小编Mar*_*jko的帖子

在文档中,predict_proba(self, x, batch_size=32, verbose=1)是

逐批生成输入样本的类概率预测.

并返回

Numpy概率预测数组.

假设我的模型是二元分类模型,输出是[a, b],a是概率class_0,b是概率class_1？

我用这个转换器将Caffe模型转换为Keras.但是我的一个层是类型的slice,它也需要转换,但转换器目前不支持这个并引发异常.它有什么工作吗？这是我的图层:

layer {
    name: "slice_label"
    type: SLICE
    bottom: "label"
    top: "label_wpqr"
    top: "label_xyz"
    slice_param {
        slice_dim: 1
        slice_point: 4
    }
}

我正在尝试为一些二进制分类问题训练LSTM.当我loss在训练后绘制曲线时,会有奇怪的选择.这里有些例子:

这是基本代码

model = Sequential()
model.add(recurrent.LSTM(128, input_shape = (columnCount,1), return_sequences=True))
model.add(Dropout(0.5))
model.add(recurrent.LSTM(128, return_sequences=False))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(optimizer='adam', 
             loss='binary_crossentropy', 
             metrics=['accuracy'])

new_train = X_train[..., newaxis]

history = model.fit(new_train, y_train, nb_epoch=500, batch_size=100, 
                    callbacks = [EarlyStopping(monitor='val_loss', min_delta=0.0001, patience=2, verbose=0, mode='auto'), 
                                 ModelCheckpoint(filepath="model.h5", verbose=0, save_best_only=True)],
                    validation_split=0.1)

# list all data in history
print(history.history.keys())
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

我不明白为什么这样的选择发生？有任何想法吗？

在Philippe Remy 关于有状态LSTM 的博客文章中,他在底部说"你可能必须通过调用predict_on_batch()或test_on_batch()来手动进行验证/测试".

查看文档,predict_on_batch执行此操作:

predict_on_batch(self, x)

Returns predictions for a single batch of samples.

Arguments

    x: Input samples, as a Numpy array.

Returns

Numpy array(s) of predictions.

test_on_batch执行此操作:

test_on_batch(self, x, y, sample_weight=None)

Test the model on a single batch of samples.

Arguments

    x: Numpy array of test data, or list of Numpy arrays if the model has multiple inputs. If all inputs in the model are named, you can also pass a dictionary mapping input …

我正在用Python实现segnet。以下是代码。

img_w = 480
img_h = 360
pool_size = 2

def build_model(img_w, img_h, pool_size):
    n_labels = 12

    kernel = 3

    encoding_layers = [
        Conv2D(64, (kernel, kernel), input_shape=(img_h, img_w, 3), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        Convolution2D(64, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        MaxPooling2D(pool_size = (pool_size,pool_size)),

        Convolution2D(128, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        Convolution2D(128, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        MaxPooling2D(pool_size = (pool_size,pool_size)),

        Convolution2D(256, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        Convolution2D(256, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        Convolution2D(256, (kernel, kernel), padding='same'),
        BatchNormalization(),
        Activation('relu'),
        MaxPooling2D(pool_size = (pool_size,pool_size)),

        Convolution2D(512, (kernel, kernel), …

Keras在训练卷积自动编码器时抛出ResourceExhaustedError.我正在运行Tensorflow后端.这台电脑既有Nvidia Tesla,内存为11 Gbs,Nvidia Quadro也有6 Gbs的内存.似乎Tensorflow正在使用两个GPU？但我对此并不太清楚.这是我正在使用的代码的最小示例.在我的示例中,数据是一个numpy数组维度=(100,1080,1920,1).

from keras.layers import Convolution2D, MaxPooling2D, UpSampling2D, Activation
from keras.models import Sequential
model = Sequential()
model.add(Convolution2D(16, 3, 3, border_mode='same', input_shape=(1080, 1920, 1)))
model.add(Activation('relu'))
model.add(MaxPooling2D((2, 2), border_mode='same'))
model.add(Convolution2D(16, 3, 3, border_mode='same'))
model.add(Activation('relu'))
model.add(UpSampling2D((2, 2)))
model.add(Convolution2D(1, 3, 3, border_mode='same'))
model.add(Activation('relu'))
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.fit(data, data)

看起来GPU的内存不足.自动编码器有2625个变量.所以这似乎不足以填满视频内存.阵列数据的大小为1600 MB.所以这也不应该填满视频公羊.我猜这个问题与nb_epoch和batch_size有关,但我不清楚这些参数是做什么的.有没有办法改变这些参数来解决我的问题？