thadeu.us
Features
Labels
Rank | Shape | |
---|---|---|
1 | 0 | () |
[1] | 1 | (1) |
[[1], [2]] | 2 | (2,1) |
[[[1], [2]], [[3], [4]], [[5], [6]]] |
3 | (3, 2, 1) |
Área (feature) | Preço (label) |
---|---|
50m² |
R$ 150 000 |
75m² |
R$ 210 000 |
120m² |
R$ 300 000 |
100m² |
? |
Qual o preço?
Área (m²)
Preço (R$)
(70%) Formatando dados
(20%) Configurar modelo
(10%) Outros
(detectar spam)
const layers: tf.layers.Layer[] = [
tf.layers.conv1d({
activation: "relu",
filters: 32,
inputShape: [xSize, mfccSize],
kernelSize: [2]
}),
tf.layers.conv1d({ activation: "relu", filters: 48, kernelSize: [2] }),
tf.layers.conv1d({ activation: "relu", filters: 120, kernelSize: [2] }),
tf.layers.maxPooling1d({ poolSize: 2 }),
tf.layers.dropout({ rate: 0.25 }),
tf.layers.flatten(),
tf.layers.dense({ units: 128, activation: "relu" }),
tf.layers.dropout({ rate: 0.25 }),
tf.layers.dense({ units: 64, activation: "relu" }),
tf.layers.dropout({ rate: 0.4 }),
tf.layers.dense({ units: 1, activation: "sigmoid" })
];
const model = tf.sequential({ layers });