I have made image patches from an image classifier. When I print it's shape it is (81, 256) which means 81 patches each with size of 256. but it lost the information of the image like these 81 patches belong to a specific image. I want to get it's shape like (1, 81, 256) so if I have batch of 20 images then it will show (20, 81, 256).
class Patches(layers.Layer):
def __init__(self, patch_size):
super(Patches, self).__init__()
self.patch_size = patch_size
def call(self, images):
batch_size = tf.shape(images)[0]
patches = tf.image.extract_patches(
images=images,
sizes=[1, self.patch_size, self.patch_size, 1],
strides=[1, self.patch_size, self.patch_size, 1],
rates=[1, 1, 1, 1],
padding="VALID",
)
patch_dims = patches.shape[-1]
patches = tf.reshape(patches, [batch_size, -1, patch_dims])
return patches
Model code
xception = keras.applications.Xception(
include_top=False, weights="imagenet", pooling="avg"
)
for layer in xception.layers:
layer.trainable = trainable
inputs = layers.Input(shape=(300, 300, 3), name="image_input")
patch_size = 72
print("inputs shape is ", inputs.shape)
xception_input = tf.keras.applications.xception.preprocess_input(inputs)
print("xception shape is", xception_input.shape)
patches = Patches(patch_size)(xception_input)
print("patches shape is", patches.shape)
patches = tf.reshape(patches, [-1, 32, 32, 3])
print("patches shape is", patches.shape)
embeddings = xception(patches)
output = embeddings(
embeddings, projection_layers, dims, dropout_rate
)
print("output shape is ", output.shape)
return keras.Model(inputs, output)
Ouput
inputs shape is (None, 300, 300, 3)
xception shape is (None, 300, 300, 3)
patches shape is (None, None, 15552)
patches shape is (None, 32, 32, 3)
output shape is (81, 256)
Below code converts each patch to size of 256 lenght
def embeddings(
embeddings, projection_layers, dims, dropout_rate
):
projected_embeddings = layers.Dense(units=projection_dims)(embeddings)
for _ in range(num_projection_layers):
x = tf.nn.gelu(projected_embeddings)
x = layers.Dense(projection_dims)(x)
x = layers.Dropout(dropout_rate)(x)
x = layers.Add()([projected_embeddings, x])
projected_embeddings = layers.LayerNormalization()(x)
return projected_embeddings
If it's just a matter of adding a dimension to your numpy array, you can use expand_dims like this:
import numpy as np
array = np.zeros((81, 256)) # example array of same shape like yours
print("Old shape: {}".format(array.shape))
new_array = np.expand_dims(array, axis=0)
print("New shape: {}".format(new_array.shape))
The output:
Old shape: (81, 256)
New shape: (1, 81, 256)
Related
I am training a deep learning model on stacks of images with variable dimensions. (Shape = [Batch, None, 256, 256, 1]), where None can be variable.
I use tf.RaggedTensor.merge_dimsions(0,1) to convert the ragged Tensor to a shape of [None, 256, 256, 1] to run into a pretrained keras CNN model.
However, using the KerasLayer API results in the following error: TypeError: the object of type 'RaggedTensor' has no len()
When I apply .merge_dimsions outside of the KerasLayer and pass the tensors to the same pretrained model I do not get this error.
import tensorflow as tf
# Synthetic Data Pipeline
def synthetic_gen():
varShape = tf.random.uniform((), minval=1, maxval=12, dtype=tf.int32)
image = tf.random.normal((varShape, 256, 256, 1))
image = tf.RaggedTensor.from_tensor(image, ragged_rank=1)
yield image
ds = tf.data.Dataset.from_generator(synthetic_gen, output_signature=(tf.RaggedTensorSpec(shape=(None, 256, 256, 1), dtype=tf.float32, ragged_rank=1)))
ds = ds.repeat().batch(8)
print(next(iter(ds)).shape)
# Build Model
inputs = tf.keras.Input(
type_spec=tf.RaggedTensorSpec(
shape=(8, None, 256, 256, 1),
dtype=tf.float32,
ragged_rank=1))
ResNet50 = tf.keras.applications.ResNet50(
include_top=True,
input_shape=(256, 256, 1),
weights=None)
def merge(x):
x = x.merge_dims(0, 1)
return x
x = tf.keras.layers.Lambda(merge)(inputs)
merged_inputs = x
# x = ResNet50(x) # Uncommenting this will result in `model` producing an error when run for inference.
model = tf.keras.Model(inputs, x)
# Run inference
data = next(iter(ds))
model(data).shape # Will be an error if ResNet50 is used
Here is a colab notebook that demonstrates the problem. https://colab.research.google.com/drive/1kN78mf4_oNqxWOluV054NlqmakC5msli?usp=sharing
Not sure if the following answer or workaround is stable for complex network design. But here are some pointers. The reason you got
Ragged Tensors have no len()
is because of ResNet models, as it expects tensor and not ragged_tensor. I'm not sure however if the ResNet(weights=None) is able to take ragged_tensor or not directly. So, if we can convert the ragged data right before the ResNet gets fed, maybe it won't complain. Below is the full working code according to this. But please note, there is probably some efficient approach maybe possible.
Data
import tensorflow as tf
# Synthetic Data Pipeline
def synthetic_gen():
varShape = tf.random.uniform((), minval=1, maxval=12, dtype=tf.int32)
image = tf.random.normal((varShape, 256, 256, 1))
image = tf.RaggedTensor.from_tensor(image, ragged_rank=1)
yield image
ds = tf.data.Dataset.from_generator(synthetic_gen,
output_signature=(tf.RaggedTensorSpec(
shape=(None, 256, 256, 1),
dtype=tf.float32, ragged_rank=1
)
)
)
ds = ds.repeat().batch(8)
Basic Model
# Build Model
inputs = tf.keras.Input(
type_spec=tf.RaggedTensorSpec(
shape=(8, None, 256, 256, 1),
dtype=tf.float32,
ragged_rank=1))
ResNet50 = tf.keras.applications.ResNet50(
include_top=True,
input_shape=(256, 256, 1),
weights=None)
def merge(x):
x = x.merge_dims(0, 1)
return x
Ragged Model
Here we convert ragged_tensor to tensor before passing the data to ResNet.
class RagModel(tf.keras.Model):
def __init__(self):
super(RagModel, self).__init__()
# base models
self.a = tf.keras.layers.Lambda(merge)
# convert: tensor = ragged_tensor.to_tensor()
self.b = tf.keras.layers.Lambda(lambda x: x.to_tensor())
self.c = ResNet50
def call(self, inputs, training=None, plot=False, **kwargs):
x = self.a(inputs)
x = self.b(x) if not plot else x
x = self.c(x)
return x
# a helper function to plot
def build_graph(self):
x = tf.keras.Input(type_spec=tf.RaggedTensorSpec(
shape=(8, None, 256, 256, 1),
dtype=tf.float32, ragged_rank=1)
)
return tf.keras.Model(inputs=[x],
outputs=self.call(x, plot=True))
x_model = RagModel()
Run
data = next(iter(ds)); print(data.shape)
x_model(data).shape
(8, None, 256, 256, 1)
TensorShape([39, 1000])
Plot
tf.keras.utils.plot_model(x_model.build_graph(),
show_shapes=True, show_layer_names=True)
x_model.build_graph().summary()
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_4 (InputLayer) [(8, None, 256, 256, 1)] 0
_________________________________________________________________
lambda_2 (Lambda) (None, 256, 256, 1) 0
_________________________________________________________________
resnet50 (Functional) (None, 1000) 25630440
=================================================================
Total params: 25,630,440
Trainable params: 25,577,320
Non-trainable params: 53,120
_________________________________________________________________
I would like to apply in Keras MobileNetV2 on images of size 39 x 39 to classify 3 classes. My images represent heat maps (e.g. what keys have been pressed on the keyboard). I think MobileNet was designed to work on images of size 224 x 224. I will not use transfer learning but train the model from scratch.
To make MobileNet work on my images, I would like to replace the first three stride 2 convolutions with stride 1. I have the following code:
from tensorflow.keras.applications import MobileNetV2
base_model = MobileNetV2(weights=None, include_top=False,
input_shape=[39,39,3])
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.5)(x)
output_tensor = Dense(3, activation='softmax')(x)
cnn_model = Model(inputs=base_model.input, outputs=output_tensor)
opt = Adam(lr=learning_rate)
cnn_model.compile(loss='categorical_crossentropy',
optimizer=opt, metrics=['accuracy', tf.keras.metrics.AUC()])
How can I replace the first three stride 2 convolutions with stride 1 without building MobileNet myself?
Here is one workaround for your need but I think probably it's possible to have a more general approach. However, in the MobileNetV2, there is only one conv layer with strides 2. If you follow the source code, here
x = layers.Conv2D(
first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name='Conv1')(img_input)
x = layers.BatchNormalization(
axis=channel_axis, epsilon=1e-3, momentum=0.999, name='bn_Conv1')(
x)
x = layers.ReLU(6., name='Conv1_relu')(x)
And the rest of the blocks are defined as follows
x = _inverted_res_block(
x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0)
x = _inverted_res_block(
x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1)
x = _inverted_res_block(
x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2)
So, here I will deal with the first conv with stride=(2, 2). The idea is simple, we will add a new layer in the right place of the built-in model and then remove the desired layer.
def _make_divisible(v, divisor, min_value=None):
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
alpha = 1.0
first_block_filters = _make_divisible(32 * alpha, 8)
inputLayer = tf.keras.Input(shape=(39, 39, 3), name="inputLayer")
inputcOonv = tf.keras.layers.Conv2D(
first_block_filters,
kernel_size=3,
strides=(1, 1),
padding='same',
use_bias=False,
name='Conv1_'
)(inputLayer)
The above _make_divisible function simply derived from the source code. Anyway, now we impute this layer to the MobileNetV2 right before the first conv layer, as follows:
base_model = tf.keras.applications.MobileNetV2(weights=None,
include_top=False,
input_tensor = inputcOonv)
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.5)(x)
output_tensor = Dense(3, activation='softmax')(x)
cnn_model = Model(inputs=base_model.input, outputs=output_tensor)
Now, if we observe
for i, l in enumerate(cnn_model.layers):
print(l.name, l.output_shape)
if i == 8: break
inputLayer [(None, 39, 39, 3)]
Conv1_ (None, 39, 39, 32)
Conv1 (None, 20, 20, 32)
bn_Conv1 (None, 20, 20, 32)
Conv1_relu (None, 20, 20, 32)
expanded_conv_depthwise (None, 20, 20, 32)
expanded_conv_depthwise_BN (None, 20, 20, 32)
expanded_conv_depthwise_relu (None, 20, 20, 32)
expanded_conv_project (None, 20, 20, 16)
Layer name Conv1_ and Conv1 are the new layer (with strides = 1) and old layer (with strides = 2) respectively. And as we need, now we remove layer Conv1 with strides = 2 as follows:
cnn_model._layers.pop(2) # remove Conv1
for i, l in enumerate(cnn_model.layers):
print(l.name, l.output_shape)
if i == 8: break
inputLayer [(None, 39, 39, 3)]
Conv1_ (None, 39, 39, 32)
bn_Conv1 (None, 20, 20, 32)
Conv1_relu (None, 20, 20, 32)
expanded_conv_depthwise (None, 20, 20, 32)
expanded_conv_depthwise_BN (None, 20, 20, 32)
expanded_conv_depthwise_relu (None, 20, 20, 32)
expanded_conv_project (None, 20, 20, 16)
expanded_conv_project_BN (None, 20, 20, 16)
Now, you have cnn_model model with strides = 1 on its first conv layer. However, in case you're wondering about this approach and possible issue, please see my other answer related to this one. Remove first N layers from a Keras Model?
System information
OS Platform and Distribution :CentOS Linux release 7.7.1908
-TensorFlow version:2.3.0
I try to convert the tensorflow offical image caption model to TFLite model
I try to convert the tf.keras.Model 's encoder and decoder model as following:
import tensorflow as tf
embedding_dim = 256
units = 512
top_k = 5000
vocab_size = top_k + 1
features_shape = 2048
attention_features_shape = 64
class BahdanauAttention(tf.keras.Model):
def __init__(self, utils):
super(BahdanauAttention, self).__init__()
self.W1 = tf.keras.layers.Dense(utils)
self.W2 = tf.keras.layers.Dense(utils)
self.V = tf.keras.layers.Dense(1)
def call(self, features, hidden):
# features(CNN_encoder output) shape == (batch_size, 64, embedding_dim)
# hidden shape == (batch_size, hidden_size)
# hidden_with_time_axis shape == (batch_size, 1, hidden_size)
hidden_with_time_axis_shape = tf.expand_dims(hidden, 1)
# score shape == (batch_size, 64, hidden_size)
score = tf.nn.tanh(self.W1(features) + self.W2(hidden_with_time_axis_shape))
# attention_weights shape == (batch_size, 64, 1)
# you get 1 at the last axis because you are applying score to self.V
attention_weights = tf.nn.softmax(self.V(score), axis=1)
# context_vector shape after sum == (batch_size, hidden_size)
context_vector = attention_weights * features
context_vector = tf.reduce_sum(context_vector, axis=1)
return context_vector, attention_weights
class CNN_Encoder(tf.keras.Model):
#由于您已经提取了特征并使用pickle进行了转储
#该编码器通过完全连接的层传递这些特征
def __init__(self, embedding):
super(CNN_Encoder, self).__init__()
# shape after fc == (batch_size, 64, embedding_dim)
self.fc = tf.keras.layers.Dense(embedding_dim)
# #tf.function(input_signature=[tf.TensorSpec(shape=(1, 64, features_shape),dtype=tf.float32)])
#tf.function
def call(self, x):
x = self.fc(x)
x = tf.nn.relu(x)
return x
class RNN_Decoder(tf.keras.Model):
def __init__(self, embedding_dim, units, vocab_size):
super(RNN_Decoder, self).__init__()
self.units = units
self.embedding = tf.keras.layers.Embedding(vocab_size, embedding_dim)
self.gru = tf.keras.layers.GRU(self.units,
return_sequences=True,
return_state=True,
recurrent_initializer='glorot_uniform',
unroll = True)
self.fc1 = tf.keras.layers.Dense(self.units)
self.fc2 = tf.keras.layers.Dense(vocab_size)
self.attention = BahdanauAttention(self.units)
#tf.function(input_signature=[tf.TensorSpec(shape=[1, 1], dtype=tf.int32, name='x'),
tf.TensorSpec(shape=[1, 64, 256], dtype=tf.float32, name='feature'),
tf.TensorSpec(shape=[1, 512], dtype=tf.float32, name='hidden')])
#tf.function
def call(self, x , features, hidden):
#将注意力定义为一个单独的模型
context_vector, attention_weights = self.attention(features, hidden)
#x shape after passing through embedding == (batch_size, 1, embedding_dim)
x = self.embedding(x)
#x shape after concatenation == (batch_size, 1, embedding_dim + hidden_size)
x = tf.concat([tf.expand_dims(context_vector, 1), x], axis=-1)
#将concated后的的向量传递给GRU
output, state = self.gru(x)
#shape == (batch_size, max_length, hidden_size)
x = self.fc1(output)
#x shape == (batch_size, max_length, hidden_size)
x = tf.reshape(x, (-1, x.shape[2]))
# output shape == (batch_size * max_length, vocab)
x = self.fc2(x)
return x, state, attention_weights
def reset_states(self, batch_size):
return tf.zeros((batch_size, self.units))
encoder = CNN_Encoder(embedding_dim)
decoder = RNN_Decoder(embedding_dim, units, vocab_size)`
encoder._set_inputs(tf.TensorSpec(shape=(1, 64, features_shape),dtype=tf.float32))
decoder._set_inputs([tf.TensorSpec(shape=[1, 1], dtype=tf.int32, name='x'),
tf.TensorSpec(shape=[1, 64, 256], dtype=tf.float32, name='feature'),
tf.TensorSpec(shape=[1, 512], dtype=tf.float32, name='hidden')])
encoder_converter = tf.lite.TFLiteConverter.from_keras_model(encoder)
decoder_converter = tf.lite.TFLiteConverter.from_keras_model(decoder)
encoder_model = encoder_converter.convert()
decoder_model = decoder_converter.convert()
open("encoder_model.tflite", "wb").write(encoder_model)
open("decoder_model.tflite", "wb").write(decoder_model)
The error messge is
ValueError: Structure of Python function inputs does not match input_signature:
inputs: (
[<tf.Tensor 'x:0' shape=(1, 1) dtype=int32>, <tf.Tensor 'feature:0' shape=(1, 64, 256) dtype=float32>, <tf.Tensor 'hidden:0' shape=(1, 512) dtype=float32>])
input_signature: (
TensorSpec(shape=(1, 1), dtype=tf.int32, name='x'),
TensorSpec(shape=(1, 64, 256), dtype=tf.float32, name='feature'),
TensorSpec(shape=(1, 512), dtype=tf.float32, name='hidden'))
I think the function input is the same as the input signature.How can I fix the problem?
i also had the same issue. found a simple solution to this. the call method of tf.keras.Model class accepts only single input, so you need to pack all your inputs inside a list/tuple
https://github.com/tensorflow/tensorflow/issues/32488#issuecomment-560248754
My input shape is (150,10,1) and my output has the same shape (150,10,1). My problem is multi-classification (3 classes). After using np_utils.to_categorical(Ytrain) the output shape will be (150,10,3) which is perfect. However during the process of modelling with GlobalAvgPool1D(), it gives the error :
"A target array with shape (150, 10, 3) was passed for an output of shape (None, 3) while using as loss categorical_crossentropy. This loss expects targets to have the same shape as the output".
How should I fix it?
My codes:
nput_size = (150, 10, 1)
Xtrain = np.random.randint(0, 100, size=(150, 10, 1))
Ytrain = np.random.choice([0,1, 2], size=(150, 10,1))
Ytrain = np_utils.to_categorical(Ytrain)
input_shape = (10, 1)
input_layer = tf.keras.layers.Input(input_shape)
conv_x = tf.keras.layers.Conv1D(filters=32, kernel_size=10, strides = 1, padding='same')(input_layer)
conv_x = tf.keras.layers.BatchNormalization()(conv_x)
conv_x = tf.keras.layers.Activation('relu')(conv_x)
g_pool = tf.keras.layers.GlobalAvgPool1D()(conv_x)
output_layer = tf.keras.layers.Dense(3, activation='softmax')(g_pool)
model = tf.keras.models.Model(inputs= input_layer, outputs = output_layer)
model.summary()
model.compile(loss='categorical_crossentropy', optimizer= tf.keras.optimizers.Adam(),
metrics='accuracy'])
hist = model.fit(Xtrain, Ytrain, batch_size= 5, epochs= 10, verbose= 0)
When I ran your code in Tensorflow Version 2.2.0 in Google colab, I got the following error - ValueError: Shapes (5, 10, 3) and (5, 3) are incompatible.
You are getting this error because, the labels Ytrain data is having the shape of (150, 10, 3) instead of (150, 3).
As your labels are having shape of (None,3), your input also should be same .i.e. (Number of records, 3). I was able to run your code successfully after modifying,
Ytrain = np.random.choice([0,1, 2], size=(150, 10,1))
to
Ytrain = np.random.choice([0,1, 2], size=(150, 1))
np_utils.to_categorical adds the 3 columns for labels thus making the shape of (150,3) which our model expects.
Fixed Code -
import tensorflow as tf
print(tf.__version__)
import numpy as np
from tensorflow.keras import utils as np_utils
Xtrain = np.random.randint(0, 100, size=(150, 10, 1))
Ytrain = np.random.choice([0,1, 2], size=(150, 1))
Ytrain = np_utils.to_categorical(Ytrain)
print(Ytrain.shape)
input_shape = (10, 1)
input_layer = tf.keras.layers.Input(input_shape)
conv_x = tf.keras.layers.Conv1D(filters=32, kernel_size=10, strides = 1, padding='same')(input_layer)
conv_x = tf.keras.layers.BatchNormalization()(conv_x)
conv_x = tf.keras.layers.Activation('relu')(conv_x)
g_pool = tf.keras.layers.GlobalAvgPool1D()(conv_x)
output_layer = tf.keras.layers.Dense(3, activation='softmax')(g_pool)
model = tf.keras.models.Model(inputs= input_layer, outputs = output_layer)
model.summary()
model.compile(loss='categorical_crossentropy', optimizer= tf.keras.optimizers.Adam(),
metrics=['accuracy'])
hist = model.fit(Xtrain, Ytrain, batch_size= 5, epochs= 10, verbose= 0)
print("Ran Successfully")
Output -
2.2.0
(150, 3)
Model: "model_13"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_21 (InputLayer) [(None, 10, 1)] 0
_________________________________________________________________
conv1d_9 (Conv1D) (None, 10, 32) 352
_________________________________________________________________
batch_normalization_15 (Batc (None, 10, 32) 128
_________________________________________________________________
activation_9 (Activation) (None, 10, 32) 0
_________________________________________________________________
global_average_pooling1d_9 ( (None, 32) 0
_________________________________________________________________
dense_14 (Dense) (None, 3) 99
=================================================================
Total params: 579
Trainable params: 515
Non-trainable params: 64
_________________________________________________________________
Ran Successfully
Hope this answers your question. Happy Learning.
I am looking at the examples/image_orc.py example in Keras, when I run it I see something like
_______________
max2 (MaxPooling2D) (None, 32, 16, 16) 0 conv2[0][0]
____________________________________________________________________________________________________
reshape (Reshape) (None, 32, 256) 0 max2[0][0]
____________________________________________________________________________________________________
dense1 (Dense) (None, 32, 32) 8224 reshape[0][0]
_____________________________________________________________________________________
The Dense layer outputs a tensor 32x32. I am trying to replicate this in pur TensorFlow where tf.matmul would be used, but how can I output 32x32 using matmul?
Addition:
I am not trying to replicate the Keras example exactly,
w = 128; h = 64
# junk image, only one
dataset = np.zeros((1,w,h,1))
import tensorflow as tf
pool_size = 1
num_filters = 16
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
inputs = tf.placeholder(tf.float32, [None, w, h, 1])
W_conv1 = weight_variable([3, 3, 1, num_filters])
b_conv1 = bias_variable([num_filters])
h_conv1 = tf.nn.relu(conv2d(inputs, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([3, 3, num_filters, num_filters])
b_conv2 = bias_variable([num_filters])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
h_pool2_flat = tf.reshape(h_pool2, [-1, 32, 256])
W_fc1 = weight_variable([256, 32])
b_fc1 = bias_variable([32])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
print inputs.shape
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(h_pool2_flat, feed_dict={inputs: dataset})
print 'output',output.shape
And I get
ValueError: Shape must be rank 2 but is rank 3 for 'MatMul_5' (op: 'MatMul') with input shapes: [?,32,256], [256,32].
A smaller example
import numpy as np
import tensorflow as tf
dataset = np.zeros((3,2,4))
inputs = tf.placeholder(tf.float32, [None, 2, 4])
print inputs
W = tf.zeros((4,5))
print W
W2 = tf.matmul(inputs, W)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(W2, feed_dict={inputs: dataset})
print 'output',output.shape
This also gives similar error
ValueError: Shape must be rank 2 but is rank 3 for 'MatMul_12' (op: 'MatMul') with input shapes: [?,2,4], [4,5].
Any ideas?
Thanks,
That 32 is there because it was in the previous layer. It keeps unchanged.
The tf.matmul multiplies considering the two last dimensions, as stated here. (See the examples taking more than two dimensions)
I see you've got a Dense(32) there, with input size = 256.
This means that the weights matrix is (256,32). In keras, the multiplication as seen here is inputs x kernel.
So, if you have the input tensor shaped as (?, any, 256), and the weights matrix shaped as (256,32), all you need is:
output = tf.matmul(input,weights)
This will output a shape (?, any, 32) - any is there untouched because it just was there before.
You may also want to sum the biases, which will follow the same principle. You need a bias vector of shape (32,).