keras topN显示,自编写代码

短命女 2022-05-27 12:10 100阅读 0赞

对于使用已经训练好的模型，比如VGG,RESNET等，keras都自带了一个keras.applications.imagenet\_utils.decode\_predictions的方法,有很多限制:

def decode_predictions(preds, top=5):
        """Decodes the prediction of an ImageNet model. # Arguments preds: Numpy tensor encoding a batch of predictions. top: Integer, how many top-guesses to return. # Returns A list of lists of top class prediction tuples `(class_name, class_description, score)`. One list of tuples per sample in batch input. # Raises ValueError: In case of invalid shape of the `pred` array (must be 2D). """
        global CLASS_INDEX
        if len(preds.shape) != 2 or preds.shape[1] != 1000:
            raise ValueError('`decode_predictions` expects '
                             'a batch of predictions '
                             '(i.e. a 2D array of shape (samples, 1000)). '
                             'Found array with shape: ' + str(preds.shape))
        if CLASS_INDEX is None:
            fpath = get_file('imagenet_class_index.json',
                             CLASS_INDEX_PATH,
                             cache_subdir='models',
                             file_hash='c2c37ea517e94d9795004a39431a14cb')
            with open(fpath) as f:
                CLASS_INDEX = json.load(f)
        results = []
        for pred in preds:
            top_indices = pred.argsort()[-top:][::-1]
            result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
            result.sort(key=lambda x: x[2], reverse=True)
            results.append(result)
        return results

把重要的东西挖出来，然后自己敲,这样就OK了，下例以MNIST数据集为例:

import keras
    from keras.models import Sequential
    from keras.layers import Dense
    import numpy as np
    import tflearn
    import tflearn.datasets.mnist as mnist
    
    def decode_predictions_custom(preds, top=5):
        CLASS_CUSTOM = ["0","1","2","3","4","5","6","7","8","9"]
        results = []
        for pred in preds:
            top_indices = pred.argsort()[-top:][::-1]
            result = [tuple(CLASS_CUSTOM[i]) + (pred[i]*100,) for i in top_indices]
            results.append(result)
        return results
    
    x_train, y_train, x_test, y_test = mnist.load_data(one_hot=True)
    
    model = Sequential()
    model.add(Dense(units=64, activation='relu', input_dim=784))
    model.add(Dense(units=10, activation='softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer='sgd',
                  metrics=['accuracy'])
    model.fit(x_train, y_train, epochs=10, batch_size=128)
    # score = model.evaluate(x_test, y_test, batch_size=128)
    # print(score)
    preds = model.predict(x_test[0:1,:])
    p = decode_predictions_custom(preds)
    for (i,(label,prob)) in enumerate(p[0]):
        print("{}. {}: {:.2f}%".format(i+1, label,prob))  
    # 1. 7: 99.43%
    # 2. 9: 0.24%
    # 3. 3: 0.23%
    # 4. 0: 0.05%
    # 5. 2: 0.03%