r - Keras predict_generator 中的输出顺序

Question

我遵循了有关在 R 中使用 Keras 进行图像识别的在线教程，最终代码如下:

library(keras)

view_list <- c("Inside", "Outside")
output_n <- length(view_list)

# image size to scale down to (original images are 100 x 100 px)
img_width <- 20
img_height <- 20
target_size <- c(img_width, img_height)

# RGB = 3 channels
channels <- 3

train_image_files_path <- "C:/Users/Tomek/Desktop/Photos"
valid_image_files_path <- "C:/Users/Tomek/Desktop/Photos valid"
test_image_files_path <- "C:/Users/Tomek/Desktop/Photos test"

# optional data augmentation
train_data_gen = image_data_generator(rescale = 1/255 )

# Validation data shouldn't be augmented! But it should also be scaled.
valid_data_gen <- image_data_generator(rescale = 1/255)  
test_data_gen <- image_data_generator(rescale = 1/255) 

# training images
train_image_array_gen <- flow_images_from_directory(train_image_files_path, 
                                                    train_data_gen,
                                                    target_size = target_size,
                                                    class_mode = "categorical",
                                                    classes = view_list,
                                                    seed = 42)


# validation images
valid_image_array_gen <- flow_images_from_directory(valid_image_files_path, 
                                                    valid_data_gen,
                                                    target_size = target_size,
                                                    class_mode = "categorical",
                                                    classes = view_list,
                                                    seed = 42)

# test images
test_image_array_gen <- flow_images_from_directory(test_image_files_path, 
                                                   test_data_gen,
                                                   target_size = target_size,
                                                   class_mode = "categorical",
                                                   classes = view_list,
                                                   seed = 42)

cat("Number of images per class:")
table(factor(train_image_array_gen$classes))
train_image_array_gen$class_indices

views_classes_indices <- train_image_array_gen$class_indices
save(views_classes_indices, file = "C:/Users/Tomek/Desktop/views_classes_indices.RData")

# number of training samples
train_samples <- train_image_array_gen$n
# number of validation samples
valid_samples <- valid_image_array_gen$n
# number of test samples
test_samples <- test_image_array_gen$n

# define batch size and number of epochs
batch_size <- 1
epochs <- 10

# initialise model
model <- keras_model_sequential()

# add layers
model %>%
  layer_conv_2d(filter = 32, kernel_size = c(3,3), padding = "same", input_shape = c(img_width, img_height, channels)) %>%
  layer_activation("relu") %>%

  # Second hidden layer
  layer_conv_2d(filter = 16, kernel_size = c(3,3), padding = "same") %>%
  layer_activation_leaky_relu(0.5) %>%
  layer_batch_normalization() %>%

  # Use max pooling
  layer_max_pooling_2d(pool_size = c(2,2)) %>%
  layer_dropout(0.25) %>%

  # Flatten max filtered output into feature vector 
  # and feed into dense layer
  layer_flatten() %>%
  layer_dense(100) %>%
  layer_activation("relu") %>%
  layer_dropout(0.5) %>%

  # Outputs from dense layer are projected onto output layer
  layer_dense(output_n) %>% 
  layer_activation("softmax")

# compile
model %>% compile(
  loss = "categorical_crossentropy",
  optimizer = optimizer_rmsprop(lr = 0.0001, decay = 1e-6),
  metrics = "accuracy"
)

summary(model)

# fit
hist <- model %>% fit_generator(
  # training data
  train_image_array_gen,

  # epochs
  steps_per_epoch = as.integer(train_samples / batch_size), 
  epochs = epochs, 

  # validation data
  validation_data = valid_image_array_gen,
  validation_steps = as.integer(valid_samples / batch_size),

  # print progress
  verbose = 2,
  callbacks = list(
    # save best model after every epoch
    callback_model_checkpoint("C:/Users/Tomek/Desktop/views_checkpoints.h5", save_best_only = TRUE),
    # only needed for visualising with TensorBoard
    callback_tensorboard(log_dir = "C:/Users/Tomek/Desktop/keras/logs")
  )
)
plot(hist)

#prediction
a <- model %>% predict_generator(test_image_array_gen, steps = 5, verbose = 1, workers = 1)
a <- round(a, digits = 4)

分类模型(有两个输出类)似乎工作得很好。训练集和验证集的准确率分别等于 ~99% 和 ~95%。但是，我不确定测试集的预测结果。看起来对观察的预测被打乱了，我无法找到一种方法来检查哪个预测指的是哪个图像(观察)。我在这个问题上看到了一些线索:github medium 1 medium 2 .

尽管如此，我对 Keras 和 Python 还是个新手，我很难在 R 中应用建议的解决方案。在 predict_generator 输出中跟踪哪个预测引用了测试集中的哪个图像的最简单方法是什么？

Answer 1

我想通了，答案很简单。改组是由参数 shuffle 引起的，默认情况下设置为 true。更改后，预测对应于 test_image_array_gen$filenames 的顺序。但是，请记住，预测(和文件名)的顺序与 Windows 上的不同，这可能有点困惑。 p>

Windows 中的顺序:照片 1 照片 2 ... 照片 10 照片 11

R 中的顺序:照片 1 照片 10 照片 11 ... 照片 2

# test images
test_image_array_gen <- flow_images_from_directory(test_image_files_path, 
                                                   test_data_gen,
                                                   target_size = target_size,
                                                   class_mode = "categorical",
                                                   classes = view_list,
                                                   seed = 42,
                                                   shuffle = FALSE)

#prediction 
a <- model %>% predict_generator(test_image_array_gen, steps = ceiling(test_samples/32), verbose = 1, workers = 1)

#bind predictions with photos names
b <- cbind.data.frame(a, test_image_array_gen$filenames)