python - 我的 CNN Keras 预测不正确，我不知道该怎么办

Question

我必须做一个 CNN 来诊断第 4 阶段的糖尿病性视网膜病变(二元分类 - 或 0 (non4thStage - nonPdr)，或 1 (4thStage - pdr))我正在使用 vgg16 和 gaussianBlur 来更好地分类。我有 1400 张测试图像(每类 700 张)，这是我的 train.py:

#import tensorflow as tf
import cv2
import os
import numpy as np

from keras.layers.core import Flatten, Dense, Dropout, Reshape
from keras.models import Model
from keras.layers import Input, ZeroPadding2D, Dropout
from keras import optimizers
from keras.optimizers import SGD
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import EarlyStopping

from keras.applications.vgg16 import VGG16

TRAIN_DIR = 'train/'
TEST_DIR = 'test/'
v = 'v/'
BATCH_SIZE = 32
NUM_EPOCHS = 5


def ReadImages(Path):
    LabelList = list()
    ImageCV = list()
    classes = ["nonPdr", "pdr"]

    # Get all subdirectories
    FolderList = [f for f in os.listdir(Path) if not f.startswith('.')]

    # Loop over each directory
    for File in FolderList:
        for index, Image in enumerate(os.listdir(os.path.join(Path, File))):
            # Convert the path into a file
            ImageCV.append(cv2.resize(cv2.imread(os.path.join(Path, File) + os.path.sep + Image), (224,224)))
            LabelList.append(classes.index(os.path.splitext(File)[0])) 


            ImageCV[index] = cv2.addWeighted (ImageCV[index],4,cv2.GaussianBlur(ImageCV[index] , (0,0) , 10) ,-4 ,128)
    return ImageCV, LabelList


data, labels = ReadImages(TRAIN_DIR)
valid, vlabels = ReadImages(TEST_DIR)

vgg16_model = VGG16(weights="imagenet", include_top=True)

# (2) remove the top layer
base_model = Model(input=vgg16_model.input, 
                   output=vgg16_model.get_layer("block5_pool").output)

# (3) attach a new top layer
base_out = base_model.output
base_out = Reshape((25088,))(base_out)
top_fc1 = Dense(64, activation="relu")(base_out)
top_fc1 = Dropout(0.50)(base_out)
# output layer: (None, 5)
top_preds = Dense(1, activation="sigmoid")(top_fc1)

# (4) freeze weights until the last but one convolution layer (block4_pool)
for layer in base_model.layers[0:14]:
    layer.trainable = False

# (5) create new hybrid model
model = Model(input=base_model.input, output=top_preds)

# (6) compile and train the model
sgd = SGD(lr=0.000001, momentum=0.9)
model.compile(optimizer=sgd, loss="binary_crossentropy", metrics=["accuracy"])

data = np.asarray(data)
valid = np.asarray(valid)

data = data.astype('float32')
valid = valid.astype('float32')

data /= 255
valid /= 255
labels = np.array(labels)

datagen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True)

# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(data)
mean = datagen.mean  
std = datagen.std

print(mean, "mean")
print(std, "std")

es = EarlyStopping(monitor='val_loss', verbose=1)

# fits the model on batches with real-time data augmentation:
model.fit_generator(datagen.flow(data, np.array(labels), batch_size=32), 
                    steps_per_epoch=len(data) / 32, epochs=50,
                    validation_data=(valid, np.array(vlabels)),
                    nb_val_samples=72, callbacks=[es])


model.save('model.h5')

这将返回以下内容:

Epoch 1/50
44/43 [==============================] - 475s 11s/step - loss: 0.9671 - acc: 0.4789 - val_loss: 0.6808 - val_acc: 0.6389
Epoch 2/50
44/43 [==============================] - 467s 11s/step - loss: 0.8427 - acc: 0.5007 - val_loss: 0.6364 - val_acc: 0.6389
Epoch 3/50
44/43 [==============================] - 468s 11s/step - loss: 0.7703 - acc: 0.5204 - val_loss: 0.6136 - val_acc: 0.6806
Epoch 4/50
44/43 [==============================] - 466s 11s/step - loss: 0.7324 - acc: 0.5512 - val_loss: 0.5941 - val_acc: 0.7500
Epoch 5/50
44/43 [==============================] - 466s 11s/step - loss: 0.7074 - acc: 0.5679 - val_loss: 0.5758 - val_acc: 0.7639
Epoch 6/50
44/43 [==============================] - 461s 10s/step - loss: 0.6640 - acc: 0.6146 - val_loss: 0.5584 - val_acc: 0.8194
Epoch 7/50
44/43 [==============================] - 455s 10s/step - loss: 0.6562 - acc: 0.6077 - val_loss: 0.5418 - val_acc: 0.8333
Epoch 8/50
44/43 [==============================] - 458s 10s/step - loss: 0.6076 - acc: 0.6700 - val_loss: 0.5263 - val_acc: 0.8889
Epoch 9/50
44/43 [==============================] - 456s 10s/step - loss: 0.5743 - acc: 0.7005 - val_loss: 0.5119 - val_acc: 0.9167
Epoch 10/50
44/43 [==============================] - 457s 10s/step - loss: 0.5649 - acc: 0.7041 - val_loss: 0.4981 - val_acc: 0.9306
Epoch 11/50
44/43 [==============================] - 452s 10s/step - loss: 0.5654 - acc: 0.7088 - val_loss: 0.4855 - val_acc: 0.9444
Epoch 12/50
44/43 [==============================] - 458s 10s/step - loss: 0.5046 - acc: 0.7616 - val_loss: 0.4740 - val_acc: 0.9444
Epoch 13/50
44/43 [==============================] - 465s 11s/step - loss: 0.5002 - acc: 0.7808 - val_loss: 0.4633 - val_acc: 0.9444
Epoch 14/50
44/43 [==============================] - 459s 10s/step - loss: 0.4694 - acc: 0.7924 - val_loss: 0.4514 - val_acc: 0.9583
Epoch 15/50
44/43 [==============================] - 463s 11s/step - loss: 0.4482 - acc: 0.8184 - val_loss: 0.4432 - val_acc: 0.9444
Epoch 16/50
44/43 [==============================] - 456s 10s/step - loss: 0.4326 - acc: 0.8343 - val_loss: 0.4330 - val_acc: 0.9583
Epoch 17/50
44/43 [==============================] - 454s 10s/step - loss: 0.4291 - acc: 0.8303 - val_loss: 0.4233 - val_acc: 0.9583
Epoch 18/50
44/43 [==============================] - 457s 10s/step - loss: 0.4060 - acc: 0.8376 - val_loss: 0.4145 - val_acc: 0.9583
Epoch 19/50
44/43 [==============================] - 457s 10s/step - loss: 0.3933 - acc: 0.8686 - val_loss: 0.4069 - val_acc: 0.9583
Epoch 20/50
44/43 [==============================] - 455s 10s/step - loss: 0.3786 - acc: 0.8684 - val_loss: 0.3985 - val_acc: 0.9583
Epoch 21/50
44/43 [==============================] - 456s 10s/step - loss: 0.3661 - acc: 0.8774 - val_loss: 0.3902 - val_acc: 0.9583
Epoch 22/50
44/43 [==============================] - 454s 10s/step - loss: 0.3493 - acc: 0.8956 - val_loss: 0.3833 - val_acc: 0.9583
Epoch 23/50
44/43 [==============================] - 456s 10s/step - loss: 0.3355 - acc: 0.9065 - val_loss: 0.3765 - val_acc: 0.9444
Epoch 24/50
44/43 [==============================] - 456s 10s/step - loss: 0.3332 - acc: 0.9053 - val_loss: 0.3680 - val_acc: 0.9583
Epoch 25/50
44/43 [==============================] - 457s 10s/step - loss: 0.3236 - acc: 0.9160 - val_loss: 0.3625 - val_acc: 0.9444
Epoch 26/50
44/43 [==============================] - 458s 10s/step - loss: 0.3097 - acc: 0.9181 - val_loss: 0.3559 - val_acc: 0.9583
Epoch 27/50
44/43 [==============================] - 469s 11s/step - loss: 0.2915 - acc: 0.9242 - val_loss: 0.3517 - val_acc: 0.9444
Epoch 28/50
44/43 [==============================] - 473s 11s/step - loss: 0.2832 - acc: 0.9368 - val_loss: 0.3454 - val_acc: 0.9583
Epoch 29/50
44/43 [==============================] - 468s 11s/step - loss: 0.2747 - acc: 0.9418 - val_loss: 0.3416 - val_acc: 0.9583
Epoch 30/50
44/43 [==============================] - 470s 11s/step - loss: 0.2627 - acc: 0.9508 - val_loss: 0.3350 - val_acc: 0.9722
Epoch 31/50
44/43 [==============================] - 469s 11s/step - loss: 0.2517 - acc: 0.9638 - val_loss: 0.3311 - val_acc: 0.9722
Epoch 32/50
44/43 [==============================] - 470s 11s/step - loss: 0.2517 - acc: 0.9484 - val_loss: 0.3266 - val_acc: 0.9722
Epoch 33/50
44/43 [==============================] - 490s 11s/step - loss: 0.2348 - acc: 0.9560 - val_loss: 0.3211 - val_acc: 0.9722
Epoch 34/50
44/43 [==============================] - 461s 10s/step - loss: 0.2427 - acc: 0.9517 - val_loss: 0.3158 - val_acc: 0.9722
Epoch 35/50
44/43 [==============================] - 467s 11s/step - loss: 0.2260 - acc: 0.9616 - val_loss: 0.3109 - val_acc: 0.9722
Epoch 36/50
44/43 [==============================] - 459s 10s/step - loss: 0.2243 - acc: 0.9706 - val_loss: 0.3064 - val_acc: 0.9722
Epoch 37/50
44/43 [==============================] - 456s 10s/step - loss: 0.2099 - acc: 0.9687 - val_loss: 0.3029 - val_acc: 0.9722
Epoch 38/50
44/43 [==============================] - 457s 10s/step - loss: 0.2094 - acc: 0.9733 - val_loss: 0.2994 - val_acc: 0.9722
Epoch 39/50
44/43 [==============================] - 465s 11s/step - loss: 0.2014 - acc: 0.9744 - val_loss: 0.2941 - val_acc: 0.9722
Epoch 40/50
44/43 [==============================] - 465s 11s/step - loss: 0.1924 - acc: 0.9709 - val_loss: 0.2915 - val_acc: 0.9722
Epoch 41/50
44/43 [==============================] - 457s 10s/step - loss: 0.1908 - acc: 0.9735 - val_loss: 0.2897 - val_acc: 0.9722
Epoch 42/50
44/43 [==============================] - 463s 11s/step - loss: 0.1864 - acc: 0.9709 - val_loss: 0.2861 - val_acc: 0.9722
Epoch 43/50
44/43 [==============================] - 464s 11s/step - loss: 0.1787 - acc: 0.9773 - val_loss: 0.2822 - val_acc: 0.9722
Epoch 44/50
44/43 [==============================] - 468s 11s/step - loss: 0.1820 - acc: 0.9744 - val_loss: 0.2794 - val_acc: 0.9722
Epoch 45/50
44/43 [==============================] - 469s 11s/step - loss: 0.1646 - acc: 0.9818 - val_loss: 0.2763 - val_acc: 0.9722
Epoch 46/50
44/43 [==============================] - 469s 11s/step - loss: 0.1689 - acc: 0.9820 - val_loss: 0.2730 - val_acc: 0.9722
Epoch 47/50
44/43 [==============================] - 471s 11s/step - loss: 0.1495 - acc: 0.9879 - val_loss: 0.2711 - val_acc: 0.9722
Epoch 48/50
44/43 [==============================] - 469s 11s/step - loss: 0.1578 - acc: 0.9858 - val_loss: 0.2676 - val_acc: 0.9722
Epoch 49/50
44/43 [==============================] - 462s 10s/step - loss: 0.1557 - acc: 0.9858 - val_loss: 0.2643 - val_acc: 0.9722
Epoch 50/50
44/43 [==============================] - 454s 10s/step - loss: 0.1501 - acc: 0.9794 - val_loss: 0.2612 - val_acc: 0.9722

这是我的预测.py:

from keras.models import load_model
import cv2
import os
import numpy as np
from keras.preprocessing import image

TEST_DIR = 'v/'
pdr = 0
nonPdr = 0

model = load_model('model.h5')

def normalize(x, mean, std):
    x[..., 0] -= mean[0]
    x[..., 1] -= mean[1]
    x[..., 2] -= mean[2]
    x[..., 0] /= std[0]
    x[..., 1] /= std[1]
    x[..., 2] /= std[2]
    return x

for filename in os.listdir(r'v/'):
    if filename.endswith(".jpg") or filename.endswith(".ppm") or filename.endswith(".jpeg") or filename.endswith(".png"):
        ImageCV = cv2.resize(cv2.imread(os.path.join(TEST_DIR) + filename), (224,224))
        ImageCV = cv2.addWeighted (ImageCV,4,cv2.GaussianBlur(ImageCV , (0,0) , 10) ,-4 ,128)
        ImageCV = np.asarray(ImageCV)

        ImageCV = ImageCV.astype('float32')

        ImageCV /= 255  
        x = ImageCV

        x = np.expand_dims(x, axis=0)
        x = normalize(x, [0.23883381, 0.23883381, 0.23883381], [0.24483591, 0.24579705, 0.2510857])

        prob = model.predict(x)
        if prob <= 0.75:  #.75 = 80% | .70=79% >>>> .70 = 82% | .75 = 79%
            print("nonPDR >>>", filename)
            nonPdr += 1
        else:
            print("PDR >>>", filename)
            pdr += 1
        print(prob)
print("Number of retinas with PDR: ",pdr)
print("Number of retinas without PDR: ",nonPdr)

问题是:在火车返回大约 97% 的准确率后，我所有的预测都是错误的...例如，这 3 张图像必须是 PDR(class1):

nonPDR >>> 16_left.jpeg
[[0.07062916]]
nonPDR >>> 16_right.jpeg
[[0.09434311]]
nonPDR >>> 217_left.jpeg
[[0.14126943]]

如果我测试我放在火车基地的相同图像，该模型也无法正确预测...

我已经尝试在没有 gaussianBlur 的情况下进行训练，但准确度很差。

我做错了什么？拜托，我感谢你的帮助!!

Answer 1

有几件事可以尝试:我建议在您确信自己的训练过程正在运行之前不要使用数据增强，即使最初的表现并不好。作为双重检查，您可能希望在 model.fit 之后直接使用训练数据进行预测，只是为了验证生成的准确度与您在训练中获得的准确度相同。您可能在导致网络表现不佳的测试数据处理过程中存在一些细微差异，因此首先要说服自己训练部分没问题，然后您可以专注于测试部分。我希望这会有所帮助。