我正在嘗試從頭開始構建一個類似于 Keras 的簡單神經網路庫，但我在讓訓練正常作業時遇到了問題。自從我從頭開始撰寫神經網路而不是使用庫已經有一段時間了，所以我認為這是一個很好的做法。
我不太確定我是否為沒有給出輸入形狀的情況正確設定了建構式，并且無論我通過層的神經元數量如何，我都會遇到“ValueError：形狀 X 和 Y 未對齊”問題或輸入形狀。這是回溯：
Traceback (most recent call last): File "NNfromScratch.py", line 551, in <module>
model.train(X_train, y_train, epochs=100, batch_size=10, verbose=True)
File "NNfromScratch.py", line 427, in train
self.forward(batch_inputs)
File "NNfromScratch.py", line 395, in forward
self.outputs = layer.forward(self.outputs)
File "NNfromScratch.py", line 153, in forward
**self.outputs = np.dot(self.weights.T, inputs) self.biases**
File "<__array_function__ internals>", line 6, in dot
ValueError: shapes (784,32) and (10,784) not aligned: 32 (dim 1) != 10 (dim 0)
該錯誤是從Dense層的forward函式拋出的。
完整的（可重現的）代碼可以在這里看到。
不過，這是最重要部分的片段：
import time
import numpy as np
import pandas as pd
import pickle as pkl
import matplotlib.pyplot as plt
import tensorflow.keras.datasets.mnist as mnist
...
class Layers:
class Dense:
def __init__(self, neurons=0, activation=Activations.ReLU, inputs=0, dropout_rate=1):
# Initialize weights and biases
self.weights = np.random.randn(neurons, inputs)
self.biases = np.random.randn(1, neurons)
self.activation = activation
self.dropout_rate = dropout_rate
# Forward-Propagation
def forward(self, inputs):
self.inputs = inputs
self.outputs = np.dot(self.weights.T, inputs) self.biases
self.outputs = self.activation(self.outputs)
self.outputs = self.dropout(self.outputs)
return self.outputs
# Backward-Propagation
def backward(self, error, learning_rate):
self.error = error
self.delta = self.error * self.activation(self.outputs)
self.delta = self.dropout(self.delta, derivative=True)
self.weights -= learning_rate * np.dot(self.delta, self.inputs.T)
self.biases -= learning_rate * np.sum(self.delta, axis=0, keepdims=True)
return self.delta
# Dropout
def dropout(self, x, derivative=False):
if derivative:
return self.dropout_rate * (1 - self.dropout_rate) * x
return self.dropout_rate * x
class NeuralNetwork:
"""..."""
def forward(self, inputs):
# Forward-Propagation
self.inputs = inputs
self.outputs = self.inputs
for layer in self.layers:
self.outputs = layer.forward(self.outputs)
return self.outputs
def backward(self, targets):
# Backward-Propagation
self.targets = targets
self.error = self.loss(self.outputs, self.targets)
self.delta = self.error
for layer in reversed(self.layers):
self.delta = layer.backward(self.delta, self.optimizer_kwargs)
return self.delta
def update_weights(self):
# Update weights and biases
for layer in self.layers:
layer.update_weights(self.optimizer_kwargs)
def train(self, inputs, targets, epochs=1, batch_size=1, verbose=False):
self.epochs = epochs
self.epoch_errors = []
self.epoch_losses = []
self.epoch_accuracies = []
self.epoch_times = []
start = time.time()
for epoch in range(self.epochs):
epoch_start = time.time()
epoch_error = 0
epoch_loss = 0
epoch_accuracy = 0
for i in range(0, inputs.shape[0], batch_size):
batch_inputs = inputs[i:i batch_size]
batch_targets = targets[i:i batch_size]
self.forward(batch_inputs)
self.backward(batch_targets)
self.update_weights()
epoch_error = self.error.sum()
epoch_loss = self.loss(self.outputs, self.targets).sum()
epoch_accuracy = self.accuracy(self.outputs, self.targets)
epoch_time = time.time() - epoch_start
self.epoch_errors.append(epoch_error)
self.epoch_losses.append(epoch_loss)
self.epoch_accuracies.append(epoch_accuracy)
self.epoch_times.append(epoch_time)
if verbose:
print('Epoch: {}, Error: {}, Loss: {}, Accuracy: {}, Time: {}'.format(epoch, epoch_error, epoch_loss, epoch_accuracy, epoch_time))
self.train_time = time.time() - start
return self.epoch_errors, self.epoch_losses, self.epoch_accuracies, self.epoch_times
# Load and flatten data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape((X_train.shape[0], -1))
X_test = X_test.reshape((X_test.shape[0], -1))
# Build model
model = NeuralNetwork([
Layers.Dense(32, Activations.ReLU, inputs=X_train.shape[1]),
Layers.Dense(10, Activations.ReLU),
Layers.Dense(1, Activations.Softmax)
], Losses.Categorical_Cross_Entropy, Optimizers.SGD, learning_rate=0.01)
model.train(X_train, y_train, epochs=100, batch_size=10, verbose=True)
model.evaluate(X_test, y_test)
uj5u.com熱心網友回復：
更改此行：
self.outputs = np.dot(self.weights.T, inputs) self.biases
至
self.outputs = np.dot(inputs, self.weights.T) self.biases
原因是內部尺寸需要對齊。你inputs的形狀是形狀[B,784]（B批量大小在哪里），你的重量是形狀[32,784]。
轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/492957.html
上一篇：程式運行時列印棋盤