ValueError:检查输入时出错:预期input_1具有4维,但数组的形状为(83,1)

时间:2019-08-04 21:30:11

标签: python tensorflow keras resnet

我想找到模型的概率,以便稍后找到AUC和ROC,但出现此错误:

  

ValueError:检查输入时出错:预期input_1具有4   尺寸,但数组的形状为(83,1)

我的代码:

def create_resnet(img_dim,CHANNEL,n_class):
    input_tensor=Input(shape=(img_dim, img_dim,CHANNEL))

    base_model = ResNet50(weights=None, include_top=False, input_tensor=input_tensor)
    base_model.load_weights('D:/Diabetic retinopathy data set/ResNet50/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5')

    x=GlobalAveragePooling2D()(base_model.output)
    x=Dropout(0.3)(x)
    x=Dense(1024, activation=relu)(x)
    x=Dropout(0.2)(x)
    x=Dense(512, activation=relu)(x)
    x=Dropout(0.2)(x)
    x=BatchNormalization()(x)
    output_layer=Dense(n_class,activation='softmax', name="Output_Layer")(x)
    model_resnet =Model(input_tensor, output_layer)

    return model_resnet

model_resnet=create_resnet(IMG_DIM,CHANNEL_SIZE, NUM_CLASSES)

0 个答案:

没有答案