我正在尝试构建和训练一个模型来预测美国手语（使用Sign Language MNIST数据集）。到目前为止，我已经成功构建了模型，并使用该模型对训练数据集进行了预测。训练图像的准确率也超过了70%。现在我想使用训练好的模型对单张图像进行预测。但问题是预测结果（类名）是错误的。我参考了这个内核。我希望能够预测任何给定图像的手语符号。
以下是代码
train = pd.read_csv('../asl_data_train/sign-language-mnist/sign-mnist-train.csv')test = pd.read_csv('../asl_data_train/sign-language-mnist/sign-mnist-test.csv')train.head()train.shapelabels = train['label'].valuesunique_val = np.array(labels)np.unique(unique_val)plt.figure(figsize = (18,8))sns.countplot(x =labels)train.drop('label', axis = 1, inplace = True)images = train.valuesimages = np.array([np.reshape(i, (28, 28)) for i in images])images = np.array([i.flatten() for i in images])label_binrizer = LabelBinarizer()labels = label_binrizer.fit_transform(labels)plt.imshow(images[0].reshape(28,28))x_train, x_test, y_train, y_test = train_test_split(images, labels, test_size = 0.3, random_state = 101)batch_size = 128num_classes = 24epochs = 50x_train = x_train / 255x_test = x_test / 255x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)plt.imshow(x_train[0].reshape(28,28))构建模型的代码
model = Sequential()model.add(Conv2D(64, kernel_size=(3,3), activation = 'relu', input_shape=(28,28,1) ))model.add(MaxPooling2D(pool_size = (2, 2)))model.add(Conv2D(64, kernel_size = (3, 3), activation = 'relu'))model.add(MaxPooling2D(pool_size = (2, 2)))model.add(Conv2D(64, kernel_size = (3, 3), activation = 'relu'))model.add(MaxPooling2D(pool_size = (2, 2)))model.add(Flatten())model.add(Dense(128, activation = 'relu'))model.add(Dropout(0.20))model.add(Dense(num_classes, activation = 'softmax'))model.compile(loss = keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adam(), metrics=['accuracy'])history = model.fit(x_train, y_train, validation_data = (x_test, y_test), epochs=epochs, batch_size=batch_size)model.save("testmodel.h5")对测试图像进行预测
plt.plot(history.history['acc'])plt.plot(history.history['val_acc'])plt.title("Accuracy")plt.xlabel('epoch')plt.ylabel('accuracy')plt.legend(['train','test'])plt.show()test_labels = test['label']test.drop('label', axis = 1, inplace = True)test_images = test.valuestest_images = np.array([np.reshape(i, (28, 28)) for i in test_images])test_images = np.array([i.flatten() for i in test_images])test_labels = label_binrizer.fit_transform(test_labels)test_images = test_images.reshape(test_images.shape[0], 28, 28, 1)test_images.shapey_pred = model.predict(test_images)accuracy_score(test_labels, y_pred.round())在这里我得到了大约0.8的准确率…
这是我尝试使用单张图像预测手语符号的方式
model = load_model("testmodel.h5")test_image = image.load_img('a.jpg',color_mode="grayscale",target_size=(28,28,1))print(test_image.format)print(test_image.mode)print(test_image.size)test_image = image.img_to_array(test_image)test_image = test_image / 255test_image = test_image.reshape((-1,) + test_image.shape)print(test_image.dtype)print(test_image.shape)y_pred = model.predict_classes(test_image)print(y_pred)classname = y_pred[0]print("Class: ",classname)在这里我得到了类名，但例如对于字母”A”（a.jpg），我得到了类6。我在这里做错了什么..请指导我正确的方向。
回答：
图像”a.jpg”是同一数据集的一部分吗？
如果答案是否定的 -> 你应该记住，NN只能预测与训练图像具有相似特征的图像。如果NN是用多种类型的图像训练的，它可以预测更广泛的图像，但如果NN是用非常静态的数据集（白色背景，相同大小，手部居中等）训练的，那么如果输入图像与训练图像非常不同，它就会失败。
如果答案是肯定的 -> 如果你得到了80%的准确率，该图像可能被错误分类。如果你使用了一组测试数据来验证你的NN，你必须通过将它们作为一个整体或逐个传递它们来获得相同的结果。
