保存 prediction_generator 导致 tensorflow 和 python

Question

假设，我们在 TensorFlow 流中拟合了一个模型

model.fit(
    train_generator,
    epochs=epochs,
    verbose=1,
    steps_per_epoch=steps_per_epoch,
    validation_data=valid_generator,
    validation_steps=val_steps_per_epoch).history

在下一步中，我们生成预测。

 Y_pred = model.predict_generator(valid_generator, np.ceil(valid_generator.samples / valid_generator.batch_size))

我想知道是否可以保存预测并从磁盘加载它们以调试后续代码，而无需在每次重启后重新训练模型和预测数据。

当然，可以保存和加载模型，但在预测上仍然存在一些开销。

非常感谢任何想法。提前致谢

Answer 1

根据我在评论框中的理解，这里有一些可能的解决方案，请告诉我它是否适合你。

I'm wondering if it is possible to save predictions and load them from disk for debugging subsequent code without retraining the model and predicting the data each time after each restart.

首先，我们建立一个模型并先训练它。

import tensorflow as tf 

# Model 
input = tf.keras.Input(shape=(28, 28))
base_maps = tf.keras.layers.Flatten(input_shape=(28, 28))(input)
base_maps = tf.keras.layers.Dense(128, activation='relu')(base_maps)
base_maps = tf.keras.layers.Dense(units=10, activation='softmax', name='primary')(base_maps) 
model = tf.keras.Model(inputs=[input], outputs=[base_maps])

# compile 
model.compile(
    loss = tf.keras.losses.CategoricalCrossentropy(),
    metrics = ['accuracy'],
    optimizer = tf.keras.optimizers.Adam(learning_rate=1e-3) )

# data 
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = tf.divide(x_train, 255)
y_train = tf.one_hot(y_train , depth=10) 

# customized fit 
model.fit(x_train, y_train, batch_size=512, epochs=3, verbose = 1)

接下来，我们使用这个经过训练的模型来预测看不见的数据 (x_test) 并将预测保存到磁盘，以便我们以后可以调试模型性能问题。

import numpy as np 
import pandas as pd 

y_pred = model.predict(x_test)       # get prediction 
y_pred = np.argmax(y_pred, axis=-1)  # get class labels

# save ground truth and prediction to local disk as CSV file
oof = pd.DataFrame(dict(
           gt = y_test, 
           pd   = y_pred, 
     ))
oof.to_csv('oof.csv', index=False)
oof.head(20)

# compute how many prediction are accurate or match 
oof['check'] = np.where((oof['gt'] == oof['pd']), 'Match', 'No Match')
oof.check.value_counts()
Match       9492
No Match     508
Name: check, dtype: int64

像这样，我们可以从模型预测和ground truth做各种类型的分析。然而，为了保存概率（而不是实际的标签），我们也可以这样做：reference.

y_pred = model.predict(x_test)
np.savetxt("y_pred.csv", y_pred , delimiter=",")

保存 prediction_generator 导致 tensorflow 和 python

Saving prediction_generator results in tensorflow and python

python

prediction

deep-learning

tensorflow

tensorflow2.0