【发布时间】:2022-02-25 02:49:40
【问题描述】:
我正在尝试对血液及其 spo2 值(血液中的氧百分比)的图像数据进行分类,spo2 值有 4 个类别
X_train.shape => (8969, 224, 224, 3)
y_train.shape => (8969,)
模型的输出将是 spo2 的百分比
y_train.shape
>>> array([98, 98, 95, ..., 98, 95, 98])
模型架构
X_train = np.array(X_train)
y_train = np.array(y_train)
model = Sequential()
model.add(Conv2D(filters=64 , kernel_size=(3,3), activation='relu' , input_shape = (X_train.shape[1:])))
model.add(MaxPool2D(pool_size=(3,3)))
model.add(Conv2D(filters=32 , kernel_size=(3,3), activation='relu'))
model.add(MaxPool2D(pool_size=(3,3)))
model.add(Dense(units=512 , activation='relu'))
model.add(Dense(units=128 , activation='relu'))
model.add(Dense(units=4, activation='softmax'))
model.compile(optimizer='adam' , loss='categorical_crossentropy' , metrics=(['accuracy']))
history = model.fit(X_train , y_train , epochs=5)
拟合模型时出现错误
ValueError: Shapes (None,) and (None, 24, 24, 4) are incompatible
【问题讨论】:
-
如果您edit 包含完整的错误回溯,而不仅仅是最后一行,这可能会有所帮助,因为其中包含有价值的信息
标签: python tensorflow keras deep-learning conv-neural-network