python - How To Train Regression Model With multiple 3D Array?

Question

I want to train my regression model with 3D array? how can I do it in Python? can you please guide me. Actually I want to predict regression value from giving input of multiple 3D arrays. Is it possible to predict just single float number from multiple 3d arrays?. Thanks

train.model((x1,x2,x3..xN), y-value).

where x1,x2,..xN are 3D array. and Y is output just single float number.

question from:https://stackoverflow.com/questions/65935261/how-to-train-regression-model-with-multiple-3d-array

Answer 1

The key point is to reshape your 3D samples to flat 1D samples. The following example code uses tf.reshape to reshape input before feeding to a regular dense network for regression to a single value output by tf.identity (no activation).

%tensorflow_version 2.x
%reset -f

import tensorflow as tf
from   tensorflow.keras import *
from   tensorflow.keras.models import *
from   tensorflow.keras.layers import *
from   tensorflow.keras.callbacks import *

class regression_model(Model):
    def __init__(self):
        super(regression_model,self).__init__()
        self.dense1 = Dense(units=300, activation=tf.keras.activations.relu)
        self.dense2 = Dense(units=200, activation=tf.keras.activations.relu)
        self.dense3 = Dense(units=1,   activation=tf.identity)

    @tf.function
    def call(self,x):
        h1 = self.dense1(x)
        h2 = self.dense2(h1)
        u  = self.dense3(h2) # Output
        return u

if __name__=="__main__":
    inp = [[[1],[2],[3],[4]], [[3],[3],[3],[3]]] # 2 samples of whatever shape
    exp = [[10],              [12]] # Regress to sums for example'

    inp = tf.constant(inp,dtype=tf.float32)
    exp = tf.constant(exp,dtype=tf.float32)

    NUM_SAMPLES = 2
    NUM_VALUES_IN_1SAMPLE = 4
    inp = tf.reshape(inp,(NUM_SAMPLES,NUM_VALUES_IN_1SAMPLE))

    model = regression_model()
    model.compile(loss=tf.losses.MeanSquaredError(),
                  optimizer=tf.optimizers.Adam(1e-3))
    
    model.fit(x=inp,y=exp, batch_size=len(inp), epochs=100)

    print(f"
Prediction from {inp}, will be:")
    print(model.predict(x=inp, batch_size=len(inp), steps=1))
# EOF