Related
I want to save a trained Keras model, so that it can be used in the Django REST backend of an application. I did a lot of research, but it seems there isn't any way to use these models without TensorFlow installed.
So, what is the use of this storage? I don't want to install a heavy library like TensorFlow on the server. I tested saving with pickle and joblib, as well as Keras' own model.save().
Is there a way to load this model without installing TensorFlow and only with Keras itself?
This is a part of my code,
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
xtrain, ytrain = np.array(xtrain), np.array(ytrain)
ytrain = np.reshape(ytrain, (ytrain.shape[0], 1, 1))
model = Sequential()
model.add(LSTM(150, return_sequences=True, input_shape=(xtrain.shape[1], 1)))
model.add(LSTM(150, return_sequences=False))
model.add(Dense(25))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(xtrain, ytrain, batch_size=1, epochs=7)
model.save('model.h5')
which normally works perfectly, but if I use the model elsewhere, I get this error:
ModuleNotFoundError: No module named 'tensorflow'
You do not need to use TensorFlow in production. You can use coefficient by replacing what random functions in your programming language.
Sample: Input array, time coefficients matrixes, and unboxed system inputs to output with feedback system in the box containers.
temp = tf.random.normal([10], 1, 0.2, tf.float32)
temp = np.asarray(temp) * np.asarray([ coefficient_0, coefficient_1, coefficient_2, coefficient_3, coefficient_4, coefficient_5, coefficient_6, coefficient_7, coefficient_8, coefficient_9 ]) #action = actions['up']
temp = tf.nn.softmax(temp)
action = int(np.argmin(temp))
I'm trying to save and load my keras model. It trains, evaluates, and saves fine (using .h5 to save model) but when I try to load the model I get the following error:
ValueError: Input 0 is incompatible with layer flatten: expected min_ndim=3, found ndim=2.
Am I loading the model incorrectly? Any help would be appreciated!
This is the code block from where I'm saving the model.
def ml(self):
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
self.addLayer(model,145,6)
model.add(tf.keras.layers.Dense(1))
optimizer = tf.keras.optimizers.Adam()
model.compile(loss='mean_squared_error',
optimizer=optimizer,
metrics=['mean_absolute_error',
'mean_squared_error'])
model.fit(self.x_train, self.y_train,epochs=130)
lm = model.evaluate(self.x_test, self.y_test, batch_size=300)
model.save('my_model.h5')
def addLayer(self, model, numNodes, numLayers):
for i in range(numLayers):
model.add(tf.keras.layers.Dense(numNodes,activation=tf.nn.relu))
To load from a different script:
import keras
from keras.models import load_model
from keras.utils import CustomObjectScope
from keras.initializers import glorot_uniform
with CustomObjectScope({'GlorotUniform': glorot_uniform()}):
model = load_model(mlPath)
While attempting to load the model I get the following error:
ValueError: Input 0 is incompatible with layer flatten: expected min_ndim=3, found ndim=2
you can try to save only the weights of your model, then re-create it using exactly the same code, and loading only the weights.
so change
model.save
to
model.save_weights('my_model.h5')
Then when you want to load your model, first, you re-create your model:
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
self.addLayer(model,145,6)
model.add(tf.keras.layers.Dense(1))
and finally load the weights:
model.load_weights('my_model.h5')
This worked for me.
Also, you could add an Input layer, together with the explicit input_shape in your model.
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
I am currently working on vgg16 model with keras.
I fine tune vgg model with some of my layer.
After fitting my model (training), I save my model with model.save('name.h5').
It can be saved without problem.
However, when I try to reload the model with load_model function, it shows the error:
You are trying to load a weight file containing 17 layers into a model
with 0 layers
Did anyone meet this problem before?
My keras verion is 2.2.
Here is part of my code ...
from keras.models import load_model
vgg_model = VGG16(weights='imagenet',include_top=False,input_shape=(224,224,3))
global model_2
model_2 = Sequential()
for layer in vgg_model.layers:
model_2.add(layer)
for layer in model_2.layers:
layer.trainable= False
model_2.add(Flatten())
model_2.add(Dense(128, activation='relu'))
model_2.add(Dropout(0.5))
model_2.add(Dense(2, activation='softmax'))
model_2.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model_2.fit(x=X_train,y=y_train,batch_size=32,epochs=30,verbose=2)
model_2.save('name.h5')
del model_2
model_2 = load_model('name.h5')
Actually I do not delete the model and then load_model immediately,
just for showing my problem.
It seems that this problem is related with the input_shape parameter of the first layer. I had this problem with a wrapper layer (Bidirectional) which did not have an input_shape parameter set. In code:
model.add(Bidirectional(LSTM(units=units, input_shape=(None, feature_size)), merge_mode='concat'))
did not work for loading my old model because the input_shape is only defined for the LSTM layer not the outer one. Instead
model.add(Bidirectional(LSTM(units=units), input_shape=(None, feature_size), merge_mode='concat'))
worked because the wrapper Birectional layer now has an input_shape parameter. Maybe you should check if the VGG net input_shape parameter is set or not or you should add a single input_layer to your model with the correct input_shape parameter.
I spent 6 hours looking around for a solution.. to apply me trained model.
finally i tried VGG16 as model and using h5 weights i´ve trained on my own and Great!
weights_model='C:/Anaconda/weightsnew2.h5' # my already trained weights .h5
vgg=applications.vgg16.VGG16()
cnn=Sequential()
for capa in vgg.layers:
cnn.add(capa)
cnn.layers.pop()
for layer in cnn.layers:
layer.trainable=False
cnn.add(Dense(2,activation='softmax'))
cnn.load_weights(weights_model)
def predict(file):
x = load_img(file, target_size=(longitud, altura))
x = img_to_array(x)
x = np.expand_dims(x, axis=0)
array = cnn.predict(x)
result = array[0]
respuesta = np.argmax(result)
if respuesta == 0:
print("Gato")
elif respuesta == 1:
print("Perro")
In case anyone is still wondering about this error:
I had the same Problem and spent days figuring out, whats causing it. I have a copy of my whole code and dataset on another system on which it worked. I noticed that it is something about the training, because without training my model, saving and loading was no problem.
The only difference between my systems was, that I was using tensorflow-gpu on my main system and for this reason, the tensorflow base version was a little bit lower (1.14.0 instead of 2.2.0). So all I had to do was using
model.fit_generator()
instead of
model.fit()
before saving it. And it works
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.