2

I have an ubermodel that uses a submodel as a layer for feature extraction. My code is modular such that I can easily switch which submodel I'm using to perform feature extraction simply by changing whichever submodel I assign:

...

elif FEATURE_EXTRACTOR == "VGG16":

    Features = keras.applications.VGG16(

        weights = "imagenet",
        pooling = FEATURE_POOLING,
        include_top = False

    )
elif FEATURE_EXTRACTOR == "EfficientNetB0":

    Features = keras_applications_master.keras_applications.efficientnet.EfficientNetB0(
    # ^ Local copy of official keras repo: https://github.com/keras-team/keras-applications
    # because pip install --upgrade keras doesn't install version with efficientnet.

        weights = "imagenet",
        include_top = False,
        pooling = FEATURE_POOLING,
        classes = None

    )

...

My routines for saving and loading the ubermodel and its weights are also aware of which submodel is being used for feature extraction:

model.load_weights(submodel_specific_path)

With any submodel, I can perform the initial training run and save the ubermodel to disk. And if I try to continue training or fine tune any ubermodel containing a VGG16 submodel, using load_weights to load the weights, everything works fine. But when I load_weights any ubermodel with an efficientnet submodel (or, say, keras.applications.xception.Xception), I get the following error:

Traceback (most recent call last):
  File "image_model.py", line 284, in <module>
    model.load_weights(model_path)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\saving.py", line 492, in load_wrapper
    return load_function(*args, **kwargs)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\network.py", line 1227, in load_weights
    reshape=reshape)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\saving.py", line 1294, in load_weights_from_hdf5_group_by_name
    reshape=reshape)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\saving.py", line 861, in preprocess_weights_for_loading
    weights = convert_nested_model(weights)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\saving.py", line 836, in convert_nested_model
    original_backend=original_backend))
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\keras\engine\saving.py", line 980, in preprocess_weights_for_loading
    weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
  File "<__array_function__ internals>", line 6, in transpose
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\numpy\core\fromnumeric.py", line 651, in transpose
    return _wrapfunc(a, 'transpose', axes)
  File "C:\Users\Username\Anaconda3\envs\tensorflow1\lib\site-packages\numpy\core\fromnumeric.py", line 61, in _wrapfunc
    return bound(*args, **kwds)
ValueError: axes don't match array

What am I doing wrong?

Nickolas
  • 111
  • 1
  • 4

1 Answers1

0

I wasn't able to recreate your issue, but I found this Github Issue, that says this issue occurs when we use multi GPU model. So the trick should be:

multi_gpu_model = multi_gpu_model(model, gpus=G)
model.save_model(...)

Instead of

multi_gpu_model = multi_gpu_model(model, gpus=G)
multi_gpu_model.save_model(...)

Being said that, I was able to successfully create the EfficientNetB0 model, evaluate the model, save the model and finally load the model.

Code to Build, Evaluate and Save the model using model.save -

%tensorflow_version 1.x
import keras
from keras.models import Model
from keras.layers import GlobalAveragePooling2D, Dense, Flatten
from keras_efficientnets import EfficientNetB0

model = EfficientNetB0(input_shape=(224, 224, 3), classes=1000, include_top=False, weights='imagenet')

x = model.output
x = GlobalAveragePooling2D()(x)
x = Dense(20, activation='relu')(x)
x = Dense(17, activation='softmax')(x)
model = Model(inputs = model.input, outputs = x)

# summarize model
#model.summary()

# (2) Get Data
import tflearn.datasets.oxflower17 as oxflower17
x, y = oxflower17.load_data(one_hot=True)

# (4) Compile 
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(x, y, batch_size=64, epochs= 1, verbose=1, validation_split=0.2, shuffle=True)

# evaluate the model
scores = model.evaluate(x, y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

# save model and architecture to single file
model.save("model.h5py")
print("Saved model to disk")

Output - 

TensorFlow 1.x selected.
Using TensorFlow backend.
WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/helpers/summarizer.py:9: The name tf.summary.merge is deprecated. Please use tf.compat.v1.summary.merge instead.

WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/helpers/trainer.py:25: The name tf.summary.FileWriter is deprecated. Please use tf.compat.v1.summary.FileWriter instead.

WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/collections.py:13: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/config.py:123: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.

WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/config.py:129: The name tf.add_to_collection is deprecated. Please use tf.compat.v1.add_to_collection instead.

WARNING:tensorflow:From /tensorflow-1.15.2/python3.6/tflearn/config.py:131: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.

Downloading Oxford 17 category Flower Dataset, Please wait...
100.0% 60276736 / 60270631
('Succesfully downloaded', '17flowers.tgz', 60270631, 'bytes.')
File Extracted
Starting to parse images...
Parsing Done!
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.

WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:431: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.

WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:438: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.

Train on 1088 samples, validate on 272 samples
Epoch 1/1
1088/1088 [==============================] - 203s 187ms/step - loss: 1.6433 - accuracy: 0.5561 - val_loss: 1.9315 - val_accuracy: 0.5074
accuracy: 54.85%

Load the model using load_model and Evaluate -

%tensorflow_version 1.x
# load and evaluate a saved model
from numpy import loadtxt
from keras.models import load_model

# load model
model = load_model('model.h5py')

# summarize model
#model.summary()

# (2) Get Data
import tflearn.datasets.oxflower17 as oxflower17
x, y = oxflower17.load_data(one_hot=True)

# evaluate the model
score = model.evaluate(x, y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], score[1]*100))

Output - Accuracy of the model before saving and after loading should match and it does here. 

accuracy: 54.85%

Save the model using model.save_weights and Load the model using model.load_weights -

from keras.models import model_from_json

# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("model.h5")
print("Saved model to disk")

# later...

# load json and create model
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("model.h5")
print("Loaded model from disk")

# evaluate loaded model on test data
loaded_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
score = loaded_model.evaluate(x, y, verbose=0)
print("%s: %.2f%%" % (loaded_model.metrics_names[1], score[1]*100))

Output -

Saved model to disk
Loaded model from disk
accuracy: 54.85%

Hope this answers your question. Happy Learning.