私のバイオ データセットには 20,000 行と 170 個の機能があります。生物活性を予測するためにdnn回帰を行っています。(線形方程式と 2 つの隠れ層を持つ 1 つの単位出力層)。私のCPUでは非常に遅く実行され、非常に悪いr二乗（負）が生成されました。次に、同じネットワーク アーキテクチャの skflow で実行しました。はるかに高速で (100 倍以上)、前回の実行よりもはるかに優れた r2 (r2=0.3) が得られましたが、素晴らしい結果ではありませんでした。誰かが理由を知っていますか？私のコードに何か問題がありますか？私のコードと基礎となる skflow コードの違いは何ですか? 私の損失関数は正しく定義されていますか? 助けていただければ幸いです。以下にコードを示します。
# with scikit flow
dnn_reg = skflow.TensorFlowDNNRegressor(hidden_units=[200,500], steps=3000, learning_rate=0.5)
dnn_reg.fit(x_train, y_train)
pred_train = dnn_reg.predict (x_train)
pred_valid = dnn_reg.predict (x_valid)
print ('r-square for training set', r2_score(y_train, pred_train))
print ('r-square for validation set',r2_score(y_valid, pred_valid))
# tensorflow code
n_samples = 15000
n_features = 171
batch_size = 1000
num_batch = n_samples/batch_size
hidden1 = 200
hidden2 = 100
learning_rate=0.01
n_epoch=3000
graph = tf.Graph()
with graph.as_default():
#constant and palceholder
tf_train_data = tf.placeholder(tf.float32, shape=(batch_size, n_features))
tf_train_act = tf.placeholder(tf.float32, shape=(batch_size))
tf_valid_data=tf.constant (x_valid.astype(np.float32))
# variables
w1 = tf.Variable(tf.truncated_normal([n_features, hidden1]), name='weight1')
b1 = tf.Variable(tf.zeros([hidden1]), name='bias1')
w2 = tf.Variable(tf.truncated_normal([hidden1, hidden2]), name='weight2')
b2 = tf.Variable(tf.zeros([hidden2]), name='bias2')
w3 = tf.Variable(tf.truncated_normal([hidden2, 1]), name='weight3')
b3 = tf.Variable(tf.zeros([1]), name='bias3')
#parameter histogram
w1_hist = tf.histogram_summary('weight_input', w1)
w2_hist = tf.histogram_summary('weight2', w2)
w3_hist = tf.histogram_summary('weight3', w3)
b1_hist = tf.histogram_summary('bias1', b1)
b2_hist = tf.histogram_summary('bias2', b2)
b3_hist = tf.histogram_summary('bias3', b3)
#y_hist = tf.histogram_summary('y', y_train)
#training computation
def forward_prop (input):
with tf.name_scope('hidden_1') as scope:
h1 = tf.nn.relu(tf.matmul(input, w1)+b1)
with tf.name_scope('hidden_2') as scope:
h2 = tf.nn.relu(tf.matmul(h1, w2)+b2)
with tf.name_scope('output') as scope:
output = tf.matmul(h2, w3)+b3
return (output)
#forward propagation
output = forward_prop(tf_train_data)
with tf.name_scope('cost') as scope:
loss=tf.sqrt(tf.reduce_mean(tf.square(tf.sub(tf_train_act, output))))
cost_summary = tf.scalar_summary('cost', loss)
#optimizer
with tf.name_scope('train') as scope:
optimizer = tf.train.AdagradOptimizer(learning_rate).minimize(loss)
#predictions
train_prediction = output
valid_prediction = forward_prop(tf_valid_data)
with tf.Session(graph=graph) as session:
session.run(tf.initialize_all_variables())
print ('initialized')
merged = tf.merge_all_summaries()
writer = tf.train.SummaryWriter ('./logs/log1', session.graph)
for epoch in range(n_epoch):
mini = np.array_split(range(y_train.shape[0]), num_batch)
for idx in mini[:-1]:
batch_x = x_train[idx]
batch_y = y_train[idx]
feed_dict = {tf_train_data:batch_x, tf_train_act:batch_y}
_,l, pred_train = session.run([optimizer, loss, output], feed_dict=feed_dict)
if epoch % 100 == 0:
print ('minibatch loss at step %d: %f' % (epoch, l))
print ('minibatch r2: %0.1f' % r2_score(batch_y, pred_train))
print ('validation r2: %0.1f' % r2_score(y_valid, valid_prediction.eval()))