[keras] keras测试

小灰灰 2022-05-12 02:48 215阅读 0赞

#### 加载模型、特征提取 ####

根据InceptionV3提取图片特征

from keras.preprocessing import image
    from keras.applications.inception_v3 import InceptionV3, preprocess_input
    from keras.models import Model, load_model
    from keras.layers import Input
    import numpy as np
    
    class Extractor():
        def __init__(self, weights=None):
            """Either load pretrained from imagenet, or load our saved
            weights from our own training."""
    
            self.weights = weights  # so we can check elsewhere which model
    
            if weights is None:
                # Get model with pretrained weights.
                base_model = InceptionV3(
                    weights='imagenet',
                    include_top=True
                )
    
                # We'll extract features at the final pool layer.
                self.model = Model(
                    inputs=base_model.input,
                    outputs=base_model.get_layer('avg_pool').output
                )
    
            else:
                # Load the model first.
                self.model = load_model(weights)
    
                # Then remove the top so we get features not predictions.
                # From: https://github.com/fchollet/keras/issues/2371
                self.model.layers.pop()
                self.model.layers.pop()  # two pops to get to pool layer
                self.model.outputs = [self.model.layers[-1].output]
                self.model.output_layers = [self.model.layers[-1]]
                self.model.layers[-1].outbound_nodes = []
    
        def extract(self, image_path):
            img = image.load_img(image_path, target_size=(299, 299))
            x = image.img_to_array(img)
            x = np.expand_dims(x, axis=0)
            x = preprocess_input(x)
            # Get the prediction.
            features = self.model.predict(x)
            if self.weights is None:
                # For imagenet/default network:
                features = features[0]
            else:
                # For loaded network:
                features = features[0]
    
            return features

#### evaluate/test\_on\_batch ####

计算精度，不仅需要输入X，还需要输出y，给出的是最终的metric，top1精度或者top5之类的

evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None)
    本函数返回一个测试误差的标量值（如果模型没有其他评价指标），或一个标量的list（如果模型还有其他的评价指标）。model.metrics_names将给出list中各个值的含义。
    metric在函数compile的时候输入
    
    test_on_batch(self, x, y, sample_weight=None)
    
    evaluate_generator(self, generator, steps, max_q_size=10, workers=1, pickle_safe=False)
    生成器应返回与test_on_batch的输入数据相同类型的数据。
    generator：生成输入batch数据的生成器
    val_samples：生成器应该返回的总样本数
    steps：生成器要返回数据的轮数
    max_q_size：生成器队列的最大容量
    nb_worker：使用基于进程的多线程处理时的进程数
    pickle_safe：若设置为True，则使用基于进程的线程。注意因为它的实现依赖于多进程处理，不可传递不可pickle的参数到生成器中，因为它们不能轻易的传递到子进程中。
    
    return : [test loss, metrics]

def evaluate_model(weight_path,model_name):
        rm=Total_Models(total_classes,model_name,optimizer,lr)
        val_generator,train_generator,train_sample,test_sample = generator()
        #6659 2737 9396
        #39882 16390
        rm.model.load_weights(weight_path,by_name=True) #
        acc = rm.model.evaluate_generator(val_generator,2737/32+1)
        print acc

**[mertics](https://keras.io/zh/metrics/)**
    
    ####  predict/predict_on_batch/predict_generator
    只输入X，用法情形与evaluate相同