使用evaluate_generator可获得0％的准确率，但在使用相同数据进行培训时，准确率为75％ - 具体情况如何？

我使用ImageDataGenerator，fit_generator和evaluate_generator遇到了一个非常奇怪的keras模型 .

我正在创建这样的模型：

classes = <list of classes>
num_classes = len(classes)

pretrained_model = Sequential()
pretrained_model.add(ResNet50(include_top=False, weights='imagenet', pooling='avg'))
pretrained_model.add(Dense(num_classes, activation='softmax'))

pretrained_model.layers[0].trainable = False

pretrained_model.compile(
    optimizer='adam',
    loss='categorical_crossentropy',
    metrics=['accuracy']
)

我正在训练它：

idg_final = ImageDataGenerator(
    data_format='channels_last',
    rescale=1./255,
    width_shift_range = 0.2,
    height_shift_range = 0.2,
    rotation_range=15,
)

traing_gen = idg_final.flow_from_directory('./train', classes=classes, target_size=(224, 224), class_mode='categorical')

pretrained_model.fit_generator(traing_gen, epochs=1, verbose=1)

fit_generator 打印 loss: 1.0297 - acc: 0.7546 .

然后，我试图评估 exact same data it was trained on. 上的模型

debug_gen = idg_final.flow_from_directory('./train', target_size=(224, 224), class_mode='categorical', classes=classes, shuffle=True)
print(pretrained_model.evaluate_generator(debug_gen, steps=100))

其中打印 [10.278913383483888, 0.0] .

为什么在相同的精确数据上精度如此不同？

编辑：我还想指出，有时精度高于0.0 . 例如，当我使用经历了五个时期训练的模型时， evaluate_accuracy 返回6％的准确度 .

编辑2：基于下面的答案，我确保训练更多的时期，并且评估的 ImageDataGenerator 没有随机的轮班和轮换 . 我在训练期间仍然获得非常高的准确度，并且在同一数据集的评估期间精度极低 .

我训练像

idg_final = ImageDataGenerator(
    data_format='channels_last',
    rescale=1./255,
    width_shift_range = 0.2,
    height_shift_range = 0.2,
    rotation_range=15,
)

traing_gen = idg_final.flow_from_directory('./train', classes=classes, target_size=(224, 224), class_mode='categorical')                  

pretrained_model.fit_generator(traing_gen, epochs=10, verbose=1)

其中打印以下内容：

Found 9850 images belonging to 4251 classes.
Epoch 1/10
308/308 [==============================] - 3985s 13s/step - loss: 8.9218 - acc: 0.0860
Epoch 2/10
308/308 [==============================] - 3555s 12s/step - loss: 3.2710 - acc: 0.3403
Epoch 3/10
308/308 [==============================] - 3594s 12s/step - loss: 1.8597 - acc: 0.5836
Epoch 4/10
308/308 [==============================] - 3656s 12s/step - loss: 1.2712 - acc: 0.7058
Epoch 5/10
308/308 [==============================] - 3667s 12s/step - loss: 0.9556 - acc: 0.7795
Epoch 6/10
308/308 [==============================] - 3689s 12s/step - loss: 0.7665 - acc: 0.8207
Epoch 7/10
308/308 [==============================] - 3693s 12s/step - loss: 0.6581 - acc: 0.8498
Epoch 8/10
308/308 [==============================] - 3618s 12s/step - loss: 0.5874 - acc: 0.8636
Epoch 9/10
308/308 [==============================] - 3823s 12s/step - loss: 0.5144 - acc: 0.8797
Epoch 10/10
308/308 [==============================] - 4334s 14s/step - loss: 0.4835 - acc: 0.8854

而且我正在评估 exact same dataset

idg_debug = ImageDataGenerator(
    data_format='channels_last',
    rescale=1./255,
)

debug_gen = idg_debug.flow_from_directory('./train', target_size=(224, 224), class_mode='categorical', classes=classes)
print(pretrained_model.evaluate_generator(debug_gen))

其打印精度如下： [10.743386410747084, 0.0001015228426395939]

完整代码是here .