Lapisan input dan dense di Keras

Deep Learning Tingkat Lanjut dengan Keras

Zach Deane-Mayer

Data Scientist

Ringkasan Pembelajaran

Bab 1: Pengantar Keras functional API (Penyegar)
Bab 2: Model dengan 2 input
Bab 3: Model dengan 3 input
Bab 4: Banyak output

Dataset Kursus: Data bola basket kampus, 1989–2017

Dataset 1: Musim reguler

ID Tim 1
ID Tim 2
Kandang vs Tandang
Selisih Skor (Tim 1 - Tim 2)
Skor Tim 1
Skor Tim 2
Menang vs Kalah

Dataset 2: Pertandingan turnamen

Sama seperti Dataset 1
Juga memiliki selisih Seed

Dataset Kursus: Data bola basket kampus, 1989–2017

import pandas as pd
games_season = pd.read_csv('datasets/games_season.csv')
games_season.head()

Out[1]:
   season  team_1  team_2  home  score_diff  score_1  score_2  won
0    1985    3745    6664     0          17       81       64    1
1    1985     126    7493     1           7       77       70    1
2    1985     288    3593     1           7       63       56    1
3    1985    1846    9881     1          16       70       54    1
4    1985    2675   10298     1          12       86       74    1

games_tourney = pd.read_csv('datasets/games_tourney.csv')
games_tourney.head()

Out[2]:
   season  team_1  team_2  home  seed_diff  score_diff  score_1  score_2  won
0    1985     288      73     0         -3          -9       41       50    0
1    1985    5929      73     0          4           6       61       55    1
2    1985    9884      73     0          5          -4       59       63    0
3    1985      73     288     0          3           9       50       41    1
4    1985    3920     410     0          1          -9       54       63    0

Input dan output

Dua bagian utama:

Lapisan input
Lapisan output

Input

from tensorflow.keras.layers import Input
input_tensor = Input(shape=(1,))

Input

from tensorflow.keras.layers import Input
input_tensor = Input(shape=(1,))
print(input_tensor)

KerasTensor(type_spec=TensorSpec(shape=(None, 1), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'input_1'")

Output

from tensorflow.keras.layers import Dense
output_layer = Dense(1)

Output

from tensorflow.keras.layers import Dense
output_layer = Dense(1)
print(output_layer)

<keras.layers.core.dense.Dense object at 0x15df15e80>

Menghubungkan input ke output

from tensorflow.keras.layers import Input, Dense
input_tensor = Input(shape=(1,))
output_layer = Dense(1)
output_tensor = output_layer(input_tensor)

Menghubungkan input ke output

print(output_tensor)

KerasTensor(type_spec=TensorSpec(shape=(None, 1), dtype=tf.float32, name=None), name='dense_1/BiasAdd:0', description="created by layer 'dense_1'")

Ayo berlatih!

Deep Learning Tingkat Lanjut dengan Keras