All geek questions in one place

Image_dim_ordering - what am I missing here?

EDIT: Failed to reproduce this issue using cuda 8.0 and using titan X (Pascal)

Using tensorflow firewall for keras i have image_dim_ordering related problems. When I use image_dim_ordering = 'th' in the keras configuration file, everything works fine. But when I use 'tf', training just doesn’t greatly improve accuracy from 0.5.

The motivation is that currently my live improvements are very expensive, and I would like to remove an unnecessary change from the color agreement using anano to tensorflow.

I tried to recreate the problem with simple code to allow other people to play it back, which can help me understand what I'm doing wrong here. I know the channels, the height, the width of the various conventions well, and at least I think I can handle it.

While I did not fully reproduce my problem in a compact example (perhaps because it is a trivial task), the training results are repeatedly and much worse for the "tf" case, even when I try different seed values. Note. In this replay code, all the networks need to do is separate the full fixes from -1.0 from the full 1.0 patches

This is my '~ / .keras / keras.json'

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

my tensorflow version is equal to `` 0.11.0rc0 '' (this happened at 0.10) my keras is the last git traction today.

'th' image_dim_ordering, >= 0.99 4 . 'tf' , >= 0,9 , , 24

, :

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)

"tf" : ( ):

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

"" ( ):

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

, case-, (0s), , , . , , , , , 2-3 .

- , , , , :)

+5
1

, , - .

Keras...

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

tensorflow , Theano tensorflow. image_dim_ordering tf, .

"image_dim_ordering": "tf"
0

Source: https://habr.com/ru/post/1656768/

More articles:


All Articles