Question

我正在尝试遵循此suggestion。

outputs = Conv2DTranspose(3, (1, 1), activation='sigmoid') (c9)
model = Model(inputs=[inputs], outputs=[outputs])
model = multi_gpu_model(model, gpus=8)
model.compile(optimizer='adam', loss = bce, metrics = [mean_iou])
model.add(Lambda(lambda x: K.batch_flatten(x)))

但是在代码的最后一行，我收到以下错误：

“模型”对象没有属性“添加”

我知道，由于我没有像链接文章中那样将模型实例化为sequential()，因此功能add()可能对我不可用。但是，我不确定如何解决此问题。

Answer 1

更正以反映出有效的解决方案：

outputs = Conv2DTranspose(3, (1, 1), activation='sigmoid') (c9)
outputs = Lambda(lambda x: K.batch_flatten(x))(outputs)
model = Model(inputs=[inputs], outputs=[outputs])
model = multi_gpu_model(model, gpus=8)
model.compile(optimizer='adam', loss = bce, metrics = [mean_iou])

Answer 2

在OP的评论中忽略@Today的答案，

SELECT x.date ,x.website ,x.country_id ,x.product_id ,x.today_users ,SUM(x.today_users) OVER (PARTITION BY x.website, x.country_id, x.product_id ORDER BY x.date ASC ROWS BETWEEN 7 PRECEDING AND 1 PRECEDING) AS Past_7D_Users FROM (SELECT date, website, country_id, product_id, SUM(user) AS today_users FROM Table GROUP BY date, website, country_id, product_id )x GROUP BY x.date ,x.website ,x.country_id ,x.product_id ,x.today_users ;

无法在keras中添加图层

2 个答案: