import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense
model = Sequential([ Dense(32, activation='relu', input_shape=(5038,)), Dense(32, activation='relu'), Dense(881, activation='sigmoid'),])
model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])
hist = model.fit(X_train, Y_train, batch_size=32, epochs=100, validation_data=(X_val, Y_val))
Gives the following OUtput
AttributeError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py in _get_default_graph()
65 try:
---> 66 return tf.get_default_graph()
67 except AttributeError:
AttributeError: module 'tensorflow' has no attribute 'get_default_graph'
During handling of the above exception, another exception occurred:
RuntimeError Traceback (most recent call last)
5 frames
/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py in _get_default_graph()
67 except AttributeError:
68 raise RuntimeError(
---> 69 'It looks like you are trying to use '
70 'a version of multi-backend Keras that '
71 'does not support TensorFlow 2.0. We recommend '
RuntimeError: It looks like you are trying to use a version of multi-backend Keras that does not support TensorFlow 2.0. We recommend using `tf.keras`, or alternatively, downgrading to TensorFlow 1.14.
Why am I getting this error?
It looks like you're using TensorFlow 2.0 (or a more recent version). TensorFlow >= 2.0 has full, built-in support for Keras, under tf.keras. As documented at the Keras website, TensorFlow users should use tf.keras instead of the Keras module.
Your specific example can be rewritten using tf.keras in the following way:
import tensorflow as tf
model = tf.keras.Sequential([
tf.keras.layers.Dense(32, activation='relu', input_shape=(5038,)),
tf.keras.layers.Dense(32, activation='relu'),
tf.keras.layers.Dense(881, activation='sigmoid')])
model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])
hist = model.fit(X_train, Y_train, batch_size=32, epochs=100, validation_data=(X_val, Y_val))
For more information, see the tf.keras tutorials here: https://www.tensorflow.org/tutorials
Related
For creating a simple convolutional neural network I have imported the keras from tensorflow but it says input_shape is undefined.
# creating a simple cnn with 2 layers input/output
# from tensorflow.python.keras.engine.sequential import Sequential
# from tensorflow.python.keras.layers import Dense
from tensorflow import keras
from keras.models import Sequential
model = keras.Sequential([
keras.layers.Dense(10, input_shape(784,), activation='sigmoid')
])
model.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics={'accuracy'}
)
model.fit(X_train_flattened, y_train, epochs=5)
I have also tried importing keras.layers separately but no use.
The error:
NameError Traceback (most recent call last)
<ipython-input-4-db449261e881> in <module>
6
7 model = keras.Sequential([
----> 8 keras.layers.Dense(10, input_shape(784,), activation='sigmoid')
9 ])
10
NameError: name 'input_shape' is not defined
Generally, if you want to specify a keyword parameter, you need to use an equal sign that you are currently missing, like so keras.layers.Dense(10, input_shape=(784,), activation='sigmoid')
I'm trying to visualize the model in Tensorboard without training.
I checked this and that, but this still doesn't work even for the simplest model.
import tensorflow as tf
import tensorflow.keras as keras
# Both tf.__version__ tensorboard.__version__ are 2.5.0
s_model = keras.models.Sequential([
keras.layers.Flatten(input_shape=(28, 28)),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.2),
keras.layers.Dense(10, activation='softmax')
])
logdir = '.../logs'
_callbacks = keras.callbacks.TensorBoard(log_dir=logdir)
_callbacks.set_model(s_model) # This is exactly suggested in the link
When I did the above, I get the error message:
Graph visualization failed.
Error: Malformed GraphDef. This can sometimes be caused by a bad
network connection or difficulty reconciling mulitple GraphDefs; for
the latter case, please refer to
https://github.com/tensorflow/tensorboard/issues/1929.
I don't think this is a reconciliation problem because it is not a custom function, and if I compile the model, train, then I can get the graph visualization I wanted.
s_model.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
(train_images, train_labels), _ = keras.datasets.fashion_mnist.load_data()
train_images = train_images / 255.0
logdir = '.../logs'
tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
s_model.fit(
train_images,
train_labels,
batch_size=64,
epochs=5,
callbacks=[tensorboard_callback])
This gives the wanted graph visualization. But is there any other way to get graph visualization in Tensorboard without training?
Of course, I'm also aware that workaround, i.e. train with the tf.random.normal() for a while, would do the trick but I'm looking for the neat way like _callbacks.set_model(s_model)...
I'm new to tensorflow. What I'm trying to do is to train a simple neural network to solve the Newton 2 problems, to guess the force value of given mass and acceleration values. The input layer consists of two neurons which are mass and acceleration values. The output layer is the force.
The program just gives a warning, prints some data which I guess the outputs and then exits with code 1. I cannot try anything to solve this problem. Because as I said before I'm new to tensorflow and there is no error message.
Here is the code:
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.models import Sequential
import numpy as np
import pickle
X = pickle.load(open("Newton2_X.pickle", "rb"))
y = pickle.load(open("Newton2_y.pickle", "rb"))
model = Sequential()
# model.add(Flatten())
model.add(Dense(2, activation="relu"))
model.add(Dense(128, activation="relu"))
model.add(Dense(1, activation="softmax"))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(X, y, epochs=3, validation_split=0.1, batch_size=100)
Here are the pickle files:
https://drive.google.com/drive/folders/1FkKmY4px8oQJkbHYb_Z4y4Lnb1EazkvP?usp=sharing
After this part of the code I've some additional lines to make the network to guess a new value and some print lines. These lines are not executed. In fact, I've found that the 'problem' must be in model.fit(...) part. Because no lines after that line are executed.
Here is the full warning msg that I got from the program:
WARNING: Logging before flag parsing goes to stderr.
W0816 07:02:05.292823 17652 deprecation.py:506] From C:\Users\SABA\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
6, 0.2142802901764338, 0.26114980919201514, 0.2451221454091551, 0.19920049739052853, ...
A couple of things to tweak.
Firstly, I don't think the data is the shape that you think it is. You have:
X.shape # (45000, 2, 2, 1)
y is a flat list with 90,000 elements.
Secondly, you are predicting a number (so a regression) but you were trying to use 'sparse_categorical_crossentropy' as a loss function which is for classification problems.
I can get your code to run by simply slicing the data down to the shape we need but obviously it won't train as I haven't paired up the correct Xs and ys. You'll need to sort this out properly in the data
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.models import Sequential
import numpy as np
import pickle
### TODO - sort this out!
X = pickle.load(open("Newton2_X.pickle", "rb"))[:,0,:,0]
y = np.array(pickle.load(open("Newton2_y.pickle", "rb")))[:45000]
####
model = Sequential()
# model.add(Flatten())
model.add(Dense(2, activation="relu"))
model.add(Dense(128, activation="relu"))
model.add(Dense(1, activation="softmax"))
model.compile(optimizer='adam',
loss='mse')
model.fit(X, y, epochs=3, validation_split=0.1, batch_size=100)
WARNING:tensorflow:Sequential models without an input_shape passed to the first layer cannot reload their optimizer state. As a result, your model is starting with a freshly initialized optimizer.
while trying to load a saved model i encountered this warning from tensorflow
import tensorflow.keras as keras
import tensorflow as tf
mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train = tf.keras.utils.normalize(x_train, axis=1)
x_test = tf.keras.utils.normalize(x_test, axis=1)
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=3)
model.save('epic_num_reader.model')
new_model = tf.keras.models.load_model('epic_num_reader.model')
predictions = new_model.predict(x_test)
Had the same problem after upgrading to TF 1.14, I fixed it changing the definition of the first layer from this:
model.add(tf.keras.layers.Flatten())
to this
model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
where 28 is the size of the input map to be flattened (mnist pixels in our case)
As the warning suggest, your first layer need the argument input_shape. In your case this would be the layer Flatten.
In the keras Documentation there is an extra section about the sequential API. See here for further information.
model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
for the first layer after tf 1.14 it is require to use input type which is the dimensions for the particular image.
Or you might get warning while retrieving model to not get proper working for your optimizer
I am trying to transform my Keras model in the Google cloud console into a TPU model. Unfortunatelly I am getting an error as shown below. My minimal example is the following:
import keras
from keras.models import Sequential
from keras.layers import Dense, Activation
import tensorflow as tf
import os
model = Sequential()
model.add(Dense(32, input_dim=784))
model.add(Dense(32))
model.add(Activation('relu'))
model.compile(optimizer='rmsprop', loss='mse')
tpu_model = tf.contrib.tpu.keras_to_tpu_model(
model,
strategy=tf.contrib.tpu.TPUDistributionStrategy(
tf.contrib.cluster_resolver.TPUClusterResolver(TPU_WORKER)))
My output is:
Using TensorFlow backend.
Traceback (most recent call last):
File "cloud_python4.py", line 11, in <module>
tpu_model = tf.contrib.tpu.keras_to_tpu_model(AttributeError: module 'tensorflow.contrib.tpu' has no attribute 'keras_to_tpu_model'
The keras_to_tpu_model method seems experimental as indicated on the tensorflow website. Has it recently been removed? If so, how can I proceed to make use of TPUs to estimate my Keras model? If the keras_to_tpu_model method would be still available, why can I not invoke it?
I am assuming you defined you TPU_WORKER as below
import os
TPU_WORKER = ‘grpc://’ + os.environ[‘COLAB_TPU_ADDR’]
Instead of converting your model to TPU, build a distribution strategy. This is the method by which the batch will be distributed to the eight TPUs and how the loss from each will be calculated.
resolver = tf.contrib.cluster_resolver.TPUClusterResolver(TPU_WORKER)
tf.contrib.distribute.initialize_tpu_system(resolver)
strategy = tf.contrib.distribute.TPUStrategy(resolver)
With the strategy build and compile your model. This should work quite nicely for regression.
with strategy.scope():
model = Sequential()
model.add(Dense(32, input_dim=784))
model.add(Dense(32))
model.add(Activation('relu'))
model.compile(optimizer='rmsprop', loss='mse')
Import keras from tensorflow.
This is because tf.contrib.tpu.keras_to_tpu_model( )' requires a tensorflow version Model, not the keras version.
For example, use from tensorflow.keras.layers import Dense, Activation instead. And so on.