What is Deep Learning?¶

Deep learning is a subset of machine learning that uses artificial neural networks to automatically learn patterns from large amounts of data. It is particularly useful for detecting complex relationships between inputs and outputs because it can model hierarchical and non-linear dependencies through multiple layers of neurons.

Tensorflow¶

An open-source deep learning framework developed by Google that provides tools for building, training, and deploying neural networks efficiently, often using GPUs or TPUs for acceleration.

Keras¶

A high-level API running on top of TensorFlow that simplifies building and training deep learning models with an intuitive and modular design.

Build a simple Neural Network¶

In [1]:
import tensorflow as tf   # Importing the tensorflow library
import numpy as np  # Importing numpy for numerical operations

Let's create our own data in order to understand the working structure of neural networks in a much better sense -

In [2]:
xs = np.array([-1.0, 0.0, 1.0, 2.0, 3.0, 4.0], dtype=float)
ys = np.array([-3.0, -1.0, 1.0, 3.0, 5.0, 7.0], dtype=float)

Now we will build the simplest model possible with one single layer and one single neuron. We will use Keras SEQUENTIAL class using which we can define network as a sequence of LAYERS. A single DENSE LAYER can be used to build the network.

In [3]:
model = tf.keras.models.Sequential([
    tf.keras.Input(shape=(1,)),   # This defines the input shape of the incoming data. This is not a layer
    tf.keras.layers.Dense(units=1) # This is the first layer and has got 1 neuron defined by units=1
]
)

You have your model architecture build now, with 1 layer and 1 neuron. Now you have to compile the network and for this you need to specify two functions - loss and optimizer. For loss - we will use mean square error and for optimizer we will use stochastic gradient descent.

In [4]:
model.compile(optimizer='sgd', loss='mean_squared_error')
In [5]:
model.summary()

Model: "sequential"

┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ dense (Dense)                        │ (None, 1)                   │               2 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘

 Total params: 2 (8.00 B)

 Trainable params: 2 (8.00 B)

 Non-trainable params: 0 (0.00 B)

The above gives the model summary that is the final model you have with you, using which you will start the training. Let's see what these three column means -

  1. Layer (type): indicates that the layer is a Dense (fully connected) layer. A Dense layer means that every neuron in the layer is connected to every neuron in the previous layer.
  2. Output Shape: (None, 1) -
    • None: represents the batch size, which is unspecified at this point. The batch size will be determined when you input data into the model.
    • 1: indicates that the layer has a single output unit (neuron).
  3. Param #: 2 - This is the total number of trainable parameters in the layer. In a Dense layer, the parameters include weights and biases.
    • Weights: There is one weight for each connection between neurons in the previous layer and neurons in the current layer. If the previous layer has one neuron, there will be 1 weight.
    • Bias: Each neuron in the Dense layer has one bias parameter.
    • In this case, the layer has: 1 weight (from the single neuron in the previous layer to the single neuron in this layer). 1 bias. So 1+1=2 parameters.

Now is the time to train the model - where it learns the relationship between x and y and is done using the fit() method of the model object.

In [6]:
model.fit(xs, ys, epochs = 500)  
#epochs means that it will loop for 500 times

Epoch 1/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 2s 2s/step - loss: 12.5066
Epoch 2/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 57ms/step - loss: 10.0657
Epoch 3/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 8.1406
Epoch 4/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 6.6215
Epoch 5/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 5.4219
Epoch 6/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 4.4738
Epoch 7/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 3.7235
Epoch 8/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 3.1291
Epoch 9/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 2.6573
Epoch 10/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 2.2821
Epoch 11/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 1.9830
Epoch 12/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 1.7438
Epoch 13/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 1.5519
Epoch 14/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 1.3972
Epoch 15/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 1.2718
Epoch 16/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 1.1697
Epoch 17/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 1.0858
Epoch 18/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 1.0165
Epoch 19/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.9586
Epoch 20/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.9098
Epoch 21/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.8681
Epoch 22/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.8323
Epoch 23/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.8010
Epoch 24/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.7734
Epoch 25/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.7487
Epoch 26/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.7264
Epoch 27/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.7061
Epoch 28/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.6873
Epoch 29/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.6698
Epoch 30/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.6534
Epoch 31/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.6379
Epoch 32/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.6232
Epoch 33/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.6091
Epoch 34/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.5956
Epoch 35/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.5825
Epoch 36/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.5699
Epoch 37/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.5577
Epoch 38/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.5459
Epoch 39/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.5344
Epoch 40/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.5231
Epoch 41/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.5122
Epoch 42/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.5015
Epoch 43/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.4911
Epoch 44/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.4809
Epoch 45/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.4710
Epoch 46/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.4613
Epoch 47/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.4517
Epoch 48/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.4424
Epoch 49/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.4333
Epoch 50/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.4244
Epoch 51/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.4157
Epoch 52/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.4071
Epoch 53/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 53ms/step - loss: 0.3987
Epoch 54/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 51ms/step - loss: 0.3905
Epoch 55/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.3825
Epoch 56/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.3746
Epoch 57/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.3669
Epoch 58/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.3594
Epoch 59/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.3520
Epoch 60/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.3448
Epoch 61/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.3377
Epoch 62/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.3308
Epoch 63/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.3240
Epoch 64/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.3173
Epoch 65/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.3108
Epoch 66/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.3044
Epoch 67/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.2982
Epoch 68/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.2920
Epoch 69/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.2860
Epoch 70/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.2802
Epoch 71/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.2744
Epoch 72/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.2688
Epoch 73/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.2632
Epoch 74/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.2578
Epoch 75/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.2525
Epoch 76/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.2474
Epoch 77/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.2423
Epoch 78/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.2373
Epoch 79/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.2324
Epoch 80/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.2276
Epoch 81/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.2230
Epoch 82/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.2184
Epoch 83/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.2139
Epoch 84/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 0.2095
Epoch 85/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.2052
Epoch 86/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.2010
Epoch 87/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.1969
Epoch 88/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.1928
Epoch 89/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.1889
Epoch 90/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 66ms/step - loss: 0.1850
Epoch 91/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.1812
Epoch 92/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.1775
Epoch 93/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.1738
Epoch 94/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.1702
Epoch 95/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 127ms/step - loss: 0.1667
Epoch 96/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 0.1633
Epoch 97/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 0.1600
Epoch 98/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 53ms/step - loss: 0.1567
Epoch 99/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.1535
Epoch 100/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.1503
Epoch 101/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.1472
Epoch 102/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 52ms/step - loss: 0.1442
Epoch 103/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.1412
Epoch 104/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.1383
Epoch 105/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 0.1355
Epoch 106/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.1327
Epoch 107/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.1300
Epoch 108/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 53ms/step - loss: 0.1273
Epoch 109/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.1247
Epoch 110/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.1221
Epoch 111/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.1196
Epoch 112/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.1172
Epoch 113/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.1148
Epoch 114/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 59ms/step - loss: 0.1124
Epoch 115/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 0.1101
Epoch 116/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.1078
Epoch 117/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.1056
Epoch 118/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.1035
Epoch 119/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.1013
Epoch 120/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 62ms/step - loss: 0.0992
Epoch 121/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0972
Epoch 122/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.0952
Epoch 123/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0933
Epoch 124/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0913
Epoch 125/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0895
Epoch 126/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0876
Epoch 127/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0858
Epoch 128/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0841
Epoch 129/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0823
Epoch 130/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0806
Epoch 131/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0790
Epoch 132/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0774
Epoch 133/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - loss: 0.0758
Epoch 134/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0742
Epoch 135/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.0727
Epoch 136/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0712
Epoch 137/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0697
Epoch 138/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0683
Epoch 139/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0669
Epoch 140/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0655
Epoch 141/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - loss: 0.0642
Epoch 142/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0629
Epoch 143/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0616
Epoch 144/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0603
Epoch 145/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0591
Epoch 146/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.0579
Epoch 147/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 58ms/step - loss: 0.0567
Epoch 148/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.0555
Epoch 149/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0544
Epoch 150/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0532
Epoch 151/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0522
Epoch 152/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0511
Epoch 153/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0500
Epoch 154/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0490
Epoch 155/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0480
Epoch 156/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0470
Epoch 157/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0460
Epoch 158/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - loss: 0.0451
Epoch 159/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0442
Epoch 160/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0433
Epoch 161/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0424
Epoch 162/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0415
Epoch 163/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0407
Epoch 164/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0398
Epoch 165/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0390
Epoch 166/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0382
Epoch 167/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0374
Epoch 168/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0366
Epoch 169/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0359
Epoch 170/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0352
Epoch 171/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0344
Epoch 172/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0337
Epoch 173/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0330
Epoch 174/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.0324
Epoch 175/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0317
Epoch 176/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - loss: 0.0310
Epoch 177/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0304
Epoch 178/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0298
Epoch 179/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0292
Epoch 180/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0286
Epoch 181/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0280
Epoch 182/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0274
Epoch 183/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0268
Epoch 184/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0263
Epoch 185/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0258
Epoch 186/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0252
Epoch 187/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0247
Epoch 188/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0242
Epoch 189/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0237
Epoch 190/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0232
Epoch 191/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0227
Epoch 192/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0223
Epoch 193/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0218
Epoch 194/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0214
Epoch 195/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0209
Epoch 196/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0205
Epoch 197/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0201
Epoch 198/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.0197
Epoch 199/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0193
Epoch 200/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0189
Epoch 201/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0185
Epoch 202/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 0.0181
Epoch 203/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0177
Epoch 204/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0174
Epoch 205/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.0170
Epoch 206/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - loss: 0.0167
Epoch 207/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0163
Epoch 208/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0160
Epoch 209/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0157
Epoch 210/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0153
Epoch 211/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0150
Epoch 212/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0147
Epoch 213/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0144
Epoch 214/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 0.0141
Epoch 215/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0138
Epoch 216/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0135
Epoch 217/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0133
Epoch 218/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0130
Epoch 219/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0127
Epoch 220/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0125
Epoch 221/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0122
Epoch 222/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 62ms/step - loss: 0.0119
Epoch 223/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0117
Epoch 224/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0115
Epoch 225/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0112
Epoch 226/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0110
Epoch 227/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0108
Epoch 228/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0106
Epoch 229/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0103
Epoch 230/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0101
Epoch 231/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0099
Epoch 232/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0097
Epoch 233/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0095
Epoch 234/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0093
Epoch 235/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0091
Epoch 236/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0089
Epoch 237/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0088
Epoch 238/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step - loss: 0.0086
Epoch 239/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0084
Epoch 240/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0082
Epoch 241/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0081
Epoch 242/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0079
Epoch 243/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0077
Epoch 244/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0076
Epoch 245/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0074
Epoch 246/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.0073
Epoch 247/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0071
Epoch 248/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0070
Epoch 249/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0068
Epoch 250/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.0067
Epoch 251/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0065
Epoch 252/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0064
Epoch 253/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0063
Epoch 254/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0062
Epoch 255/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0060
Epoch 256/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0059
Epoch 257/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0058
Epoch 258/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0057
Epoch 259/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0055
Epoch 260/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0054
Epoch 261/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 52ms/step - loss: 0.0053
Epoch 262/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 0.0052
Epoch 263/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0051
Epoch 264/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0050
Epoch 265/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0049
Epoch 266/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 0.0048
Epoch 267/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.0047
Epoch 268/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0046
Epoch 269/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0045
Epoch 270/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0044
Epoch 271/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0043
Epoch 272/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0042
Epoch 273/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0041
Epoch 274/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0041
Epoch 275/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0040
Epoch 276/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.0039
Epoch 277/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0038
Epoch 278/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0037
Epoch 279/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0037
Epoch 280/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.0036
Epoch 281/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0035
Epoch 282/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0034
Epoch 283/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0034
Epoch 284/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0033
Epoch 285/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 0.0032
Epoch 286/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0032
Epoch 287/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 0.0031
Epoch 288/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0030
Epoch 289/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0030
Epoch 290/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0029
Epoch 291/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 0.0029
Epoch 292/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0028
Epoch 293/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0027
Epoch 294/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0027
Epoch 295/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0026
Epoch 296/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0026
Epoch 297/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0025
Epoch 298/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 0.0025
Epoch 299/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0024
Epoch 300/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0024
Epoch 301/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0023
Epoch 302/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0023
Epoch 303/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0022
Epoch 304/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0022
Epoch 305/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 62ms/step - loss: 0.0021
Epoch 306/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0021
Epoch 307/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - loss: 0.0020
Epoch 308/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0020
Epoch 309/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 59ms/step - loss: 0.0020
Epoch 310/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0019
Epoch 311/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 58ms/step - loss: 0.0019
Epoch 312/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0018
Epoch 313/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0018
Epoch 314/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 0.0018
Epoch 315/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 0.0017
Epoch 316/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - loss: 0.0017
Epoch 317/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 0.0017
Epoch 318/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0016
Epoch 319/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 0.0016
Epoch 320/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0016
Epoch 321/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0015
Epoch 322/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0015
Epoch 323/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 0.0015
Epoch 324/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 0.0014
Epoch 325/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 0.0014
Epoch 326/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0014
Epoch 327/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0014
Epoch 328/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0013
Epoch 329/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 0.0013
Epoch 330/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 0.0013
Epoch 331/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 0.0012
Epoch 332/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0012
Epoch 333/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 0.0012
Epoch 334/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0012
Epoch 335/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0011
Epoch 336/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 0.0011
Epoch 337/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0011
Epoch 338/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0011
Epoch 339/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 0.0011
Epoch 340/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 0.0010
Epoch 341/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 0.0010
Epoch 342/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 9.9017e-04
Epoch 343/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 9.6983e-04
Epoch 344/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 51ms/step - loss: 9.4990e-04
Epoch 345/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 9.3040e-04
Epoch 346/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 9.1129e-04
Epoch 347/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 8.9257e-04
Epoch 348/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - loss: 8.7423e-04
Epoch 349/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 8.5627e-04
Epoch 350/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 8.3868e-04
Epoch 351/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 8.2146e-04
Epoch 352/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 55ms/step - loss: 8.0458e-04
Epoch 353/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 7.8806e-04
Epoch 354/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 7.7187e-04
Epoch 355/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 7.5602e-04
Epoch 356/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 7.4048e-04
Epoch 357/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 7.2528e-04
Epoch 358/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 7.1038e-04
Epoch 359/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 6.9579e-04
Epoch 360/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 6.8149e-04
Epoch 361/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 6.6750e-04
Epoch 362/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 6.5379e-04
Epoch 363/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 6.4036e-04
Epoch 364/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 6.2721e-04
Epoch 365/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 6.1432e-04
Epoch 366/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 6.0170e-04
Epoch 367/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 5.8934e-04
Epoch 368/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 5.7724e-04
Epoch 369/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 5.6538e-04
Epoch 370/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 5.5377e-04
Epoch 371/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 5.4239e-04
Epoch 372/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 5.3125e-04
Epoch 373/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 5.2034e-04
Epoch 374/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 5.0965e-04
Epoch 375/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 4.9918e-04
Epoch 376/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 4.8893e-04
Epoch 377/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 4.7889e-04
Epoch 378/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 4.6905e-04
Epoch 379/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 4.5941e-04
Epoch 380/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 4.4998e-04
Epoch 381/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 4.4074e-04
Epoch 382/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 4.3168e-04
Epoch 383/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - loss: 4.2281e-04
Epoch 384/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 4.1413e-04
Epoch 385/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 4.0562e-04
Epoch 386/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 3.9729e-04
Epoch 387/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 3.8913e-04
Epoch 388/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - loss: 3.8114e-04
Epoch 389/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 3.7331e-04
Epoch 390/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 3.6564e-04
Epoch 391/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 3.5813e-04
Epoch 392/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 3.5078e-04
Epoch 393/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 3.4357e-04
Epoch 394/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 3.3651e-04
Epoch 395/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 3.2960e-04
Epoch 396/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 3.2283e-04
Epoch 397/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 3.1620e-04
Epoch 398/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 3.0970e-04
Epoch 399/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 3.0334e-04
Epoch 400/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 2.9711e-04
Epoch 401/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 2.9101e-04
Epoch 402/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 2.8503e-04
Epoch 403/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 2.7918e-04
Epoch 404/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 2.7344e-04
Epoch 405/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - loss: 2.6782e-04
Epoch 406/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 2.6232e-04
Epoch 407/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 2.5693e-04
Epoch 408/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 2.5165e-04
Epoch 409/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 2.4648e-04
Epoch 410/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 2.4142e-04
Epoch 411/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 2.3646e-04
Epoch 412/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 2.3161e-04
Epoch 413/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 2.2685e-04
Epoch 414/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 2.2219e-04
Epoch 415/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 2.1763e-04
Epoch 416/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 2.1315e-04
Epoch 417/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - loss: 2.0878e-04
Epoch 418/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 2.0449e-04
Epoch 419/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 2.0029e-04
Epoch 420/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step - loss: 1.9617e-04
Epoch 421/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 1.9214e-04
Epoch 422/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 43ms/step - loss: 1.8820e-04
Epoch 423/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 1.8433e-04
Epoch 424/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 1.8054e-04
Epoch 425/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - loss: 1.7684e-04
Epoch 426/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 1.7320e-04
Epoch 427/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - loss: 1.6965e-04
Epoch 428/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 1.6616e-04
Epoch 429/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 1.6275e-04
Epoch 430/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 1.5940e-04
Epoch 431/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 1.5613e-04
Epoch 432/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 1.5292e-04
Epoch 433/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 1.4978e-04
Epoch 434/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 1.4670e-04
Epoch 435/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 1.4369e-04
Epoch 436/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - loss: 1.4074e-04
Epoch 437/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 1.3785e-04
Epoch 438/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 1.3502e-04
Epoch 439/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 1.3224e-04
Epoch 440/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 1.2953e-04
Epoch 441/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 1.2687e-04
Epoch 442/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 1.2426e-04
Epoch 443/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 1.2171e-04
Epoch 444/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 1.1921e-04
Epoch 445/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 1.1676e-04
Epoch 446/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 1.1436e-04
Epoch 447/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step - loss: 1.1201e-04
Epoch 448/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 1.0971e-04
Epoch 449/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 1.0746e-04
Epoch 450/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 1.0525e-04
Epoch 451/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 1.0309e-04
Epoch 452/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 1.0097e-04
Epoch 453/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 9.8897e-05
Epoch 454/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 9.6866e-05
Epoch 455/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step - loss: 9.4876e-05
Epoch 456/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 29ms/step - loss: 9.2928e-05
Epoch 457/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 9.1018e-05
Epoch 458/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 8.9148e-05
Epoch 459/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 8.7318e-05
Epoch 460/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step - loss: 8.5524e-05
Epoch 461/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 50ms/step - loss: 8.3768e-05
Epoch 462/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 8.2046e-05
Epoch 463/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 8.0361e-05
Epoch 464/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 7.8711e-05
Epoch 465/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step - loss: 7.7094e-05
Epoch 466/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 7.5510e-05
Epoch 467/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 7.3958e-05
Epoch 468/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 7.2440e-05
Epoch 469/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 7.0951e-05
Epoch 470/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 6.9494e-05
Epoch 471/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 6.8067e-05
Epoch 472/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 6.6667e-05
Epoch 473/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 6.5299e-05
Epoch 474/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 6.3958e-05
Epoch 475/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 28ms/step - loss: 6.2643e-05
Epoch 476/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 6.1356e-05
Epoch 477/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 6.0096e-05
Epoch 478/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 5.8861e-05
Epoch 479/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 5.7653e-05
Epoch 480/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 5.6468e-05
Epoch 481/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 5.5309e-05
Epoch 482/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 5.4173e-05
Epoch 483/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 5.3061e-05
Epoch 484/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - loss: 5.1970e-05
Epoch 485/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step - loss: 5.0903e-05
Epoch 486/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - loss: 4.9857e-05
Epoch 487/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step - loss: 4.8833e-05
Epoch 488/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 4.7830e-05
Epoch 489/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step - loss: 4.6847e-05
Epoch 490/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 4.5885e-05
Epoch 491/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 4.4942e-05
Epoch 492/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step - loss: 4.4020e-05
Epoch 493/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 25ms/step - loss: 4.3116e-05
Epoch 494/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 82ms/step - loss: 4.2230e-05
Epoch 495/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 47ms/step - loss: 4.1363e-05
Epoch 496/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step - loss: 4.0513e-05
Epoch 497/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step - loss: 3.9681e-05
Epoch 498/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 42ms/step - loss: 3.8866e-05
Epoch 499/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step - loss: 3.8068e-05
Epoch 500/500
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step - loss: 3.7286e-05
Out[6]:
<keras.src.callbacks.history.History at 0x1b32f8f1c30>
1/1 [==============================] - 0s 7ms/step - loss: 3.7374e-04
Epoch 408/500
1/1 [==============================] - 0s 10ms/step - loss: 3.6606e-04
Epoch 409/500
1/1 [==============================] - 0s 8ms/step - loss: 3.5855e-04
Epoch 410/500
1/1 [==============================] - 0s 11ms/step - loss: 3.5118e-04
Epoch 411/500
1/1 [==============================] - 0s 6ms/step - loss: 3.4397e-04
Epoch 412/500
1/1 [==============================] - 0s 8ms/step - loss: 3.3690e-04
Epoch 413/500
1/1 [==============================] - 0s 8ms/step - loss: 3.2998e-04
Epoch 414/500
1/1 [==============================] - 0s 8ms/step - loss: 3.2321e-04
Epoch 415/500
1/1 [==============================] - 0s 12ms/step - loss: 3.1656e-04
Epoch 416/500
1/1 [==============================] - 0s 9ms/step - loss: 3.1006e-04
Epoch 417/500
1/1 [==============================] - 0s 7ms/step - loss: 3.0370e-04
Epoch 418/500
1/1 [==============================] - 0s 9ms/step - loss: 2.9746e-04
Epoch 419/500
1/1 [==============================] - 0s 11ms/step - loss: 2.9135e-04
Epoch 420/500
1/1 [==============================] - 0s 8ms/step - loss: 2.8536e-04
Epoch 421/500
1/1 [==============================] - 0s 8ms/step - loss: 2.7950e-04
Epoch 422/500
1/1 [==============================] - 0s 13ms/step - loss: 2.7376e-04
Epoch 423/500
1/1 [==============================] - 0s 9ms/step - loss: 2.6813e-04
Epoch 424/500
1/1 [==============================] - 0s 11ms/step - loss: 2.6263e-04
Epoch 425/500
1/1 [==============================] - 0s 13ms/step - loss: 2.5723e-04
Epoch 426/500
1/1 [==============================] - 0s 13ms/step - loss: 2.5195e-04
Epoch 427/500
1/1 [==============================] - 0s 10ms/step - loss: 2.4677e-04
Epoch 428/500
1/1 [==============================] - 0s 10ms/step - loss: 2.4171e-04
Epoch 429/500
1/1 [==============================] - 0s 14ms/step - loss: 2.3674e-04
Epoch 430/500
1/1 [==============================] - 0s 11ms/step - loss: 2.3188e-04
Epoch 431/500
1/1 [==============================] - 0s 11ms/step - loss: 2.2712e-04
Epoch 432/500
1/1 [==============================] - 0s 9ms/step - loss: 2.2245e-04
Epoch 433/500
1/1 [==============================] - 0s 8ms/step - loss: 2.1788e-04
Epoch 434/500
1/1 [==============================] - 0s 7ms/step - loss: 2.1340e-04
Epoch 435/500
1/1 [==============================] - 0s 7ms/step - loss: 2.0902e-04
Epoch 436/500
1/1 [==============================] - 0s 10ms/step - loss: 2.0473e-04
Epoch 437/500
1/1 [==============================] - 0s 10ms/step - loss: 2.0052e-04
Epoch 438/500
1/1 [==============================] - 0s 8ms/step - loss: 1.9640e-04
Epoch 439/500
1/1 [==============================] - 0s 8ms/step - loss: 1.9237e-04
Epoch 440/500
1/1 [==============================] - 0s 10ms/step - loss: 1.8842e-04
Epoch 441/500
1/1 [==============================] - 0s 8ms/step - loss: 1.8455e-04
Epoch 442/500
1/1 [==============================] - 0s 8ms/step - loss: 1.8076e-04
Epoch 443/500
1/1 [==============================] - 0s 7ms/step - loss: 1.7704e-04
Epoch 444/500
1/1 [==============================] - 0s 9ms/step - loss: 1.7341e-04
Epoch 445/500
1/1 [==============================] - 0s 9ms/step - loss: 1.6984e-04
Epoch 446/500
1/1 [==============================] - 0s 8ms/step - loss: 1.6636e-04
Epoch 447/500
1/1 [==============================] - 0s 8ms/step - loss: 1.6294e-04
Epoch 448/500
1/1 [==============================] - 0s 8ms/step - loss: 1.5959e-04
Epoch 449/500
1/1 [==============================] - 0s 8ms/step - loss: 1.5632e-04
Epoch 450/500
1/1 [==============================] - 0s 8ms/step - loss: 1.5310e-04
Epoch 451/500
1/1 [==============================] - 0s 11ms/step - loss: 1.4996e-04
Epoch 452/500
1/1 [==============================] - 0s 9ms/step - loss: 1.4688e-04
Epoch 453/500
1/1 [==============================] - 0s 7ms/step - loss: 1.4386e-04
Epoch 454/500
1/1 [==============================] - 0s 7ms/step - loss: 1.4091e-04
Epoch 455/500
1/1 [==============================] - 0s 10ms/step - loss: 1.3801e-04
Epoch 456/500
1/1 [==============================] - 0s 8ms/step - loss: 1.3518e-04
Epoch 457/500
1/1 [==============================] - 0s 8ms/step - loss: 1.3240e-04
Epoch 458/500
1/1 [==============================] - 0s 8ms/step - loss: 1.2968e-04
Epoch 459/500
1/1 [==============================] - 0s 10ms/step - loss: 1.2702e-04
Epoch 460/500
1/1 [==============================] - 0s 8ms/step - loss: 1.2441e-04
Epoch 461/500
1/1 [==============================] - 0s 8ms/step - loss: 1.2185e-04
Epoch 462/500
1/1 [==============================] - 0s 11ms/step - loss: 1.1935e-04
Epoch 463/500
1/1 [==============================] - 0s 9ms/step - loss: 1.1690e-04
Epoch 464/500
1/1 [==============================] - 0s 7ms/step - loss: 1.1450e-04
Epoch 465/500
1/1 [==============================] - 0s 9ms/step - loss: 1.1214e-04
Epoch 466/500
1/1 [==============================] - 0s 12ms/step - loss: 1.0984e-04
Epoch 467/500
1/1 [==============================] - 0s 14ms/step - loss: 1.0759e-04
Epoch 468/500
1/1 [==============================] - 0s 12ms/step - loss: 1.0538e-04
Epoch 469/500
1/1 [==============================] - 0s 13ms/step - loss: 1.0321e-04
Epoch 470/500
1/1 [==============================] - 0s 11ms/step - loss: 1.0109e-04
Epoch 471/500
1/1 [==============================] - 0s 15ms/step - loss: 9.9013e-05
Epoch 472/500
1/1 [==============================] - 0s 11ms/step - loss: 9.6980e-05
Epoch 473/500
1/1 [==============================] - 0s 11ms/step - loss: 9.4989e-05
Epoch 474/500
1/1 [==============================] - 0s 11ms/step - loss: 9.3038e-05
Epoch 475/500
1/1 [==============================] - 0s 7ms/step - loss: 9.1127e-05
Epoch 476/500
1/1 [==============================] - 0s 7ms/step - loss: 8.9256e-05
Epoch 477/500
1/1 [==============================] - 0s 8ms/step - loss: 8.7422e-05
Epoch 478/500
1/1 [==============================] - 0s 8ms/step - loss: 8.5626e-05
Epoch 479/500
1/1 [==============================] - 0s 9ms/step - loss: 8.3867e-05
Epoch 480/500
1/1 [==============================] - 0s 7ms/step - loss: 8.2144e-05
Epoch 481/500
1/1 [==============================] - 0s 10ms/step - loss: 8.0458e-05
Epoch 482/500
1/1 [==============================] - 0s 7ms/step - loss: 7.8804e-05
Epoch 483/500
1/1 [==============================] - 0s 7ms/step - loss: 7.7186e-05
Epoch 484/500
1/1 [==============================] - 0s 10ms/step - loss: 7.5600e-05
Epoch 485/500
1/1 [==============================] - 0s 8ms/step - loss: 7.4046e-05
Epoch 486/500
1/1 [==============================] - 0s 8ms/step - loss: 7.2527e-05
Epoch 487/500
1/1 [==============================] - 0s 11ms/step - loss: 7.1037e-05
Epoch 488/500
1/1 [==============================] - 0s 7ms/step - loss: 6.9577e-05
Epoch 489/500
1/1 [==============================] - 0s 6ms/step - loss: 6.8147e-05
Epoch 490/500
1/1 [==============================] - 0s 9ms/step - loss: 6.6748e-05
Epoch 491/500
1/1 [==============================] - 0s 6ms/step - loss: 6.5378e-05
Epoch 492/500
1/1 [==============================] - 0s 12ms/step - loss: 6.4035e-05
Epoch 493/500
1/1 [==============================] - 0s 9ms/step - loss: 6.2719e-05
Epoch 494/500
1/1 [==============================] - 0s 10ms/step - loss: 6.1431e-05
Epoch 495/500
1/1 [==============================] - 0s 10ms/step - loss: 6.0169e-05
Epoch 496/500
1/1 [==============================] - 0s 10ms/step - loss: 5.8934e-05
Epoch 497/500
1/1 [==============================] - 0s 10ms/step - loss: 5.7723e-05
Epoch 498/500
1/1 [==============================] - 0s 13ms/step - loss: 5.6537e-05
Epoch 499/500
1/1 [==============================] - 0s 10ms/step - loss: 5.5376e-05
Epoch 500/500
1/1 [==============================] - 0s 7ms/step - loss: 5.4240e-05
Out[6]:
<keras.callbacks.History at 0x146451fc6d0>

Now you have the model that has the knowledge of the relationship between xs and ys. Now we can use predict() method to predict for unknown xs values (that is unknown to the model)

In [7]:
new_x = np.array([12.0])
new_y = model.predict(new_x, verbose=0)
new_y
Out[7]:
array([[22.977022]], dtype=float32)
In [8]:
new_y.item()
Out[8]:
22.977022171020508

As per the numbers in xs and ys, it is showing the relationship of y=2x-1. However we got a little below 23 and not 23 exactly. This is because neural network deals with probabilities. So given the data that we fed to the model, it calculated that there is a very high probability that the relationship between x and y is y=2x-1, but with only 6 data points we cant be very much sure about this. As a result, for 12 we got value very close to 23 but not necessarily 23. Neural networks are data hungry models.

So what you did here?¶

  1. You generated your own data
  2. You created the model architecture with Input layer for the incoming data and 1 neural network layer with 1 neuron
  3. Compiled the model with loss and optimizer
  4. Fitted the model with training data
  5. Predicted on the trained model
In [ ]: