I am not able to import resnet from keras.applications module - tensorflow

Question

I'm unable to import this module
import keras.applications.resnet
ModuleNotFoundError
in ()
----> 1 import keras.applications.resnet
ModuleNotFoundError: No module named 'keras.applications.resnet'
keras resnet link

Answer 1

Keras team hasn't included resnet, resnet_v2 and resnext in the current module, they will be added from Keras 2.2.5, as mentioned here.
For a workaround, you can use keras_applications module directly to import all ResNet, ResNetV2 and ResNeXt models, as given below
from keras_applications.resnet import ResNet50
Or if you just want to use ResNet50
from keras.applications.resnet50 import ResNet50
Alternatively, you can always build from source as mentioned here.

Answer 2

try to use
from tensorflow.keras.applications.resnet50 import ResNet50

Answer 3

Found a workaround to use ResNeXt in Keras 2.2.4 here.
ResNeXt50() function needs 4 more arguments: backend, layers, models and utils.
import keras
from keras_applications.resnext import ResNeXt50
model = ResNeXt50(weights='imagenet',
backend=keras.backend,
layers=keras.layers,
models=keras.models,
utils=keras.utils)

Answer 4

In Keras there are multiple flavours of ResNet, you will have to specify the version of ResNet that you want e.g. You wish to load the ResNet50.
Use
from keras.applications import ResNet50
Edit 2 This is the list you get when you use dir() command on applications
['DenseNet121', 'DenseNet169', 'DenseNet201', 'InceptionResNetV2', 'InceptionV3', 'MobileNet', 'MobileNetV2', 'NASNetLarge', 'NASNetMobile', 'ResNet50', 'VGG16', 'VGG19', 'Xception', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__path__', '__spec__', 'absolute_import', 'backend', 'densenet', 'division', 'inception_resnet_v2', 'inception_v3', 'keras_applications', 'keras_modules_injection', 'layers', 'mobilenet', 'mobilenet_v2', 'models', 'nasnet', 'print_function', 'resnet50', 'utils', 'vgg16', 'vgg19', 'xception'], the models visible here can be laoded like this, There are some models like ResNet101 missing here, let me see if I can come up with a way to fix this.
Edit Proof that this works too
To see all the available versions of the Resnet models, visit https://keras.io/applications/#resnet

Answer 5

There is a python package named 'keras-resnet' which has ResNet50, ResNet101, ResNet152 and many more variants of ResNet. (https://pypi.org/project/keras-resnet/)
Installation is also quite easy. Just type
pip install keras-resnet
It will install this module and then use it like:
from keras_resnet.models import ResNet50, ResNet101, ResNet152
backbone = ResNet50(inputs=image_input, include_top=False, freeze_bn=True)
C2, C3, C4, C5 = backbone.outputs # this will give you intermediate
# outputs of four blocks of resnet if you want to merge low and high level features
I am using backbones from this module and is working fine for me!

Answer 6

Check the versions:
pip list | grep Keras
If it's already installed, uninstall and upgrade:
pip uninstall Keras
pip install Keras==2.3.1
pip uninstall Keras-Applications
pip install Keras-Applications==1.0.8
pip uninstall Keras-Preprocessing
pip install Keras-Preprocessing==1.1.0

Answer 7

from keras.applications.resnet
import ResNet101
tf.keras.backend.clear_session
model=VGG19()
model.summary()
tf.keras.utils.plot_model(model,show_shapes=True)
visualkeras.layered_view(model,legend=True)

Answer 8

Before running
tensorflow.keras.applications.resnet50 import ResNet50
you need to run
from tensorflow import keras