我正在尝试构建双子CNN,我的数据库有两个输入,最终合并在一起,输出为IC50的单个神经元。
当我尝试这样做时,我得到了0的准确率,而损失值是正常的。我是否使用了错误的损失函数?当前使用的是mean_squared_error
操作系统:Windows 10
TensorFlow版本:2.3.0
我的代码:
encoded_drugs=np.load('encoded_drugs.npy')encoded_cells=np.load('encoded_cells.npy')encoded_ICs=np.load('encoded_ICs.npy')encoded_drugs_train, encoded_drugs_test,encoded_cells_train, encoded_cells_test, encoded_ICs_train, encoded_ICs_test = train_test_split(encoded_drugs,encoded_cells, encoded_ICs, test_size=0.2)input1=keras.layers.Input(shape=(139,32,))x1=keras.layers.Flatten(input_shape=(139,32,))(input1)x2=keras.layers.Dense(64,activation='relu')(x1)x3=keras.layers.Dense(64,activation='relu')(x2)input2=keras.layers.Input(shape=(735,2,))y1=keras.layers.Flatten(input_shape=(735,2,))(input2)y2=keras.layers.Dense(128,activation='relu')(y1)y3=keras.layers.Dense(64,activation='relu')(y2)merged=keras.layers.concatenate([x3,y3],axis=-1)z=keras.layers.Dense(64,activation='relu')(merged)out=keras.layers.Dense(1,activation='sigmoid')(z)model=keras.models.Model(inputs=[input1,input2], outputs=out)model.compile(optimizer='sgd',loss='mean_squared_error',metrics=['accuracy'])model.fit([encoded_drugs_train,encoded_cells_train],encoded_ICs_train,validation_split = 0.2,epochs=2)test_loss, test_accuracy= model.evaluate([encoded_drugs_test,encoded_cells_test],encoded_ICs_test)print('Accuracy=', test_accuracy)
我的输出:
2020-02-18 11:06:00.759824: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations: AVX AVX2To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags.2020-02-18 11:06:00.774869: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.Train on 75793 samples, validate on 18949 samplesEpoch 1/275793/75793 [==============================] - 17s 229us/sample - loss: 10.3671 - accuracy: 0.0000e+00 - val_loss: 10.4082 - val_accuracy: 0.0000e+00Epoch 2/275793/75793 [==============================] - 11s 146us/sample - loss: 10.2673 - accuracy: 0.0000e+00 - val_loss: 10.3852 - val_accuracy: 0.0000e+003s 125us/sample - loss: 8.3239 - accuracy: 0.0000e+00Accuracy= 0.0
回答:
您正在尝试解决一个回归问题(使用mean_squared_error
损失函数),但却使用了准确率作为评估指标。在这种情况下,准确率不是一个有效的评估指标。
首先,请确保您要解决的问题确实是回归还是分类问题。
如果是回归问题,请使用Dense(1,activation='linear')
作为最后一层输出层,并使用model.compile(optimizer='sgd',loss='mean_squared_error',metrics=['mse'])
。
如果是分类问题,请使用Dense(1,activation='sigmoid')
作为最后一层输出层,并使用model.compile(optimizer='sgd',loss='binary_crossentropy',metrics=['accuracy'])
。
其次,您需要训练更多的轮次(29秒真的不足以提供对结果的全面了解)。