import tensorflow as tf import numpy as np # Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3 x_data = np.random.rand(100).astype(np.float32) y_data = x_data * 0.1 + 0.3 # Try to find values for W and b that compute y_data = W * x_data + b # (We know that W should be 0.1 and b 0.3, but TensorFlow will # figure that out for us.) W = tf.Variable(tf.random_uniform([1], -1.0, 1.0)) b = tf.Variable(tf.zeros([1])) y = W * x_data + b # Minimize the mean squared errors. loss = tf.reduce_mean(tf.square(y - y_data)) optimizer = tf.train.GradientDescentOptimizer(0.5) train = optimizer.minimize(loss) # Before starting, initialize the variables. We will 'run' this first. init = tf.initialize_all_variables() # Launch the graph. sess = tf.Session() sess.run(init) # Fit the line. for step in range(201): sess.run(train) if step % 20 == 0: print(step, sess.run(W), sess.run(b)) # Learns best fit is W: [0.1], b: [0.3]# your code goes here
import random import time import tensorflow as tf from tensorflow import keras # list of possible colors colors = ["red", "green", "violet"] # create an empty list to store the data data = [] # function to gather data from user def gather_data(): color = input("Enter a color (red, green, or violet): ") number = input("Enter a number (0-9): ") data.append((color, number)) # function to train the model on the gathered data def train_model(): # convert the data to a numpy array data_np = np.array(data) # split the data into input (X) and output (y) X = data_np[:, 0] y = data_np[:, 1] # one-hot encode the input data X = tf.keras.utils.to_categorical(X) # create a model model = keras.Sequential([ keras.layers.Dense(64, input_shape=(3,), activation='relu'), keras.layers.Dense(32, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) model.compile(optimizer='adam', loss='categ
(0, array([0.8336869], dtype=float32), array([-0.10020426], dtype=float32)) (20, array([0.30165207], dtype=float32), array([0.19833234], dtype=float32)) (40, array([0.15451856], dtype=float32), array([0.27251318], dtype=float32)) (60, array([0.11473963], dtype=float32), array([0.29256868], dtype=float32)) (80, array([0.10398501], dtype=float32), array([0.2979909], dtype=float32)) (100, array([0.10107742], dtype=float32), array([0.2994568], dtype=float32)) (120, array([0.10029128], dtype=float32), array([0.29985315], dtype=float32)) (140, array([0.10007876], dtype=float32), array([0.29996032], dtype=float32)) (160, array([0.10002132], dtype=float32), array([0.29998925], dtype=float32)) (180, array([0.10000577], dtype=float32), array([0.2999971], dtype=float32)) (200, array([0.10000156], dtype=float32), array([0.29999924], dtype=float32))
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/util/tf_should_use.py:193: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. Instructions for updating: Use `tf.global_variables_initializer` instead.