how to extract output of a layer of model to numpy array

Question

def build(width, height, depth, classes, weightsPath=None):
        # initialize the model
        model = Sequential()
        model.add(Conv2D(100, (5, 5), padding="same",input_shape=(depth, height, width), data_format="channels_first"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2),data_format="channels_first"))

        model.add(Conv2D(100, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), data_format="channels_first"))

        # 3 set of CONV => RELU => POOL
        model.add(Conv2D(100, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2),data_format="channels_first"))

        # 4 set of CONV => RELU => POOL
        model.add(Conv2D(50, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2),data_format="channels_first"))

        # 5 set of CONV => RELU => POOL
        model.add(Conv2D(50, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), data_format="channels_first"))

        # 6 set of CONV => RELU => POOL
        model.add(Conv2D(50, (5, 5), padding="same"))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), data_format="channels_first"))

        # set of FC => RELU layers
        model.add(Flatten())
        #model.add(Dense(classes))
        #model.add(Activation("relu"))

        # softmax classifier
        model.add(Dense(classes))
        model.add(Activation("softmax"))

        return model
test_model = build(width=200, height=200, depth=1, classes=100) 
epochs=50
batch_size=128
cnn_model.compile(optimizer='Adam', loss='mse')
history = test_model.fit(X_train, y_train,validation_data=[X_valid,y_valid],epochs=epochs,batch_size=batch_size,
                   verbose=1)

I want to extract the output of the intermediate layer which is provided below as numpy array and want to save it to a text file

The output of the layer I want to extract is

# 6 set of CONV => RELU => POOL

model.add(Conv2D(50, (5, 5), padding="same"))

I tried links from here Keras, How to get the output of each layer?

However i am unable to incorporate the solution provided in link to my problem. I hope experts may help me overcoming this problem.

I have updated my answer to save the numpy arrays to file. Please take a look. — MSS
– MSS, Commented Jan 11, 2023 at 9:02

MSS · Accepted Answer · 2023-01-11 08:58:10Z

1

You can do it in this way:

from tensorflow.keras.models import Model
cnn_model = build(...) # build your model by invoking your function
     ...
 # train your model
layer_idx = 6
# Indices are based on order of horizontal graph traversal (bottom-up).
layer_to_interpret = cnn_model.get_layer(index=layer_idx)
# You can also use the name of layer to get it.
# layer_to_interpret = cnn_model.get_layer(layer_name)
# Create multi-output model
multiout_model = Model(inputs=cnn_model.inputs, outputs=[layer_to_interpret.output, cnn_model.output])

conv_outs, predictions = multiout_model(images)
# save conv_outs to a file 
conv_outs.numpy().save("conv_output.npy")
# np.savetxt("foo.csv", conv_outs, delimiter=",")

edited Jan 11, 2023 at 8:58

answered Jan 10, 2023 at 10:11

MSS

3,6932 gold badges28 silver badges57 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

learner Over a year ago

Can you please explain why using with tf.GradientTape() for calling multiout_model? If cnn_model is already trained there is no need for tf.GradientTape. In the other scenario that cnn_model is not trained, and the outputs need to be saved while the network is being trained, there are other steps to be included in the code for training the network.

MSS Over a year ago

Yes you are correct. If model is already trained, we dont need to use tf.GradientTape

Timbus Calin · Accepted Answer · 2023-01-10 13:50:37Z

0

Note that the Sequential constructor accepts a name argument, so to make things easy and unambiguous, add name feature to the layer you want to extract its output :

# 6 set of CONV => RELU => POOL

model.add(Conv2D(50, (5, 5), padding="same", name="my_intermediate_layer"))

# to extract output :
outputs=model.get_layer(name="my_intermediate_layer").output

edited Jan 10, 2023 at 13:50

Timbus Calin

15.2k6 gold badges49 silver badges69 bronze badges

answered Jan 10, 2023 at 8:44

Yassine

12 bronze badges

3 Comments

pro Over a year ago

How to save it to numpy array

Yassine Over a year ago

the output will be a 4D tensor : batch_shape + (filters, new_rows, new_cols), so it's already a 4D numpy array. if you want : outputs = np.array(outputs)

Alberto Over a year ago

please give a look at how to answer here on SO, because your answer is very badly formatted.

Collectives™ on Stack Overflow

how to extract output of a layer of model to numpy array

2 Answers 2

2 Comments

3 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

3 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related