Question

编辑：无法使用cuda 8.0和使用titan X（Pascal）重现此问题

对keras使用tensorflow后端我遇到了与image_dim_ordering相关的问题。当我使用image_dim_ordering =＆＃39; th＆＃39;在keras配置文件中，一切运行良好但是当我使用＆t 39时，训练根本不会从0.5准确度中提高很多。

目前我的现场扩充是非常昂贵的，并且我喜欢将不需要的重塑从theano暗淡的顺序约定移除到tensorflow。

我尝试用简单的代码重新创建问题，以便让其他人复制，这可能有助于我理解我在这里做错了什么。我很清楚通道，高度，宽度的不同惯例，至少我认为我处理它。

虽然我没有在紧凑的例子中完全重现我的问题（也许是因为这是一项微不足道的任务），但是训练结果反复不同，而且对于“tf”而言则更糟糕。即使我尝试不同的种子值也是如此。注意 - 在这个重现代码中，网络需要做的就是从1.0的完整补丁中分辨出-1.0的完整补丁

这是我的＆＃39;〜/ .keras / keras.json＆＃39;

{
    "floatx": "float32",
    "epsilon": 1e-07,
    "backend": "tensorflow",
    "image_dim_ordering": "th"  
}

我的张量流版本是＆＃39; 0.11.0rc0＆＃39;＆＃39; （它发生在0,10上）我的keras是今天最新的git pull。

使用＆＃39; th＆＃39;对于image_dim_ordering，对于三个不同的种子，我在时期4得到准确度＆gt; = 0.99。使用＆＃t;＆＃39;对于昏暗的顺序，我得到的准确度＆gt; = 0.9最新，你可以在下面的日志中看到，仅在24左右

以下是应该重现问题的独立代码：

from keras import backend as K
import keras.optimizers
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense, Input
from keras.models import Model
import numpy as np

def make_model(input_dim_size):
    if K.image_dim_ordering() == 'tf':
        input_shape = (input_dim_size, input_dim_size,1)
    else:
        input_shape = (1, input_dim_size, input_dim_size)
    img_input = Input(shape=input_shape)

    x = Convolution2D(64,5,5,border_mode='same')(img_input)
    x = Activation('relu')(x)
    x = MaxPooling2D((2,2),strides=(2,2))(x)

    x = Convolution2D(64, 5, 5, border_mode='same')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2))(x)

    x = Convolution2D(64, 5, 5, border_mode='same')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2))(x)

    x = Convolution2D(128, 5, 5, border_mode='same')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2))(x)

    x = Convolution2D(128, 5, 5, border_mode='same')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2))(x)

    x = Flatten()(x)
    x = Dense(1024*2)(x)
    x = Activation('relu')(x)
    x = Dropout(0.5)(x)

    x = Dense(1024 * 2)(x)
    x = Activation('relu')(x)
    x = Dropout(0.75)(x)

    x = Dense(200)(x)
    x = Activation('relu')(x)
    x = Dropout(0.75)(x)

    x = Dense(1,activation='sigmoid')(x)

    model = Model(img_input, x)

    learning_rate = 0.01

    sgd = keras.optimizers.sgd(lr=learning_rate, momentum=0.9, nesterov=True)

    model.summary()

    model.compile(loss='binary_crossentropy',
                  optimizer=sgd,
                  metrics=['accuracy']
                  )
    return model

np.random.seed(456)

def dummy_generator(mini_batch_size=64, block_size=100):
    if K.image_dim_ordering() == 'tf':
        tensor_X_shape = (mini_batch_size,block_size, block_size,1)
    else:
        tensor_X_shape = (mini_batch_size, 1, block_size, block_size)

    X = np.zeros(tensor_X_shape, dtype=np.float32)
    y = np.zeros((mini_batch_size, 1))

    while True:
        for b in range(mini_batch_size):
            X[b, :, :, :] = (float(b % 2) * 2.0) - 1.0
            y[b, :] = float(b % 2)
        yield X,y

with K.tf.device('/gpu:2'):
    K.set_session(K.tf.Session(config=K.tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)))
    MINI_BATCH_SIZE = 64
    PATCH_SIZE = 100
    model = make_model(PATCH_SIZE)
    gen = dummy_generator(mini_batch_size=MINI_BATCH_SIZE,block_size=PATCH_SIZE)
    model.fit_generator(gen, MINI_BATCH_SIZE*10,
                        100, verbose=1,
                        callbacks=[],
                        validation_data=None,
                        nb_val_samples=None,
                        max_q_size=1,
                        nb_worker=1, pickle_safe=False)

对于＆＃39; tf＆＃39;这是训练日志:(并且在不同种子上看起来非常相似）：

Epoch 1/100
640/640 [==============================] - 1s - loss: 0.6932 - acc: 0.4781     
Epoch 2/100
640/640 [==============================] - 0s - loss: 0.6932 - acc: 0.4938     
Epoch 3/100
640/640 [==============================] - 0s - loss: 0.6921 - acc: 0.5203     
Epoch 4/100
640/640 [==============================] - 0s - loss: 0.6920 - acc: 0.5469     
Epoch 5/100
640/640 [==============================] - 0s - loss: 0.6935 - acc: 0.4875     
Epoch 6/100
640/640 [==============================] - 0s - loss: 0.6941 - acc: 0.4969     
Epoch 7/100
640/640 [==============================] - 0s - loss: 0.6937 - acc: 0.5047     
Epoch 8/100
640/640 [==============================] - 0s - loss: 0.6931 - acc: 0.5312     
Epoch 9/100
640/640 [==============================] - 0s - loss: 0.6923 - acc: 0.5250     
Epoch 10/100
640/640 [==============================] - 0s - loss: 0.6929 - acc: 0.5281     
Epoch 11/100
640/640 [==============================] - 0s - loss: 0.6934 - acc: 0.4953     
Epoch 12/100
640/640 [==============================] - 0s - loss: 0.6918 - acc: 0.5234     
Epoch 13/100
640/640 [==============================] - 0s - loss: 0.6930 - acc: 0.5125     
Epoch 14/100
640/640 [==============================] - 0s - loss: 0.6939 - acc: 0.4797     
Epoch 15/100
640/640 [==============================] - 0s - loss: 0.6936 - acc: 0.5047     
Epoch 16/100
640/640 [==============================] - 0s - loss: 0.6917 - acc: 0.4922     
Epoch 17/100
640/640 [==============================] - 0s - loss: 0.6945 - acc: 0.4891     
Epoch 18/100
640/640 [==============================] - 0s - loss: 0.6948 - acc: 0.5000     
Epoch 19/100
640/640 [==============================] - 0s - loss: 0.6968 - acc: 0.4594     
Epoch 20/100
640/640 [==============================] - 0s - loss: 0.6919 - acc: 0.5391     
Epoch 21/100
640/640 [==============================] - 0s - loss: 0.6904 - acc: 0.5172     
Epoch 22/100
640/640 [==============================] - 0s - loss: 0.6881 - acc: 0.5906     
Epoch 23/100
640/640 [==============================] - 0s - loss: 0.6804 - acc: 0.6359     
Epoch 24/100
640/640 [==============================] - 0s - loss: 0.6470 - acc: 0.8219     
Epoch 25/100
640/640 [==============================] - 0s - loss: 0.4134 - acc: 0.9625     
Epoch 26/100
640/640 [==============================] - 0s - loss: 0.2347 - acc: 0.9953     
Epoch 27/100
640/640 [==============================] - 0s - loss: 0.1231 - acc: 1.0000

而对于＆＃39;＆＃39;案例培训日志是（并且在不同的种子上看起来非常相似）：

Epoch 1/100
640/640 [==============================] - 3s - loss: 0.6891 - acc: 0.5594     
Epoch 2/100
640/640 [==============================] - 2s - loss: 0.6079 - acc: 0.7328     
Epoch 3/100
640/640 [==============================] - 2s - loss: 0.3166 - acc: 0.9422     
Epoch 4/100
640/640 [==============================] - 2s - loss: 0.1767 - acc: 0.9969

我发现它在tensorflow情况下（0s）如此之快，但在将调试打印添加到生成器之后，似乎确实被调用了。我认为也许它与keras有关，不需要重塑任何东西，但2-3秒听起来太多时间进行这种重塑

如果有人可以尝试重现我看到的结果并帮助我理解我在这里错过了什么，我将不胜感激：）

Answer 1

这个帖子有点旧，但我仍在回复以防有人面临同样的问题。

由于Keras后端配置不一致导致错误...

{
    "floatx": "float32",
    "epsilon": 1e-07,
    "backend": "tensorflow",
    "image_dim_ordering": "th"  
}

配置使用tensorflow作为后端，但使用Theano而不是tensorflow的图片维度排序。将image_dim_ordering更改为tf，这应解决问题..

"image_dim_ordering": "tf"

image_dim_ordering - 我在这里缺少什么？

1 个答案: