i want to save my trained model to .h5 without last two layers, in order to transfer learning using my custom model in the furture, just like MobileNetV2 include_top=False, can someone help me, thanks!
base_model = tf.keras.applications.mobilenet_v2.MobileNetV2(
alpha=1.0,
input_shape=IMG_SHAPE,
include_top=False,
weights='imagenet')
model = tf.keras.Sequential([
base_model,
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dense(255, activation=tf.nn.softmax)
])
trained model like this:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
mobilenetv2_1.00_224 (Model) (None, 2, 2, 1280) 2257984
_________________________________________________________________
global_average_pooling2d (Gl (None, 1280) 0
_________________________________________________________________
dense (Dense) (None, 205) 262605
=================================================================
Total params: 2,520,589
Trainable params: 2,486,477
Non-trainable params: 34,112
_________________________________________________________________
when i try to using it for transfer learning
keras_model = loadModel(keras_model_path)
keras_model.summary()
input = keras_model.input
hidden = tf.keras.layers.GlobalMaxPooling2D()(keras_model.layers[-3].output)
out = tf.keras.layers.Dense(128, activation=tf.nn.softmax)(hidden)
model2 = tf.keras.Model(input, out)
model2.summary()
an error occurs
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, 64, 64, 3), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []
i want to save my trained model to .h5 without last two layers,
why don't you save the full model with model.save() and when you reload it for transfer learning, just remove the layers using:
model.layers.pop()
You can also remove the layers before saving the model but I wouldn't do that
Related
I have a trained EfficientNetB0-based model with saved weights in a H5 format.
I want to add some preprocessing layers before the model, load the weights, and retrain it.
If I create a model like this:
inp = tf.keras.layers.Input(shape=[224,224,3])
noise = tf.keras.layers.GaussianNoise(stddev=10.)(inp)
feature_extractor = tf.keras.applications.EfficientNetB0(include_top=False, pooling="max")
features = feature_extractor(noise)
output1 = tf.keras.layers.Dense(100, activation="sigmoid")(features)
output2 = tf.keras.layers.Dense(10, activation="softmax")(output1)
model = tf.keras.models.Model(inp, [output1, output2])
I get this summary:
Layer (type) Output Shape Param #
=================================================================
input_27 (InputLayer) [(None, 224, 224, 3)] 0
_________________________________________________________________
gaussian_noise_13 (GaussianN (None, 224, 224, 3) 0
_________________________________________________________________
efficientnetb0 (Functional) (None, 1280) 4049571
_________________________________________________________________
dense (Dense) (None, 100) 128100
_________________________________________________________________
dense_1 (Dense) (None, 10) 1010
and I lose access to intermediate layers. I can't use the tf.keras.Sequential approach because my model has two outputs.
I want to retain the layer names inside EfficientNetB0 so that I can reload my weights. How do I do that?
So it looks like for the toy example I created above the answer is:
inp = tf.keras.layers.Input(shape=[224,224,3])
noise = tf.keras.layers.GaussianNoise(stddev=10.)(inp)
feature_extractor = tf.keras.applications.EfficientNetB0(input_tensor=noise, include_top=False, pooling="max")
output1 = tf.keras.layers.Dense(100, activation="sigmoid")(feature_extractor.output)
output2 = tf.keras.layers.Dense(10, activation="softmax")(output1)
model = tf.keras.models.Model(inp, [output1, output2])
However, I'm actually working with a custom model class that doesn't have that argument in the constructor...
Without the input_tensor argument is there another way to do this?
I'm using tensorflow 2.6 keras for transfer learning. Currently I take MobileNetV2. I take input, apply some preprocessing using Lambda layer, then feed this preprocessed input to MobileNetV2, then add Dense layer and train this thing. Training, inference etc actually work as expected.
However, the summary of the model looks as follows:
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) [(None, 201, 189, 1)] 0
_________________________________________________________________
lambda (Lambda) (None, 201, 189, None) 0
_________________________________________________________________
lambda_1 (Lambda) (None, 201, 189, None) 0
_________________________________________________________________
mobilenetv2_1.00_224 (Functi (None, 7, 6, 1280) 2257984
_________________________________________________________________
flatten (Flatten) (None, 53760) 0
_________________________________________________________________
output (Dense) (None, 2) 107522
=================================================================
Total params: 2,365,506
Trainable params: 2,331,394
Non-trainable params: 34,112
So the MobileNetV2 structure is hidden and shown as one layer of type tensorflow.python.keras.engine.functional.Functional. If I print summary of this layer, I get all the internal layers of the model. I have a script for automatic GradCam visualizations which looks for the last Conv layer of the model. If the model is constructed by hand using Lambda, Conv2D, Dense layers, then everyhting works fine. If I use pretrained model, then currently it fails, because the Conv layer is hidden inside of this Functional layer.
How do I construct my modified MobileNetV2 model with my additional layers so that the full structure of the model is shown?
This is how I approximately construct my final model:
input = Input(shape=params.image_shape, name="input")
flow = input
flow = input_correction(flow, params) #some Lambda layers
keras_model = MobileNetV2(
input_shape=image_shape,
weights='imagenet',
include_top=False)
keras_model_output=keras_model(flow)
keras_model_input=input
keras_model_output = Flatten()(keras_model_output)
output = Dense(units=len(params.classes),
activation=tf.nn.softmax,
name="output")(keras_model_output)
model = Model(inputs=keras_model_input, outputs=output)
model.compile(...)
In default, summary doesnt show nested models. Just include expand_nested argument in the summary.
model.summary(expand_nested=True)
so I'm currently having an issue that every time I predict my loaded model, my Jupyter Notebook's kernel shut down.
So I was given this Keras model that has this model summary:
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 100) 200
_________________________________________________________________
re_lu_1 (ReLU) (None, 100) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 100) 0
_________________________________________________________________
dense_2 (Dense) (None, 50) 5050
_________________________________________________________________
re_lu_2 (ReLU) (None, 50) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 50) 0
_________________________________________________________________
dense_3 (Dense) (None, 1) 51
=================================================================
Total params: 5,301
Trainable params: 5,301
Non-trainable params: 0
I was planning to save this model using this method that I got online. I saved the entire model. Then, I tried to load the saved model onto a different notebook. Done dimension/shape adjustment and I started noticing that every time I did model.predict(), my kernel shuts and gave no error massages. So I started to do this backwards, which is trying to predict on the original notebook, where the model was trained. And I found no error. My hypothesis is:
There's nothing wrong with the model. Because this it can predict one data. Anything greater than that, it'll crush.
The problem came from saving and loading the model
This is my code for saving and loading my model
MODEL ORIGIN NOTEBOOK
Has anyone ever encountered the same problem? The below code is my code:
#Model architecture
#Model ANN
model = Sequential()
model.add(Dense(100, input_shape=(1,)))
model.add(ReLU())
model.add(Dropout(.5))
model.add(Dense(50))
model.add(ReLU())
model.add(Dropout(.5))
model.add(Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
model.fit(X_train, y_train, epochs=1000, batch_size=100, validation_data=(X_valid, y_valid))
# ATTEMPT 1 save the model to disk
filename = 'model_pake_pickle_bener.sav'
pickle.dump(model, open(filename, 'wb'))
DIFFERENT NOTEBOOK
This is where things gone wrong
#Load the saved model
filename = 'model_pake_pickle_bener.sav'
loaded_model = pickle.load(open(filename, 'rb'))
#reduce number of data used
bersih = bessp[:2]
#Introducing our dataset to tf (Voltage only)
X = bersih['Voltage_y'].values
y = bersih['SOC'].values
#Reshaping
X = X.reshape(X.shape[0], 1)
y = y.reshape(y.shape[0], 1)
#Adjustment
X = np.asarray(X).astype('float32')
y = loaded_model.predict(X)
I've tried using h5 file and it ended up the same as the others.
Have you tried saving and loading the model with the direct object methods? I noticed that you use pickle, but it's recommended to use (taken from the documentation):
model = ... # Get model (Sequential, Functional Model, or Model subclass)
model.save('path/to/location')
To load the model in your second notebook:
from tensorflow import keras
model = keras.models.load_model('path/to/location')
I have a U-net network with VGG16 encoder architecture with pre-trained imagenet weights. Since my input images are grayscale, I added in a convolutional layer with depth 3 prior to sending the input to the U-net model.
Now, I'm trying to get the output of an intermediate layer within the U-net network. I create an intermediate model whose output is the output of the layer that I'm interested in. Here is my code:
base_model = sm.Unet('vgg16', encoder_weights='imagenet', classes=1, activation='sigmoid')
inp = Input(shape=(448, 224, 1))
l1 = Conv2D(3, (1,1))(inp)
out = base_model(l1)
model = Model(inp, out)
model.summary()
intermediate_layer_model = Model(inputs=model.layers[0].input,
outputs=model.get_layer('model_1').get_layer('center_block2_relu').output)
Here is the output:
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) (None, 448, 224, 1) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 448, 224, 3) 6
_________________________________________________________________
model_1 (Model) multiple 23752273
=================================================================
Total params: 23,752,279
Trainable params: 23,748,247
Non-trainable params: 4,032
_________________________________________________________________
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, ?, ?, 3), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []
It seems to me that there is an issue with the U-net model having an input layer (input_1) and I'm not supplying this information during the construction of intermediate_layer_model. However, I expect that the intermediate model to take only the grayscale images as input and not require an additional 3-channel input.
Any help would be appreciated.
I am trying to develop a siamese network for simple face verification (and recognition in the second stage). I have a network in place that I managed to train but I am a bit puzzled when it comes to how to save and restore the model + making predictions with the trained model. Hoping that maybe an experienced person in the domain can help to make progress..
Here is how I create my siamese network, to begin with...
model = ResNet50(weights='imagenet') # get the original ResNet50 model
model.layers.pop() # Remove the last layer
for layer in model.layers:
layer.trainable = False # do not train any of original layers
x = model.get_layer('flatten_1').output
model_out = Dense(128, activation='relu', name='model_out')(x)
model_out = Lambda(lambda x: K.l2_normalize(x,axis=-1))(model_out)
new_model = Model(inputs=model.input, outputs=model_out)
# At this point, a new layer (with 128 units) added and normalization applied.
# Now create siamese network on top of this
anchor_in = Input(shape=(224, 224, 3))
positive_in = Input(shape=(224, 224, 3))
negative_in = Input(shape=(224, 224, 3))
anchor_out = new_model(anchor_in)
positive_out = new_model(positive_in)
negative_out = new_model(negative_in)
merged_vector = concatenate([anchor_out, positive_out, negative_out], axis=-1)
# Define the trainable model
siamese_model = Model(inputs=[anchor_in, positive_in, negative_in],
outputs=merged_vector)
siamese_model.compile(optimizer=Adam(lr=.0001),
loss=triplet_loss,
metrics=[dist_between_anchor_positive,
dist_between_anchor_negative])
And I train the siamese_model. When I train it, if I interpret results right, it is not really training the underlying model, it just trains the new siamese network (essentially, just the last layer is trained).
But this model has 3 input streams. After the training, I need to save this model in a way so that it just takes 1 or 2 inputs so that I can perform predictions by calculating the distance between 2 given images. How do I save this model and reuse it now?
Thank you in advance!
ADDENDUM:
In case you wonder, here is the summary of siamese model.
siamese_model.summary()
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_2 (InputLayer) (None, 224, 224, 3) 0
__________________________________________________________________________________________________
input_3 (InputLayer) (None, 224, 224, 3) 0
__________________________________________________________________________________________________
input_4 (InputLayer) (None, 224, 224, 3) 0
__________________________________________________________________________________________________
model_1 (Model) (None, 128) 23849984 input_2[0][0]
input_3[0][0]
input_4[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 384) 0 model_1[1][0]
model_1[2][0]
model_1[3][0]
==================================================================================================
Total params: 23,849,984
Trainable params: 262,272
Non-trainable params: 23,587,712
__________________________________________________________________________________________________
You can use below code to save your model
siamese_model.save_weights(MODEL_WEIGHTS_FILE)
And then to load your model you need to use
siamese_model.load_weights(MODEL_WEIGHTS_FILE)
Thanks