Input tensors to a Model must be Keras tensors. Found:
Tensor("my_layer/Identity:0", shape=(?, 10, 1152, 16), dtype=float32)
(missing Keras metadata).
Hi, I get this error when trying to take one layer's intermediate variable to use it as input to a parallel network. Such that one layer's intermediate variable will be input to the other network.
def call(self, inputs, training=None):
inputs_expand = K.expand_dims(inputs, 1)
tensor_b = K.tile(inputs_expand, [1, 16, 1, 1])
tensor_a = K.map_fn(lambda x: K.batch_dot(x, self.Weights, [2, 3]), elems=tensor_b)
# I need this tensor_a
# I tried many things but ended putting it to member variable.
self.tensor_a = K.identity(inputs_hat)
....
outside when trying to build the parallel model I do this
a_model = models.Model([my_layer.tensor_a],[my_layer.c])
I could not find any good solution to this problem? How can I turn the tensor into K.tensor??
Related
I'm wondering about how to do the following thing:
If I have a torch.tensor x with shape (4,5,1) how can apply a neural network using PyTorch on the last dimension?
Using the standard procedure, the model is flattening the entire tensor into some new tensor of shape (20,1) but this is not actually what I want.
Let's say we want some output features of dimension 64, then I would like to obtain a new object of shape (4,5,64)
import torch
import torch.nn as nn
x = torch.randn(4, 5, 1)
print(x.size())
# https://pytorch.org/docs/stable/generated/torch.nn.Linear.html
m = nn.Linear(1, 64)
y = m(x)
print(y.size())
result:
torch.Size([4, 5, 1])
torch.Size([4, 5, 64])
I have some pre-trained weights (both for layer and gradient) as Numpy Arrays, and I need to set them in a network I recreated.
Example of part of my network:
X_input = Input((4,256,256))
# batchSize is 4
# size so far: (batchSize,4,256,256)
X = Conv2D(96,(11,11), strides=(4,4), data_format = 'channels_first')(X_input)
# output of the convolution has size: (batchSize, 96, 62, 62)
X = BatchNormalization(axis = 1)(X)
X = Activation('relu')(X)
X = MaxPooling2D((3, 3), strides=(2, 2), data_format='channels_first')(X)
The np.array of weights I should set in the Conv2D layer has shape: (96, 4, 11, 11)
I can actually call the set_weights() function as with a Sequential() model like:
model.get_layer('layerName').set_weights(myNpArrayWeights)
But if I do so, this gives the error:
ValueError: You called `set_weights(weights)` on layer "step2_conv1" with a
weight list of length 96, but the layer was expecting 2 weights.
Provided weights: [[[[ 3.87499551e-03 1.32818555e-03 2.97062146e-0...
as if shape were incorrect?
So I tried to input 2 testing weights using np.array([1,2]).
This is the error reported:
ValueError: Fetch argument <tf.Variable 'step2_conv1_4/kernel:0'
shape=(11, 11, 4, 96) dtype=float32_ref> cannot be interpreted as a Tensor.
(Tensor Tensor("step2_conv1_4/kernel:0", shape=(11, 11, 4, 96), dtype=float32_ref)
is not an element of this graph.)
How do I solve this?
How do can I set the weights also for the gradient?
Python version: 3.6.5
Keras version: 2.2.4
Tensorflow version: 1.13.1
EDIT
For the first ValueError:
In Conv2D layer set use_bias=False so that it expects only 1 array of weights, if use_bias is set True then an additional array of weights will be considered in the layer.
For the second ValueError:
Before instantiating the model, it is necessary to clear the session, because you might have run multiple times a model (as I did) and apparently Tensorflow gets confused about the multiple graphs present.
To clean the session run:
keras.backend.clear_session()
Trying to run a beam search in a Keras model, I get confusing (and conflicting?) error messages. My model has inputs such as
inputs = Input(name='spectrograms',
shape=(None, hparams["n_spectrogram"]))
input_length = Input(name='len_spectrograms',
shape=[1], dtype='int64')
and the CTC loss function requires the [1] shapes in input and label length. As far as I understand, the output should be obtained with something like
# Stick connectionist temporal classification on the end of the core model
paths = K.function(
[inputs, input_length],
K.ctc_decode(output, input_length, greedy=False, top_paths=4)[0])
but as-is, that leads to a complain about the shape of input_length
ValueError: Shape must be rank 1 but is rank 2 for 'CTCBeamSearchDecoder' (op: 'CTCBeamSearchDecoder') with input shapes: [?,?,44], [?,1].
but if I chop off that dimension
K.ctc_decode(output, input_length[..., 0], greedy=False, top_paths=4)[0])
the model definition runs, but when I run y = paths([x, numpy.array([[30], [30]])]) with a x.shape == (2, 30, 513) I suddenly get
tensorflow.python.framework.errors_impl.InvalidArgumentError: sequence_length is not a vector
[[{{node CTCBeamSearchDecoder}} = CTCBeamSearchDecoder[beam_width=100, merge_repeated=true, top_paths=4, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Log, ToInt32)]]
What am I doing wrong?
I'm using the estimator library of tensorflow on python. I want to train a student network by using a pre-trained teacher.I'm facing the following issue.
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": train_data},
y=train_labels,
batch_size=100,
num_epochs=None,
shuffle=True)
student_classifier.train(
input_fn=train_input_fn,
steps=20,
hooks=None)
This code returns a generator object that is passed to a student classifier. Inside the generator, we have the inputs and labels (in batches of 100) as tensors. The problem is, I want to pass the same values to the teacher model and extract its softmax outputs. But unfortunately, the model input requires a numpy array as follows
student_classifier = tf.estimator.Estimator(
model_fn=student_model_fn, model_dir="./models/mnist_student")
def student_model_fn(features, labels, mode):
sess=tf.InteractiveSession()
tf.train.start_queue_runners(sess)
data=features['x'].eval()
out=labels.eval()
sess.close()
input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])
eval_teacher_fn = tf.estimator.inputs.numpy_input_fn(
x={"x":data},
y=out,
num_epochs=1,
shuffle=False)
This requires x and y to be numpy arrays so I converted it via using such as ugly hack of using a session to convert tensor to numpy. Is there a better way of doing this?
P.S. I tried tf.estimator.Estimator.get_variable_value() but it retrieves weights from the model, not the input and output
Convert Tensor to Numpy_array using tf.make_ndarray.
tf.make_ndarray(), Create a numpy ndarray with the same shape and data as the tensor.
Sample working code:
import tensorflow as tf
a = tf.constant([[1,2,3],[4,5,6]])
proto_tensor = tf.make_tensor_proto(a)
tf.make_ndarray(proto_tensor)
output:
array([[1, 2, 3],
[4, 5, 6]], dtype=int32)
# output has shape (2,3)
I'm a bit new to Keras and deep learning. I'm currently trying to replicate this paper but when I'm compiling the second model (with the LSTMs) I get the following error:
"TypeError: unsupported operand type(s) for +: 'NoneType' and 'int'"
The description of the model is this:
Input (length T is appliance specific window size)
Parallel 1D convolution with filter size 3, 5, and 7
respectively, stride=1, number of filters=32,
activation type=linear, border mode=same
Merge layer which concatenates the output of
parallel 1D convolutions
Bidirectional LSTM consists of a forward LSTM
and a backward LSTM, output_dim=128
Bidirectional LSTM consists of a forward LSTM
and a backward LSTM, output_dim=128
Dense layer, output_dim=128, activation type=ReLU
Dense layer, output_dim= T , activation type=linear
My code is this:
from keras import layers, Input
from keras.models import Model
def lstm_net(T):
input_layer = Input(shape=(T,1))
branch_a = layers.Conv1D(32, 3, activation='linear', padding='same', strides=1)(input_layer)
branch_b = layers.Conv1D(32, 5, activation='linear', padding='same', strides=1)(input_layer)
branch_c = layers.Conv1D(32, 7, activation='linear', padding='same', strides=1)(input_layer)
merge_layer = layers.Concatenate(axis=-1)([branch_a, branch_b, branch_c])
print(merge_layer.shape)
BLSTM1 = layers.Bidirectional(layers.LSTM(128, input_shape=(8,40,96)))(merge_layer)
print(BLSTM1.shape)
BLSTM2 = layers.Bidirectional(layers.LSTM(128))(BLSTM1)
dense_layer = layers.Dense(128, activation='relu')(BLSTM2)
output_dense = layers.Dense(1, activation='linear')(dense_layer)
model = Model(input_layer, output_dense)
model.name = "lstm_net"
return model
model = lstm_net(40)
After that I get the above error. My goal is to give as input a batch of 8 sequences of length 40 and get as output a batch of 8 sequences of length 40 too. I found this issue on Keras Github LSTM layer cannot connect to Dense layer after Flatten #818 and there #fchollet suggests that I should specify the 'input_shape' in the first layer which I did but probably not correctly. I put the two print statements to see how the shape is changing and the output is:
(?, 40, 96)
(?, 256)
The error occurs on the line BLSTM2 is defined and can be seen in full here
Your problem lies in these three lines:
BLSTM1 = layers.Bidirectional(layers.LSTM(128, input_shape=(8,40,96)))(merge_layer)
print(BLSTM1.shape)
BLSTM2 = layers.Bidirectional(layers.LSTM(128))(BLSTM1)
As a default, LSTM is returning only the last element of computations - so your data is losing its sequential nature. That's why the proceeding layer raises an error. Change this line to:
BLSTM1 = layers.Bidirectional(layers.LSTM(128, return_sequences=True))(merge_layer)
print(BLSTM1.shape)
BLSTM2 = layers.Bidirectional(layers.LSTM(128))(BLSTM1)
In order to make the input to the second LSTM to have sequential nature also.
Aside of this - I'd rather not use input_shape in middle model layer as it's automatically inferred.