All Questions
Tagged with tf.keras keras-layer
171
questions
59
votes
20
answers
131k
views
How to fix "AttributeError: module 'tensorflow' has no attribute 'get_default_graph'"?
I am trying to run some code to create an LSTM model but i get an error:
AttributeError: module 'tensorflow' has no attribute 'get_default_graph'
My code is as follows:
from keras.models import ...
- 663
46
votes
4
answers
96k
views
Running the Tensorflow 2.0 code gives 'ValueError: tf.function-decorated function tried to create variables on non-first call'. What am I doing wrong?
error_giving_notebook
non_problematic_notebook
As it can be seen that I have used tf.function decorator in the 'error_giving_notebook' and it throws a ValueError while the same notebook without any ...
- 585
11
votes
1
answer
1k
views
How do I save and load BatchNormalization Layer in this Tensorflow model?
I am trying to save a model and then load it later to make some predictions; what happens is that the accuracy of the model after training is 95%+, but when I save it and then load it, the accuracy ...
- 461
9
votes
2
answers
4k
views
Is it still necessary to implement `compute_output_shape()` when defining a custom tf.keras Layer?
I have implemented a custom Layer in tf.keras, using TensorFlow 2.1.0.
In the past, when using the stand-alone Keras, it was important to define the compute_output_shape(input_shape) method in any ...
- 1,517
5
votes
2
answers
17k
views
AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'
I have been working on keras yolov3 model for object detection. This error keeps showing up.
Here is the error:
AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'
...
5
votes
2
answers
11k
views
keras : add layers to another model
I need to add layers to an existing model. However, I need to add the layers at "the main model level", that is I can't use the classic functional approach. For example, if I use something ...
- 1,359
5
votes
1
answer
3k
views
How does Embedding layer in Keras work on float input values?
x is a (64, 1) dimensional vector created randomly using tf.random.uniform((BATCH_SIZE, 1)), where the BATCH_SIZE = 64.
A random initialization looks like this:
tf.Tensor(
[[0.76922464]
[0.7928164 ]
...
- 888
5
votes
0
answers
2k
views
keras.backend.function return a AttributeError: Layer dense is not connected, no input to return
I want to know the median result of a neutral network for tuning purpose. I design my model and use keras.backend.function but failed(AttributeError: Layer dense is not connected, no input to return). ...
- 401
4
votes
1
answer
5k
views
Adding custom metric Keras Subclassing API
I'm following the section "Losses and Metrics Based on Model Internals" on chapter 12 of "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition - Aurélien Geron", in which he ...
- 303
4
votes
1
answer
2k
views
Memory leak when running universal-sentence-encoder-large itterating on dataframe
I have 140K sentences I want to get embeddings for. I am using TF_HUB Universal Sentence Encoder and am iterating over the sentences(I know it's not the best way but when I try to feed over 500 ...
- 624
4
votes
1
answer
4k
views
Unable to understand the behavior of method `build` in tensorflow keras layers (tf.keras.layers.Layer)
Layers in tensorflow keras have a method build that is used to defer the weights creation to a time when you have seen what the input is going to be. a layer's build method
I have a few questions i ...
- 5,082
4
votes
0
answers
2k
views
TypeError: Cannot interpret '<KerasTensor: shape=(None, 3) dtype=float32 (created by layer 'input_1')>' as a data type
Very simple question. I am using tensorflow probability package to use a bijector to form a trainable_distribution from a simple distribution (let's say gaussian)
Everything works properly in jupyter ...
3
votes
3
answers
2k
views
How to display the layers of a pretrained model instead of a single entry in model.summary() output?
As the title clearly describes the question, I want to display the layers of a pretained model instead of a single entry (please see the vgg19 (Functional) entry below) in model.summary() function ...
- 6,346
3
votes
1
answer
1k
views
Keras Layer Build Error: build() takes 1 Positional Argument but two were given
I have the following error in this simple layer:
class MyLayer(Layer):
def __init__(self):
super(MyLayer, self).__init__()
def build(self):
# Create a trainable weight variable for this ...
- 1,279
3
votes
1
answer
62
views
a problem and how to deal with batch while creating a Model
from keras_multi_head import MultiHeadAttention
import keras
from keras.layers import Dense,Input,Multiply
from keras import backend as K
from keras.layers.core import Dropout, Layer
from keras.models ...
- 81
3
votes
1
answer
486
views
Converting Keras to Tensorflow -- Pruning + Probability
I have a code that mixes Tensorflow Probability (requires TF 2.00) with Keras Pruning, pruning weights of a first Dense Layer and providing inputs for TF probability, having both codes (Keras + TF) in ...
- 4,916
3
votes
1
answer
689
views
Tensorflow v2.16 tf.keras.layers Embedding not accepting argument for input_length
While working with Embedding for an LSTM model I came across an issue with input_length:
ValueError: Unrecognized keyword arguments passed to Embedding: {'input_length': 536}
Is input length being ...
- 41
3
votes
1
answer
125
views
How to obtain all layers within a custom layer subclassed from keras.layers
I'm trying to get all layers from within a custom layer subclassed from tf.keras.layers but I am having difficulties with this. The end goal is to create a DAG (Directed Acyclic Graph) that has layers ...
- 59
3
votes
1
answer
790
views
How to freeze selected weights in keras or tf.keras?
I am trying out something where I required to freeze some selected weights. Take this example
from keras.models import Sequential
from keras.layers import Dense,Input
model = Sequential()
model.add(...
- 14.6k
3
votes
0
answers
59
views
Custom layer at top of Tensorflow model
I want to add a Custom Layer to a Tensorflow Model which transforms every row of a the input set to the model in a set pattern.
For example, below is the custom layer than I have:
class CustomLayer:
...
2
votes
2
answers
8k
views
How to remove the last layer from a pre-trained model. I have tried model.layers.pop() but it is not working
I am trying to remove the last layer so that I can use transfer Leaning.
vgg16_model = keras.applications.vgg16.VGG16()
model = Sequential()
for layer in vgg16_model.layers:
model.add(layer)
...
- 67
2
votes
1
answer
5k
views
Keras --- Training freezes during fit_generator()
I am trying to train my 6000 train dataset and 1000 validation dataset but I have a problem: the program just freezes and hangs during training without any error message .
1970/6000 [========>........
- 23
2
votes
1
answer
4k
views
keras Conv2d value error: Negative dimension size
New to keras, i am dealing with a regression problem with Tensorflow as backend.
X1 = TrainingSet[:,0:603]
Y1 = TrainingSet[:,603:607]
###################################
#reshape Xtrain for CNN
X1 ...
- 39
2
votes
3
answers
2k
views
Can't load Keras model using RectifiedAdam optimizer
Trying to load a Keras model using tf.keras.models.load_model I get the following error:
import tensorflow as tf
from tensorflow_addons.optimizers import RectifiedAdam
model = tf.keras.models....
2
votes
2
answers
4k
views
"A `Concatenate` layer requires inputs with matching shapes except for the concat axis." how to solve this issuse?
Below is my unet model ,i loaded images with kerasImageDataGenerator with 360X480
dim,but when compile the model.
but model is complied if dim are 128X128 , 256X256, to load this dim what are ...
- 148
2
votes
1
answer
112
views
ValueError in model subclassing with tensorflow 2
I'm trying to implement a WideResnet using Model subclassing in keras. I cannot understand what's wrong in my code:
class ResidualBlock(layers.Layer):
def __init__(self, filters, kernel_size, ...
- 247
2
votes
3
answers
9k
views
'KerasLayer' object has no attribute 'layers'
I'm trying to customize the model taken from tf hub but
can't access the layers with following error 'KerasLayer' object has no attribute 'layers'
Here is my code as an example:
import ...
- 91
2
votes
3
answers
9k
views
TypeError: __init__() got multiple values for argument 'kernel_size'
I am getting the below error while executing my program ...
def conv2d(x, output_dim, k_size=5, stride=2, stddev=0.02, name="conv2d"):
#conv = tf.keras.layers.Conv2D(x, output_dim, kernel_size=...
- 29
2
votes
1
answer
3k
views
ValueError: Dimensions must be equal, but are 68 and 10 for '{{node mean_squared_error/SquaredDifference}} = SquaredDifference[T=DT_FLOAT]
I am using a LSTM and a VNN to convert active text to passive text. I am feeding in tokenized data to the lstm and getting a feature vector of shape (68,1) and I am then using that as input data for a ...
- 41
2
votes
1
answer
1k
views
How to use batch size to create a tensor within a custom TensorFlow Layer
I'm creating a custom TF layer and inside it I need to create a tensor of ones with something like this
class MyLayer(Layer):
def __init__(self, config, **kwargs):
super(MyLayer, self).__init__(*...
- 5,888
2
votes
1
answer
864
views
How to perform Virtual Batch Normalization (VBN) in keras
VBN is talked in This paper. And implemented Here, Here and Here. I donot want to go to core/full code. I just want to know, how to use VBN as keras layer, as i am not very expert tensorflow/keras ...
- 1,305
2
votes
0
answers
472
views
Custom Image Shear layer in tf.keras
Im migrating from Keras's ImageDataGenerators to tf.data and I have issues with reproducing the same augmentation I used to have in generator. While there are regularization layers for Random Zoom, ...
- 310
2
votes
1
answer
371
views
Multiply output of Keras layer with a scalar
Pardon me if this is a poorly framed question. This happens to be my first question here.
Say I have an output layer in Keras, and I want to multiply the last value (result of sigmoid activation) with ...
- 47
2
votes
0
answers
341
views
Error with Tensorflow 2 in a custom-written layer which worked okay in Tensorflow 1 (assert t.graph == cond_graph; AssertionError)
I have written a custom-written layer (implementing this article in Keras). This layer works fine in TF versions (1.13 and 1.15) as I have tested myself. Also, in TF 2.0, when I run tf.compat.v1....
1
vote
2
answers
9k
views
ValueError: A merge layer should be called on a list of inputs. Tensorflow Keras
I am currently trying to use the first 50 layers of the MobileNetV2. Therefore, I want to extract those layers and create a new model.
I thought I could just call every layer, but the "block_2_add" ...
- 41
1
vote
1
answer
2k
views
Loading a model Raise ValueError Unknown loss function
this is the code after i try to save and load my model:
model.save('path_to_my_model.h5')
del model
model = tf.keras.models.load_model('path_to_my_model.h5', custom_objects={'Wraparound2D': ...
- 15
1
vote
1
answer
5k
views
how to see tensor value of a layer output in keras
I have a Seq2Seq model. I am interested to print out the matrix value of the output of the encoder per iteration.
So for example as the dimension of the matrix in the encoder is (?,20) and the epoch =...
- 2,080
1
vote
1
answer
2k
views
How to load a saved model with keras? (Error : : TypeError: __init__() got an unexpected keyword argument 'trainable')
I created a CAPTCHA model based on what is provided in the Keras code example.
But when I load the model, an error pops up.
I show you the code I wrote in Jupyter notebook.
STEP1) Model build
class ...
- 121
1
vote
2
answers
711
views
Concatenation of ResNet (2D images) with fully-connected network (1D input)
I'm using a pre-built ResNet in Keras (TensorFlow 2) in the following way:
from tensorflow.keras.applications.resnet50 import ResNet50
base_model = ResNet50(weights=None, include_top=False, ...
- 6,092
1
vote
1
answer
124
views
a question about boolean list in custom layer in tf.keras
I'm trying to construct a custom output layer for my model so that the range of angles can be constrained in [-90,90]. The code is as follows:
class OutputLayer(Layer):
def __init__(self):
...
- 817
1
vote
1
answer
548
views
Does freezing keras layers reduce memory needed for training?
I have pretrained weights of a large model that can't fit in my vram. If I freeze layers, the memory needed for training will be reduced? If so, the freezed layer weights aren't saved in vram?
- 854
1
vote
2
answers
2k
views
Can I write a Keras Lambda layer with non-trainable/fixed weights?
https://keras.io/layers/writing-your-own-keras-layers/
According to here, stateless customer operations can be wrapped to Lambda layers. But if there are trainable variables, we need to implement our ...
- 73
1
vote
1
answer
2k
views
Keras (Tensorflow) Reshape Layer input error
I have a reshape input error and i don't know why.
The requested shape is 1058400, what is (1, 21168) multiplied with the batch size of 50.
What I do not understand is the apparent input size of ...
- 43
1
vote
1
answer
429
views
TensorFlow 'Variable' has no trainable parameters
I'm using a Keras Lambda Layer to make some operations with a tensor of trainable weights (or at least it should); to do that I choosed a tf.Variable as parameter but, despite trainable=True, the ...
- 69
1
vote
1
answer
429
views
Is it possible to add different behavior for training and testing in keras Functional API
I want to use different behavior in functional API for training and testing. Is it possible?
E.g.,
a = Input
b = CONV1(a)
if testing:
return b
c = CONV2(b)
- 181
1
vote
1
answer
750
views
keras: insert layers to the beginning (near the input) of an existing model
I need to add layers to the beginning of an existing model. However, I need to add the layers on "the main model level", that is I can't use the classic functional approach. For example, if ...
- 1,359
1
vote
1
answer
191
views
How to retrieve intermediate predictions results in a loop
Need to calculate time of the prediction results of each layer and pass the output of the model as an input to another layer. Treating each layer as a model and getting the intermediate results and ...
user11549734
1
vote
1
answer
789
views
Fix “AttributeError: module 'tensorflow' has no attribute 'get_default_graph'”
I have created an LSTM model, when run it I get the following error:
(...) File "/Users/myfolder/Desktop/Project-Deep-Learning-master/Flask_App/app.py", line 40, in <module>
graph = tf....
- 562
1
vote
0
answers
16
views
Extracting intermediate layer of saved model in keras. That intermediate layer is another sub-model defined in main model
Here is my architecture.
def model1():
inputs = layers.Input(shape=(x1.shape[-2],x1.shape[-1]), name='Input_layer')
x = layers.Reshape((x1.shape[-2], x1.shape[-1], 1), name='Input_reshape')(...
- 11
1
vote
0
answers
39
views
Keras tensorflow Model not returning Map with UserDefined Keynames
I am new to Keras API , I am able to get Map as response but i am not able to get userdefined key names in response For Ex: My Expected response is
{
"predictions": [
{
...
- 493