为什么我的神经网络在训练后会做出如此不准确的预测？

Question

我一直在研究我找到的用于制作对象分类器的指南。我的分类器的工作是确定它正在查看的图像是否是动漫，因为我想将其集成到一个机器人中，该机器人将在群聊中标记动漫。训练后网络输出的图表显示了不错但可改进的结果，但分类脚本似乎一点也不准确。我的数据集是 1000 张图像，here is the chart of my last training attempt。 如您所见，val_loss 值相当可行，但波动很大。

在训练和保存权重后，我正在为训练模型提供 2 张图像以对其进行测试，一张normal houseplant 的图像和一张generic anime girl 的图像。该模型预测室内植物的动漫为 0.37%，动漫照片的动漫为 0.00%。这些照片在视觉上类似于它们各自的数据集，即“动漫”和“其他”（包括汽车、植物、房屋和其他“随机”对象的图像）。这些图像由它们的子文件夹标记。

这是我的模型的代码：

from tensorflow.keras.layers import BatchNormalization
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import Activation
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Dense
from tensorflow.keras import backend as K

class SmallerVGGNet:
    @staticmethod
    def build(width, height, depth, classes):
        # initialize the model along with the input shape to be
        # "channels last" and the channels dimension itself
        model = Sequential()
        inputShape = (height, width, depth)
        chanDim = -1
        # if we are using "channels first", update the input shape
        # and channels dimension
        if K.image_data_format() == "channels_first":
            inputShape = (depth, height, width)
            chanDim = 1


        # CONV => RELU => POOL
        model.add(Conv2D(32, (3, 3), padding="same",
            input_shape=inputShape))
        model.add(Activation("relu"))
        model.add(BatchNormalization(axis=chanDim))
        model.add(MaxPooling2D(pool_size=(3, 3)))
        model.add(Dropout(0.25))

        # (CONV => RELU) * 2 => POOL
        model.add(Conv2D(64, (3, 3), padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(axis=chanDim))
        model.add(Conv2D(64, (3, 3), padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(axis=chanDim))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.25))

        # (CONV => RELU) * 2 => POOL
        model.add(Conv2D(128, (3, 3), padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(axis=chanDim))
        model.add(Conv2D(128, (3, 3), padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(axis=chanDim))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.25))

        # first (and only) set of FC => RELU layers
        model.add(Flatten())
        model.add(Dense(1024))
        model.add(Activation("relu"))
        model.add(BatchNormalization())
        model.add(Dropout(0.5))

        # 1 node
        model.add(Dense(1))
        model.add(Activation("sigmoid"))

        return model 

我的教练：

import matplotlib
matplotlib.use("Agg")
# import the necessary packages
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.image import img_to_array
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from pyimagesearch.smallervggnet import SmallerVGGNet
import matplotlib.pyplot as plt
from imutils import paths
import numpy as np
import argparse
import random
import pickle
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True,
    help="path to input dataset (i.e., directory of images)")
ap.add_argument("-m", "--model", required=True,
    help="path to output model")
ap.add_argument("-l", "--labelbin", required=True,
    help="path to output label binarizer")
ap.add_argument("-p", "--plot", type=str, default="plot.png",
    help="path to output accuracy/loss plot")
args = vars(ap.parse_args())

# initialize the number of epochs to train for, initial learning rate,
# batch size, and image dimensions
EPOCHS = 100
INIT_LR = 1e-3
BS = 32
IMAGE_DIMS = (96, 96, 3)
# initialize the data and labels
data = []
labels = []
# grab the image paths and randomly shuffle them
print("Output: loading images...")
imagePaths = sorted(list(paths.list_images(args["dataset"])))
random.seed(42)
random.shuffle(imagePaths)

# loop over the input images
for imagePath in imagePaths:
    # load the image, pre-process it, and store it in the data list
    image = cv2.imread(imagePath)
    image = cv2.resize(image, (IMAGE_DIMS[1], IMAGE_DIMS[0]))
    image = img_to_array(image)
    data.append(image)
    # extract the class label from the image path and update the
    # labels list
    label = imagePath.split(os.path.sep)[-2]
    labels.append(label)


    # scale the raw pixel intensities to the range [0, 1]
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
print("Output: data matrix: {:.2f}MB".format(
    data.nbytes / (1024 * 1000.0)))

# binarize the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)

# partition the data into training and testing splits using 80% of
# the data for training and the remaining 20% for testing
(trainX, testX, trainY, testY) = train_test_split(data,
    labels, test_size=0.2, random_state=42)

    # construct the image generator for data augmentation
aug = ImageDataGenerator(rotation_range=45, width_shift_range=0.1,
    height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
    horizontal_flip=True, fill_mode="nearest")

# initialize the model
print("Output: compiling model...")
model = SmallerVGGNet.build(width=IMAGE_DIMS[1], height=IMAGE_DIMS[0],
    depth=IMAGE_DIMS[2], classes=len(lb.classes_))
opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss="binary_crossentropy", optimizer=opt,
    metrics=["accuracy"])
# train the network
print("Output: training network...")
H = model.fit(
    x=aug.flow(trainX, trainY, batch_size=BS),
    validation_data=(testX, testY),
    steps_per_epoch=len(trainX) // BS,
    epochs=EPOCHS, verbose=1)

    # save the model to disk
print("Output: serializing network...")
model.save(args["model"], save_format="h5")
# save the label binarizer to disk
print("Output: serializing label binarizer...")
f = open(args["labelbin"], "wb")
f.write(pickle.dumps(lb))
f.close()

最后，我的分类器：

import tensorflow
from keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
import numpy as np
import argparse
import imutils
import pickle
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True,
    help="path to trained model model")
ap.add_argument("-l", "--labelbin", required=True,
    help="path to label binarizer")
ap.add_argument("-i", "--image", required=True,
    help="path to input image")
args = vars(ap.parse_args())

# load the image
image = cv2.imread(args["image"])
output = image.copy()

# pre-process the image for classification
image = cv2.resize(image, (96, 96))
image = image.astype("float") / 255.0
image = img_to_array(image)
image = np.expand_dims(image, axis=0)

# load the trained convolutional neural network and the label
# binarizer
print("[INFO] loading network...")
model = load_model(args["model"])
lb = pickle.loads(open(args["labelbin"], "rb").read())

# classify the input image
print("[INFO] classifying image...")
proba = model.predict(image)[0]
idx = np.argmax(proba)
label = lb.classes_[idx]

# correct answer
filename = args["image"][args["image"].rfind(os.path.sep) + 1:]
correct = "correct" if filename.rfind(label) != -1 else "incorrect"

# build the label and draw the label on the image
label = "{}: {:.2f}% ({})".format(label, proba[idx] * 100, correct)
output = imutils.resize(output, width=400)
cv2.putText(output, label, (10, 25),  cv2.FONT_HERSHEY_SIMPLEX,
    0.7, (0, 255, 0), 2)

# show the output image
print("[INFO] {}".format(label))
cv2.imshow("Output", output)
cv2.waitKey(0)

我尝试过的一些事情包括更小的 epoch 数、sigmoid 的替代方法、不同的损失函数以及更具体的类别。

Answer 1

您的模型以带有 sigmoid 激活的单个 Dense 单元结束，但是，您稍后使用 np.argmax() 和标签列表，就像使用 softmax 激活一样。您不小心预测了每个样本的哪个类被标记为“0”。你的模型训练得很好，这就是你之后做出预测的方式。