I use Keras pretrained model VGG16. The problem is that after configuring tensorflow to use the GPU I get an error that I didn't have before when using the CPU.
The error is the following one:
Traceback (most recent call last):
File "/home/guillaume/Documents/Allianz/ConstatOrNotConstatv3/train_network.py", line 109, in <module>
model = LeNet.build(width=100, height=100, depth=3, classes=5)
File "/home/guillaume/Documents/Allianz/ConstatOrNotConstatv3/lenet.py", line 39, in build
output = model(pretrainedOutput)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 443, in __call__
previous_mask = _collect_previous_mask(inputs)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 1311, in _collect_previous_mask
mask = node.output_masks[tensor_index]
AttributeError: 'Node' object has no attribute 'output_masks'
I get it after executing this code :
pretrained_model = VGG16(
include_top=False,
input_shape=(height, width, depth),
weights='imagenet'
)
for layer in pretrained_model.layers:
layer.trainable = False
model = Sequential()
# first (and only) set of FC => RELU layers
model.add(Flatten())
model.add(Dense(200, activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
model.add(Dense(400, activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
# softmax classifier
model.add(Dense(classes,activation='softmax'))
pretrainedInput = pretrained_model.input
pretrainedOutput = pretrained_model.output
output = model(pretrainedOutput)
model = Model(pretrainedInput, output)
EDIT1 : I've got keras (2.2.2) and tensorflow(1.10.0rc1). I've also tried on keras 2.2.0 and same error. The thing is that the python environment I use works on others non-pretrained NN.
EDIT2 : I'm able to connect two homemade models. It's only whith the pretrained ones there is a problem and not only VGG16.
You're likely importing tf.keras.layers or tf.keras.applications or other keras modules from tensorflow.keras, and mixing these objects with objects from the "pure" keras package, which is not compatible, based upon version, etc.
I recommend seeing if you can import and run everything from the "pure" keras modules; don't use tf.keras while debugging, as they're not necessarily compatible. I had the same problem, and this solution is working for me.
I had the same error when I import keras and tenerflow.keras simultaneously:
from tensorflow.keras.optimizers import Adam
from keras.utils import multi_gpu_model
I solved this problem after changing the code into:
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.utils import multi_gpu_model
I had a similar issue, but with different architecture. As people suggested, it's important not to mix keras with tensorflow.keras, so try swapping code like:
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K
to:
from tensorflow.keras.preprocessing import image
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras import backend as K
Also make sure, you don't use keras.something inside your code (not only imports) as well, hope it helps : )
Also, I used Keras 2.2.4 with tensorflow 1.10.0
if you are importing VGG16 from tensorflow.keras.applications.vgg16 then import all models from tensorflow
from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
elif you are importing from keras like:
from keras.applications.vgg16 import VGG16
then use model import from keras
from keras.models import Sequential
from keras.layers import Dense
Related
I got this error while working with CNN:
This model has not yet been built. Build the model first by calling `build()` or by calling the model on a batch of data.
My code is below :
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Dropout
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.callbacks import TensorBoard
model=Sequential()
model.add(Conv2D(32,5,input_shape=(1,28,28),activation='relu',data_format='channels_last'))
model.add(MaxPooling2D(pool_size=(2,2),strides=2))
model.add(Flatten())
model.add(Conv2D(64,5,input_shape=(1,28,28),activation='relu',data_format='channels_last'))
model.add(MaxPooling2D(pool_size=2,strides=2))
model.add(Flatten())
model.add(Dense(units=32,activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(units=1,activation='softmax'))
model.summary()
According to the error, run:
input_shape=(1,28,28)
model.build(input_shape)
model.summary()
So I'm loading the keras Resnet50 model using the below code:
backbone = resnet50.ResNet50(include_top=False, weights=None, input_tensor=None, pooling=None, classes=1000)
I need to get a batch normalization layer which is named 'bn5c_branch2c' in the resnet50 code on github(line 75).
Running backbone.get_layer('bn5c_branch2c') gives me a ValueError: No such layer: bn5c_branch2c.
Printing the names of the layers using:
for layer in backbone.layers:
print(layer.name)
I found that indeed none of the layers go by this name, instead they're named something like 'conv5_block1_3_bn'. However, in the code of resnet50 the name is clearly fed as 'bn5c_branch2c'. I'm unable to understand how this is happening and how can I extract a layer by the name it is assigned in the code. Any help would be great. Thanks.
tensorflow - 2.3.1
keras - 2.4.3
OS - Ubuntu 20.04.1 LTS
bn5c_branch2c layer works with Tensorflow 1.13.1.
from tensorflow.keras.applications import resnet50
from tensorflow.keras import layers
from tensorflow.keras.layers import Concatenate, Conv2D, UpSampling2D, BatchNormalization, Add, Lambda
from tensorflow.keras.models import Model
backbone = resnet50.ResNet50(include_top=False,
weights=None,
input_tensor=None,
pooling=None,
classes=1000)
C5 = backbone.get_layer('bn5c_branch2c').output
In line where I try to add LSTM layer to my Sequential model from tensorflow.keras in this way:
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, LSTM, Dropout, GRU, TimeDistributed
#...
modelX1 = Sequential()
modelX1.add(LSTM(LSTM_neurons[0],input_shape=(dataX1.shape[1],dataX1.shape[2]), activation='tanh', recurrent_activation='tanh', use_bias=True, return_sequences = True))
This error appears:
File "C:\Users\mroso\Anaconda3\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py", line 168, in _variable_handle_from_shape_and_dtype handle_data.shape_and_type.append(
AttributeError: 'google.protobuf.pyext._message.RepeatedCompositeCo' object has no attribute 'append'
I am using Tensorflow 2.1.0, protobuf 3.11.4, Spyder 4 and I am working on Windows 10.
When I was using Tensorflow 1.4 (90% sure, that was this version) everything was all right.
Does anyone know how to fix this error?
Thank you in advance for your help.
You might want to look at the solution stated at this link
As the solution suggests, you can try rolling back your TensorFlow version to 2.0.0
I got this error when I tried to modify the learning rate parameter of SGD optimizer in Keras. Did I miss something in my code or my Keras was not installed properly?
Here is my code:
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, GlobalAveragePooling2D, Activation
import keras
from keras.optimizers import SGD
model = Sequential()
model.add(Dense(64, kernel_initializer='uniform', input_shape=(10,)))
model.add(Activation('softmax'))
model.compile(loss='mean_squared_error', optimizer=SGD(lr=0.01), metrics= ['accuracy'])*
and here is the error message:
Traceback (most recent call last): File
"C:\TensorFlow\Keras\ResNet-50\test_sgd.py", line 10, in
model.compile(loss='mean_squared_error', optimizer=SGD(lr=0.01), metrics=['accuracy']) File
"C:\Users\nsugiant\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\keras_impl\keras\models.py",
line 787, in compile
**kwargs) File "C:\Users\nsugiant\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\keras_impl\keras\engine\training.py",
line 632, in compile
self.optimizer = optimizers.get(optimizer) File "C:\Users\nsugiant\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\keras_impl\keras\optimizers.py",
line 788, in get
raise ValueError('Could not interpret optimizer identifier:', identifier) ValueError: ('Could not interpret optimizer identifier:',
<keras.optimizers.SGD object at 0x000002039B152FD0>)
The reason is you are using tensorflow.python.keras API for model and layers and keras.optimizers for SGD. They are two different Keras versions of TensorFlow and pure Keras. They could not work together. You have to change everything to one version. Then it should work.
I am bit late here, Your issue is you have mixed Tensorflow keras and keras API in your code. The optimizer and the model should come from same layer definition. Use Keras API for everything as below:
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM, BatchNormalization
from keras.callbacks import TensorBoard
from keras.callbacks import ModelCheckpoint
from keras.optimizers import adam
# Set Model
model = Sequential()
model.add(LSTM(128, input_shape=(train_x.shape[1:]), return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
# Set Optimizer
opt = adam(lr=0.001, decay=1e-6)
# Compile model
model.compile(
loss='sparse_categorical_crossentropy',
optimizer=opt,
metrics=['accuracy']
)
I have used adam in this example. Please use your relevant optimizer as per above code.
Hope this helps.
This problem is mainly caused due to different versions. The tensorflow.keras version may not be same as the keras.
Thus causing the error as mentioned by #Priyanka.
For me, whenever this error arises, I pass in the name of the optimizer as a string, and the backend figures it out.
For example instead of
tf.keras.optimizers.Adam
or
keras.optimizers.Adam
I do
model.compile(optimizer= 'adam' , loss= keras.losses.binary_crossentropy, metrics=['accuracy'])
from tensorflow.keras.optimizers import SGD
This works well.
Since Tensorflow 2.0, there is a new API available directly via tensorflow:
https://www.pyimagesearch.com/2019/10/21/keras-vs-tf-keras-whats-the-difference-in-tensorflow-2-0/
Solution works for tensorflow==2.2.0rc2, Keras==2.2.4 (on Win10)
Please also note that the version above uses learning_rate as parameter and no longer lr.
For some libraries (e.g. keras_radam) you'll need to set up an environment variable before the import:
import os
os.environ['TF_KERAS'] = '1'
import tensorflow
import your_library
In my case it was because I missed the parentheses. I am using tensorflow_addons so my code was like
model.compile(optimizer=tfa.optimizers.LAMB, loss='binary_crossentropy',
metrics=['binary_accuracy'])
And it gives
ValueError: ('Could not interpret optimizer identifier:', <class tensorflow_addons.optimizers.lamb.LAMB'>)
Then I changed my code into:
model.compile(optimizer=tfa.optimizers.LAMB(), loss='binary_crossentropy',
metrics=['binary_accuracy'])
and it works.
recently, in the latest update of Keras API 2.5.0 , importing Adam optimizer shows the following error:
from keras.optimizers import Adam
ImportError: cannot import name 'Adam' from 'keras.optimizers'
instead use the following for importing optimizers (i.e. Adam) :
from keras.optimizers import adam_v2
optimizer = adam_v2.Adam(learning_rate=lr, decay=lr/epochs)
Model.compile(loss='--', optimizer=optimizer , metrics=['--'])
Running the Keras documentaion example https://keras.io/examples/cifar10_cnn/
and installing the latest keras and tensor flow versions
(at the time of this writing
tensorflow 2.0.0a0 and Keras version 2.2.4 )
I had to import explicitly the optimizer the keras the example is using,specifically the line on top of the example :
opt = tensorflow.keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)
was replaced by
from tensorflow.keras.optimizers import RMSprop
opt = RMSprop(lr=0.0001, decay=1e-6)
In the recent version the api "broke" and keras.stuff in a lot of cases became tensorflow.keras.stuff.
Use one style in one kernel, try not to mix
from keras.optimizers import sth
with
from tensorflow.keras.optimizers import sth
I tried the following and it worked for me:
from keras import optimizers
sgd = optimizers.SGD(lr=0.01)
model.compile(loss='mean_squared_error', optimizer=sgd)
use
from tensorflow.keras import optimizers
instead of
from keras import optimizers
Try changing your import lines to
from keras.models import Sequential
from keras.layers import Dense, ...
Your imports seem a little strange to me. Maybe you could elaborate more on that.
I have misplaced parenthesis and got this error,
Initially it was
x=Conv2D(filters[0],(3,3),use_bias=False,padding="same",kernel_regularizer=l2(reg),x))
The corrected version was
x=Conv2D(filters[0],(3,3),use_bias=False,padding="same",kernel_regularizer=l2(reg))(x)
Just give
optimizer = 'sgd' / 'RMSprop'
I got the same error message and resolved this issue, in my case, by replacing the assignment of optimizer:
optimizer=keras.optimizers.Adam
with its instance instead of the class itself:
optimizer=keras.optimizers.Adam()
I tried everything in this thread to fix it but they didn't work. However, I managed to fix it for me. For me, the issue was that calling the optimizer class, ie. tensorflow.keras.optimizers.Adam caused the error, but calling the optimizer as a function, ie. tensorflow.keras.optimizers.Adam() worked. So my code looks like:
model.compile(
loss=tensorflow.keras.losses.categorical_crossentropy(),
optimizer=tensorflow.keras.optimizers.Adam()
)
Looking at the tensorflow github, I am not the only one with this error where calling the function rather than the class fixed the error.
import tensorflow as tf
import tensorflow
from tensorflow import keras
from keras.layers import Dense
I am getting the below error
from keras.layers import Input, Dense
Traceback (most recent call last):
File "<ipython-input-6-b5da44e251a5>", line 1, in <module>
from keras.layers import Input, Dense
ModuleNotFoundError: No module named 'keras'
How do I solve this?
Note: I am using Tensorflow version 1.4
Use the keras module from tensorflow like this:
import tensorflow as tf
Import classes
from tensorflow.python.keras.layers import Input, Dense
or use directly
dense = tf.keras.layers.Dense(...)
EDIT Tensorflow 2
from tensorflow.keras.layers import Input, Dense
and the rest stays the same.
Try from tensorflow.python import keras
with this, you can easily change keras dependent code to tensorflow in one line change.
You can also try from tensorflow.contrib import keras. This works on tensorflow 1.3
Edited: for tensorflow 1.10 and above you can use import tensorflow.keras as keras to get keras in tensorflow.
To make it simple I will take the two versions of the code in keras and tf.keras. The example here is a simple Neural Network Model with different layers in it.
In Keras (v2.1.5)
from keras.models import Sequential
from keras.layers import Dense
def get_model(n_x, n_h1, n_h2):
model = Sequential()
model.add(Dense(n_h1, input_dim=n_x, activation='relu'))
model.add(Dense(n_h2, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
return model
In tf.keras (v1.9)
import tensorflow as tf
def get_model(n_x, n_h1, n_h2):
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(n_h1, input_dim=n_x, activation='relu'))
model.add(tf.keras.layers.Dense(n_h2, activation='relu'))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(4, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
return model
or it can be imported the following way instead of the above-mentioned way
from tensorflow.keras.layers import Dense
The official documentation of tf.keras
Note: TensorFlow Version is 1.9
Its not quite fine to downgrade everytime, you may need to make following changes as shown below:
Tensorflow
import tensorflow as tf
#Keras
from tensorflow.keras.models import Sequential, Model, load_model, save_model
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.layers import Dense, Activation, Dropout, Input, Masking, TimeDistributed, LSTM, Conv1D, Embedding
from tensorflow.keras.layers import GRU, Bidirectional, BatchNormalization, Reshape
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding
from tensorflow.keras import optimizers
from tensorflow.keras.callbacks import ModelCheckpoint
The point is that instead of using
from keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding
you need to add
from tensorflow.keras.layers import Reshape, Dropout, Dense,Multiply, Dot, Concatenate,Embedding
Starting from TensorFlow 2.0, only PyCharm versions > 2019.3 are able to recognise tensorflow and keras inside tensorflow (tensorflow.keras). Francois Chollet himself (author of Keras) recommends that everybody switches to tensorflow.keras in place of plain keras.
There is also one important mentioning here:
IMPORTANT NOTE FOR TF >= 2.0
There (this) is an ongoing issue with JetBrains (in fact from TensorFlow side), it seems that this error comes up from time to time (https://youtrack.jetbrains.com/issue/PY-53599).
It sometimes happens that PyCharm is not able to correctly import/recognize keras inside tensorflow or other imports.
Depending on Python + TF + PyCharm versions, you may have to alternate between the following import types:
from tensorflow.keras.models import Model
OR
from tensorflow.python.keras.models import Model
this worked for me in tensorflow==1.4.0
from tensorflow.python import keras
I have a similar problem importing those libs. I am using Anaconda Navigator 1.8.2 with Spyder 3.2.8.
My code is the following:
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
import math
#from tf.keras.models import Sequential # This does not work!
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import InputLayer, Input
from tensorflow.python.keras.layers import Reshape, MaxPooling2D
from tensorflow.python.keras.layers import Conv2D, Dense, Flatten
I get the following error:
from tensorflow.python.keras.models import Sequential
ModuleNotFoundError: No module named 'tensorflow.python.keras'
I solve this erasing tensorflow.python
With this code I solve the error:
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
import math
#from tf.keras.models import Sequential # This does not work!
from keras.models import Sequential
from keras.layers import InputLayer, Input
from keras.layers import Reshape, MaxPooling2D
from keras.layers import Conv2D, Dense, Flatten
I had the same problem with Tensorflow 2.0.0 in PyCharm. PyCharm did not recognize tensorflow.keras; I updated my PyCharm and the problem was resolved!