请问, 房价预测 training-model 输出值为什么一直为0呢?

[liuguangqiang]

Epoch 10 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 20 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 30 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 40 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 50 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 60 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 70 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 80 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 90 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 100 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 110 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 120 Loss=0 Model: y = 0x1 + 0x2 + 0
...
...
Epoch 460 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 470 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 480 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 490 Loss=0 Model: y = 0x1 + 0x2 + 0
Epoch 500 Loss=0 Model: y = 0x1 + 0x2 + 0

[ChesterYue]

loss_op = 1 / (2 * len(X_data)) * tf.matmul((y_pred - y), (y_pred - y), transpose_a=True) 1 to 1.0