恢復的模型未初始化（初始V3 /轉移學習）

我正在使用Inception v3模型並應用了轉移學習。培訓和評估很好。恢復的模型未初始化（初始V3 /轉移學習）

現在我嘗試實際使用（保存的）模型。我訓練

print("Saving model...") 
saver = tf.train.Saver() 
save_path = saver.save(sess, self.MODEL_SAV_PATH) 
print("...Saved @ ", save_path)

在剛保存的模型，並嘗試將其與

def load_model(self):  
    tf.reset_default_graph() 
    self.input_shape = tf.placeholder(tf.float32, shape=[None, pipeline.height, pipeline.width, pipeline.channels]) 
    with slim.arg_scope(inception.inception_v3_arg_scope()): 
     self.logits, self.end_points = inception.inception_v3(self.input_shape, num_classes=1001, is_training=False) 

    self.predictions = self.end_points['Predictions'] 

    self.sess = tf.Session() 
    saver = tf.train.import_meta_graph(META_PATH) 
    saver.restore(self.sess, train.latest_checkpoint(CHECKPOINT_PATH))

恢復...

，並最終用它

prediction = self.sess.run(self.predictions, feed_dict={self.input_shape: converted_images}).argmax()

但sess.run會拋出以下錯誤

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value InceptionV3/Conv2d_1a_3x3/weights 
[[Node: InceptionV3/Conv2d_1a_3x3/weights/read = Identity[T=DT_FLOAT, _class=["loc:@InceptionV3/Conv2d_1a_3x3/weights"], _device="/job:localhost/replica:0/task:0/gpu:0"](InceptionV3/Conv2d_1a_3x3/weights)]] 
[[Node: InceptionV3/Predictions/Reshape_1/_795 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_2278_InceptionV3/Predictions/Reshape_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

，所以我想自己是不是就在我的恢復過程......

來源

2017-08-26 Marco

用'saver = tf.train.Saver（）'替換'saver = tf.train.import_meta_graph（META_PATH）'就行了。 –

thx！想讓它成爲答案嗎？ – Marco

當然！將它作爲答案發布。 –

因爲要創建使用self.logits, self.end_points = inception.inception_v3，默認的圖形已經持有該圖中所有變量的曲線圖。

# replacing this one 
saver = tf.train.import_meta_graph(META_PATH) 
# with this saver would work 
saver = tf.train.Saver()

來源

2017-08-26 15:22:20

恢復的模型未初始化（初始V3 /轉移學習）

回答

相關問題