolicException:Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'patch:0' shape=(None, 64, 64, 3) dtype=float32>].
I would appreciate some guidance to convert my code. I'm using Python 3.7, TensorFlow 2.0rc2 and Keras 2.3.0. The class I have defined is the following:
class TestCNN(Model):
"""
conv1 > conv2 > fc1 > fc2 > alpha * fc2 > Sigmoid > output
"""
def __init__(self, input_dimension, n_category,**kwargs):
"""
Instanciator
:param input_dimension: tuple of int, theoretically (patch_size x patch_size x channels)
:param n_category: int, the number of categories to classify,
:param weight_decay: float, weight decay parameter for all the kernel regularizers
:return: the Keras model
"""
super(TestCNN, self).__init__(name='testcnn', **kwargs)
self.input_dimension = input_dimension
self.n_category = n_category
self.conv1 = Conv2D(36, activation='relu', name='conv1/relu')
self.conv1_maxpooling = MaxPooling2D((2, 2), name='conv1/maxpooling')
self.conv2 = Conv2D(48, activation='relu', name='conv2/relu')
self.conv2_maxpooling = MaxPooling2D((2, 2), name='conv2/maxpooling')
self.flatten1 = Flatten(name='flatten1')
self.fc1 = Dense(512, activation='relu', name='fc1/relu')
self.fc2 = Dense(512, activation='relu', name='fc2/relu')
self.alpha = TestLayer(layer_dim=128, name='alpha')
self.output1 = TestSigmoid(output_dimension=n_category, name='output_layer')
#tensorflow.function
def call(self, x):
x = self.conv1(x)
x = self.conv1_maxpooling(x)
x = self.conv2(x)
x = self.conv2_maxpooling(x)
x = self.flatten1(x)
x = self.fc1(x)
x = self.fc2(x)
alpha_times_fc2 = multiply([alpha_output, fc2_output], name='alpha_times_fc2')
return self.output1(alpha_times_fc2)
def build(self, **kwargs):
inputs = Input(shape=self.input_dimension, dtype='float32', name='patch')
outputs = self.call(inputs)
super(TestCNN, self).__init__(name="TestCNN", inputs=inputs, outputs=outputs, **kwargs)
Then, in my main loop, I'm creating the instance as following:
testcnn = TestCNN(input_dimension=input_dimension, n_category=training_set.category_count)
optimizer = tensorflow.keras.optimizers.Adam(
lr=parameter['training']['adam']['learning_rate'],
beta_1=parameter['training']['adam']['beta1'],
beta_2=parameter['training']['adam']['beta2'])
metrics_list = [tensorflow.keras.metrics.TruePositives]
loss_function = tensorflow.keras.losses.categorical_crossentropy
loss_metrics = tensorflow.keras.metrics.Mean()
testcnn.build()
testcnn.summary()
This code is raising the tensorflow.python.eager.core._SymbolicException. If I comment out some lines and return directly the results of the fc2 layer, I've got the ValueError.
I have commenter the build() function in my model and call it in my main script as following:
testcnn.build(input_dimension)
testcnn.compile(optimizer=adam_optimizer, loss=loss_function, metrics=metrics_list)
testcnn.summary()
Input dimension is a list formatted as following:
input_dimension = (batch_size, image_size, image_size, channels)