我收到以下错误 - 显然是在保存我的模型时
Step = 1799 | Tensorflow Accuracy = 1.0
Step = 1799 | My Accuracy = 0.0363355780022
Step = 1800 | Tensorflow Accuracy = 1.0
Step = 1800 | My Accuracy = 0.0364694929089
Traceback (most recent call last):
File "CNN-LSTM-seg-reg-sigmoid.py", line 290, in <module>
saver.save(sess, save_path)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1085, in save
self.export_meta_graph(meta_graph_filename)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1103, in export_meta_graph
add_shapes=True),
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2175, in as_graph_def
result, _ = self._as_graph_def(from_version, add_shapes)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2138, in _as_graph_def
raise ValueError("GraphDef cannot be larger than 2GB.")
ValueError: GraphDef cannot be larger than 2GB.
Here建议留意tf.constant s，但我的程序中常量为零。但是，我的weights和biases如下所示：tf.Variable(tf.random_normal([32]),name="bc1")。这可能是一个问题吗？
如果不是这样，那么this告诉我在每次循环迭代后我都会添加到图形中的某个地方，但我不确定它在哪里发生。
我的第一个猜测是当我做出预测时。我通过这个做出预测 以下代码......
# Make prediction
im = Image.open('/home/volcart/Documents/Data/input_crops/temp data0001.tif')
batch_x = np.array(im)
batch_x = batch_x.reshape((1, n_input_x, n_input_y))
batch_x = batch_x.astype(float)
prediction = sess.run(pred, feed_dict={x: batch_x})
prediction = tf.sigmoid(prediction.reshape((n_input_x * n_input_y, n_classes)))
prediction = prediction.eval().reshape((n_input_x, n_input_y, n_classes))
我的第二个猜测是当我通过以下方式计算loss和accuracy时：loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x, y: batch_y})
我的整个会话代码如下所示：
# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
gpu_options = tf.GPUOptions()
config = tf.ConfigProto(gpu_options=gpu_options)
config.gpu_options.allow_growth = True
# Launch the graph
with tf.Session(config=config) as sess:
sess.run(init)
summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph) #initialize graph for tensorboard
step = 1
# Import data
data = scroll_data.read_data('/home/volcart/Documents/Data/')
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = data.train.next_batch(batch_size)
# Run optimization op (backprop)
batch_x = batch_x.reshape((batch_size, n_input_x, n_input_y))
batch_y = batch_y.reshape((batch_size, n_input_x, n_input_y))
batch_y = convert_to_2_channel(batch_y, batch_size)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
step = step + 1
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y})
# Make prediction
im = Image.open('/home/volcart/Documents/Data/input_crops/temp data0001.tif')
batch_x = np.array(im)
batch_x = batch_x.reshape((1, n_input_x, n_input_y))
batch_x = batch_x.astype(float)
prediction = sess.run(pred, feed_dict={x: batch_x})
prediction = tf.sigmoid(prediction.reshape((n_input_x * n_input_y, n_classes)))
prediction = prediction.eval().reshape((n_input_x, n_input_y, n_classes))
# Temp arrays are to splice the prediction n_input_x x n_input_y x 2
# into 2 matrices n_input_x x n_input_y
temp_arr1 = np.empty((n_input_x, n_input_y))
for i in xrange(n_input_x):
for j in xrange(n_input_x):
for k in xrange(n_classes):
if k == 0:
temp_arr1[i][j] = 1 - prediction[i][j][k]
my_acc = accuracy_custom(temp_arr1,batch_y[0,:,:,0])
print "Step = " + str(step) + " | Tensorflow Accuracy = " + str(acc)
print "Step = " + str(step) + " | My Accuracy = " + str(my_acc)
if step % 100 == 0:
save_path = "/home/volcart/Documents/CNN-LSTM-reg-model/CNN-LSTM-seg-step-" + str(step) + "-model.ckpt"
saver.save(sess, save_path)
csv_file = "/home/volcart/Documents/CNN-LSTM-reg/CNNLSTMreg-step-" + str(step) + "-accuracy-" + str(my_acc) + ".csv"
np.savetxt(csv_file, temp_arr1, delimiter=",")
答案 0 :(得分：2)
你正在这条线上增长你的图表：
private Uri startCameraFileUri;
private void startCameraIntent() {
final Intent intentCamera = new Intent(android.provider.MediaStore.ACTION_IMAGE_CAPTURE);
try {
startCameraFileUri = Uri.fromFile(Utils.getNewFile());
intentCamera.putExtra(MediaStore.EXTRA_OUTPUT, startCameraFileUri);
intentCamera.putExtra("return-data", true);
startActivityForResult(intentCamera, IConstants.REQUEST_TAKE_PICTURE);
} catch (Exception e) {
e.printStackTrace();
}
}
public void openGalleryIntent() {
final boolean isKitKat = Build.VERSION.SDK_INT >= Build.VERSION_CODES.KITKAT;
if (isKitKat) {
final Intent openGalleryIntent = new Intent(Intent.ACTION_OPEN_DOCUMENT);
openGalleryIntent.addCategory(Intent.CATEGORY_OPENABLE);
openGalleryIntent.setType("image/*");
openGalleryIntent.putExtra(Intent.EXTRA_LOCAL_ONLY, true);
startActivityForResult(
Intent.createChooser(openGalleryIntent, getString(R.string.PROFILE_PIC_LIBRARY)),
IConstants.REQUEST_GALLERY);
} else {
final Intent openGalleryIntent = new Intent(Intent.ACTION_PICK,
android.provider.MediaStore.Images.Media.EXTERNAL_CONTENT_URI);
openGalleryIntent.putExtra(Intent.EXTRA_LOCAL_ONLY, true);
startActivityForResult(Intent.createChooser(openGalleryIntent, getString(R.string.PROFILE_PIC_LIBRARY)), IConstants.REQUEST_GALLERY);
}
}
@Override
public void onActivityResult(int requestCode, int resultCode, Intent data) {
if (resultCode == Activity.RESULT_OK) {
final Uri uri;
if(data != null) {
uri = data.getData();
}
else{
uri = startCameraFileUri;
}
switch (requestCode) {
case IConstants.REQUEST_GALLERY:
case IConstants.REQUEST_TAKE_PICTURE:
try {
if (!uri.toString().isEmpty()) {
loadUserPhoto(uri.toString());
}
} catch (Exception e) {
e.printStackTrace();
}
break;
}
}
}
这将您的prediction = tf.sigmoid(prediction.reshape((n_input_x * n_input_y, n_classes)))
numpy数组转换为TensorFlow常量节点，将其内联到Graph中，并在其上添加prediction节点。
您可以在开始训练循环之前添加Sigmoid来解决此类问题
答案 1 :(得分：1)
您可以使用tf.placeholder重写代码的以下行：
预测= tf.sigmoid（prediction.reshape（（n_input_x * n_input_y，n_classes）））
这将解决问题。