我正试图从Keras过渡到PYTorch。
阅读教程和类似问题后,我提出了以下简单模型进行测试。但是,以下两个模型给我的得分却截然不同:Keras(0.9),PyTorch(0.03)。
有人可以给我指导吗?
基本上我的数据集具有120个要素和具有3个如下所示的类的多标签。
[
[1,1,1],
[0,1,1],
[1,0,0],
...
]
def score(true, pred):
lrl = label_ranking_loss(true, pred)
lrap = label_ranking_average_precision_score(true, pred)
print('LRL:', round(lrl), 'LRAP:', round(lrap))
#Keras:
model= Sequential()
model.add(Dense(60, activation="relu", input_shape=(120,)))
model.add(Dense(30, activation="relu"))
model.add(Dense(3, activation="sigmoid"))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=100)
pred = model.predict(x_test)
score(y_test, pred)
#PyTorch
model = torch.nn.Sequential(
torch.nn.Linear(120, 60),
torch.nn.ReLU(),
torch.nn.Linear(60, 30),
torch.nn.ReLU(),
torch.nn.Linear(30, 3),
torch.nn. Sigmoid())
loss_fn = torch.nn. BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
epochs = 100
batch_size = 32
n_batch = int(x_train.shape[0]/batch_size)
for epoch in range(epochs):
avg_cost = 0
for i in range(n_batch):
x_batch = x_train[i*batch_size:(i+1)*batch_size]
y_batch = y_train[i*batch_size:(i+1)*batch_size]
x, y = Variable(torch.from_numpy(x_batch).float()), Variable(torch.from_numpy(y_batch).float(), requires_grad=False)
pred = model(x)
loss = loss_fn(pred, y)
loss.backward()
optimizer.step()
avg_cost += loss.item()/n_batch
print(epoch, avg_cost)
x, y = Variable(torch.from_numpy(x_test).float()), Variable(torch.from_numpy(y_test).float(), requires_grad=False)
pred = model(x)
score(y_test, pred.data.numpy())
答案 0 :(得分:0)
您需要在每次迭代开始时调用optimizer.zero_grad()
,否则来自不同批次的梯度会不断累积。