Question

我正在按照我在Multi-Input Convolutional Neural Network for Flower Grading上阅读的体系结构，尝试开发多输入CNN。

我有一个csv文件，其中存储了每个数据项的值，并且对于每个项，我从不同角度捕获了4张图片。当我运行以下代码时，网络可以正确打印，但似乎永远不会进行训练，因为什么也没有发生，并且使用nvidia-smi的GPU使用率低于5％。

<!DOCTYPE HTML>

<html>
   <head>

      <script type = "text/javascript">
         function WebSocketTest() {

            if ("WebSocket" in window) {
               alert("WebSocket is supported by your Browser!");

               // Let us open a web socket
               var exampleSocket = new WebSocket("ws://localhost:12345/echo");
               alert("website opened")

               exampleSocket.onopen = function(event) {


                  // Web Socket is connected, send data using send()
                  exampleSocket.send('{"Command":"Start","Status":"Check"}');
                  alert("Message is sent...");
               };

               exampleSocket.onmessage = function (event) { 
                  var received_msg = event.data;
                  alert("Message is received...");
               };

               exampleSocket.onclose = function() { 

                  // websocket is closed.
                  alert("Connection is closed..."); 
               };
            } else {

               // The browser doesn't support WebSocket
               alert("WebSocket NOT supported by your Browser!");
            }
         }
      </script>

   </head>

   <body>
      <div id = "sse">
         <a href = "javascript:WebSocketTest()">Run WebSocket</a>
      </div>

   </body>
</html>

Expected:(on server side)
RcvdDAta : '{"Command":"Start","Status":"Check"}'
Acutal:
RcvdDAta :  
b'GET /echo HTTP/1.1\r\nHost: localhost:12345\r\nConnection: Upgrade\r\nPragma: no-cache\r\nCache-Control: no-cache\r\nUpgrade: websocket\r\nOrigin: file://\r\nSec-WebSocket-Version: 13\r\nUser-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36\r\nAccept-Encoding: gzip, deflate, br\r\nAccept-Language: en-US,en;q=0.9\r\nSec-WebSocket-Key: s1qAa96xxm9IZqU21C0TQA==\r\nSec-WebSocket-Extensions: permessage-deflate; client_max_window_bits\r\n\r\n'

下面是nvidia-smi输出：

kilograms_trees = tf.data.experimental.CsvDataset(
        filenames='dataset/agrumeto.csv',
        record_defaults=[tf.float32],
        field_delim=",",
        header=True)

kilo_train = kilograms_trees.take(35)
kilo_test = kilograms_trees.skip(35)


def create_conv_layer(input):
    x = tf.keras.layers.Conv2D(32, (7, 7), activation='relu')(input)
    x = tf.keras.layers.MaxPooling2D((2, 2), (2,2))(x)
    x = tf.keras.Model(inputs=input, outputs=x)
    return x

inputA = tf.keras.Input(shape=(size,size,3))
inputB = tf.keras.Input(shape=(size,size,3))
inputC = tf.keras.Input(shape=(size,size,3))
inputD = tf.keras.Input(shape=(size,size,3))


x = create_conv_layer(inputA)
y = create_conv_layer(inputB)
w = create_conv_layer(inputC)
z = create_conv_layer(inputD)

# combine the output of the two branches
combined = tf.keras.layers.concatenate([x.output, y.output, w.output, z.output])

layer_1 = tf.keras.layers.Conv2D(16, (3,3), activation="relu")(combined)
layer_1 = tf.keras.layers.MaxPooling2D((2, 2))(layer_1)

layer_2 = tf.keras.layers.Conv2D(16, (3,3), activation="relu")(layer_1)
layer_2 = tf.keras.layers.MaxPooling2D((2, 2), (2,2))(layer_2)

layer_3 = tf.keras.layers.Conv2D(32, (3,3), activation="relu")(layer_2)
layer_3 = tf.keras.layers.MaxPooling2D((2, 2), (2,2))(layer_3)

layer_4 = tf.keras.layers.Conv2D(32, (3,3), activation="relu")(layer_3)
layer_4 = tf.keras.layers.MaxPooling2D((2, 2), (2,2))(layer_4)

flatten = tf.keras.layers.Flatten()(layer_4)
hidden1 = tf.keras.layers.Dense(10, activation='relu')(flatten)
output = tf.keras.layers.Dense(1, activation='relu')(hidden1)

model = tf.keras.Model(inputs=[x.input, y.input, w.input, z.input], outputs=output)

print(model.summary())

model.compile(optimizer='adam',
              loss="mean_absolute_percentage_error")

print("[INFO] training model...")
model.fit([trainA, trainB, trainC, trainD], kilo_train, epochs=5, batch_size=4)

test_loss, test_acc = model.evaluate([testA, testB, testC, testD], kilo_test)

print(test_acc)

这是输出控制台的最后几行：

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.40.04    Driver Version: 418.40.04    CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 1050    On   | 00000000:01:00.0 Off |                  N/A |
| N/A   54C    P0    N/A /  N/A |   3830MiB /  4042MiB |      8%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0       909      C   ...ycharmProjects/agrumeto/venv/bin/python  3159MiB |
|    0      1729      G   /usr/lib/xorg/Xorg                            27MiB |
|    0      1870      G   /usr/bin/gnome-shell                          69MiB |
|    0      6290      G   /usr/lib/xorg/Xorg                           273MiB |
|    0      6420      G   /usr/bin/gnome-shell                         127MiB |
|    0      6834      G   ...quest-channel-token=6261236721362009153    85MiB |
|    0      8806      G   ...pycharm-professional/132/jre64/bin/java     2MiB |
|    0     12830      G   ...-token=60E939FEF0A8E3D5C46B3D6911048536    31MiB |
|    0     27478      G   ...-token=ECA4D3D9ADD8448674D34492E89E40E3    51MiB |
+-----------------------------------------------------------------------------+

Answer 1

我忘记禁用Eager Execution，该功能在Tensorflow 2.0中默认启用。就是这个问题。

Tensorflow 2.0中的多输入CNN无效

1 个答案: