Tensorflow

cross_entropy <- tf$reduce_mean(-tf$reduce_sum(y_ * tf$log(y_conv), reduction_indices=1L))

train_step <- tf$train$AdamOptimizer(1e-4)$minimize(cross_entropy)

correct_prediction <- tf$equal(tf$argmax(y_conv, 1L), tf$argmax(y_, 1L))

accuracy <- tf$reduce_mean(tf$cast(correct_prediction, tf$float32))

sess$run(tf$global_variables_initializer())



for (i in 1:20000) {

  batch <- mnist$train$next_batch(50L)

  if (i %% 100 == 0) {

    train_accuracy <- accuracy$eval(feed_dict = dict(

        x = batch[[1]], y_ = batch[[2]], keep_prob = 1.0))

    cat(sprintf("step %d, training accuracy %g\n", i, train_accuracy))

  }

  train_step$run(feed_dict = dict(

    x = batch[[1]], y_ = batch[[2]], keep_prob = 0.5))

}



test_accuracy <- accuracy$eval(feed_dict = dict(

     x = mnist$test$images, y_ = mnist$test$labels, keep_prob = 1.0))

cat(sprintf("test accuracy %g", test_accuracy))

Keras

model_top %>% fit(

        x = train_x, y = train_y,

        epochs=epochs, 

        batch_size=batch_size,

        validation_data=valid)

用Keras进行图像分类

Keras的代码片段

train_generator <- flow_images_from_directory(train_directory, generator = image_data_generator(), target_size = c(img_width, img_height), color_mode = "rgb",

  class_mode = "binary", batch_size = batch_size, shuffle = TRUE,

  seed = 123)

model <- keras_model_sequential()



model %>%

  layer_conv_2d(filter = 32, kernel_size = c(3,3), input_shape = c(img_width, img_height, 3)) %>%

  layer_activation("relu") %>%

  layer_max_pooling_2d(pool_size = c(2,2)) %>% 

  

  layer_conv_2d(filter = 32, kernel_size = c(3,3)) %>%

  layer_activation("relu") %>%

  layer_max_pooling_2d(pool_size = c(2,2)) %>%

  

  layer_conv_2d(filter = 64, kernel_size = c(3,3)) %>%

  layer_activation("relu") %>%

  layer_max_pooling_2d(pool_size = c(2,2)) %>%

  

  layer_flatten() %>%

  layer_dense(64) %>%

  layer_activation("relu") %>%

  layer_dropout(0.5) %>%

  layer_dense(1) %>%

  layer_activation("sigmoid")

augment <- image_data_generator(rescale=1./255,

                               shear_range=0.2,

                               zoom_range=0.2,

                               horizontal_flip=TRUE)

model_vgg <- application_vgg16(include_top = FALSE, weights = "imagenet")

save_model_weights_hdf5(model_ft, 'finetuning_30epochs_vggR.h5', overwrite = TRUE)