Tensorflow分類迴歸「分配既需要張量的形狀以匹配」

Question

我想下面的分類圖表轉換成迴歸，而不是讓，而不是3個值返回只有一個值 -

baseFeatureSize = 5 
keep_prob = tf.placeholder(tf.float32) 
x = tf.placeholder(tf.float32, shape=[None, 64]) 
x_image = tf.reshape(x, [-1, 8, 8, 1]) 
W_conv1 = weight_variable([5, 5, 1, baseFeatureSize]) 
b_conv1 = bias_variable([baseFeatureSize]) 
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) 
W_conv2 = weight_variable([8, 8, baseFeatureSize, baseFeatureSize * 2]) 
b_conv2 = bias_variable([baseFeatureSize * 2]) 
h_conv2 = tf.nn.relu(conv2d(h_conv1, W_conv2) + b_conv2) 
W_fc1 = weight_variable([8 * 8 * baseFeatureSize * 2, baseFeatureSize * 4]) 
b_fc1 = bias_variable([baseFeatureSize * 4]) 
h_pool2_flat = tf.reshape(h_conv2, [-1, 8 * 8 * baseFeatureSize * 2]) 
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) 
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

W_fc3 = weight_variable([baseFeatureSize * 4, 3]) 
b_fc3 = bias_variable([3]) 
y_policy = tf.placeholder(tf.float32, shape=[None, 3]) 
y_policy_conv = tf.matmul(h_fc1, W_fc3) + b_fc3 
cross_entropy_policy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_policy, logits=y_policy_conv)) 
train_step_policy = tf.train.AdamOptimizer(learning_rate = 0.01).minimize(cross_entropy_policy) 

對於它作爲迴歸工作，我已經改變了完全連接的部分 - W_fc3，b_fc3，輸出，交叉熵和train_step使得張量的形狀尺寸爲1而不是3，如下所示（圖的其餘部分保持不變） -

W_fc3 = weight_variable([baseFeatureSize * 4, 1]) 
b_fc3 = bias_variable([1]) 
y_policy = tf.placeholder(tf.float32, shape=[None, 1]) 
y_policy_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc3) + b_fc3) 
cross_entropy_policy = tf.reduce_mean(-tf.reduce_sum(y_policy * tf.log(y_policy_conv), reduction_indices=1)) 
train_step_policy = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy_policy) 

但它一直拋出以下錯誤 -

InvalidArgumentError（請參閱上面的回溯）：分配要求兩個張量的形狀要匹配。 lhs shape = [1] rhs shape = [3]

我無法在任何地方看到3。什麼可能是錯的？

Answer 1

以供將來參考：看到評論被阿基里斯：

對不起，我只是意識到發生了什麼事。主管的logdir指向該模型的以前版本（分類版本）。我指出它是一個空的logdir，它工作。感謝您查看它。 - 跟腱