Styjun

What does 5d4 x 10 gp mean?

Active wildlife outside the window- Good or Bad for Cat psychology?

What was the first science fiction or fantasy multiple choice book?

What prevents a US state from colonizing a smaller state?

Why is my 401k manager recommending me to save more?

Why are symbols not written in words?

Is my guitar action too high or is the bridge too high?

How did they film the Invisible Man being invisible in 1933?

Word ending in "-ine" for rat-like

"I am [the / an] owner of a bookstore"?

What are the advantages and disadvantages of Manhattan-Style routing?

How does mmorpg store data?

Can US Supreme Court justices / judges be "rotated" out against their will?

Meaning of the word "good" in context

Can I take Amul cottage cheese from India to Netherlands?

How do I keep a running total of data in a column in Excel?

Does friction always oppose motion?

What verb for taking advantage fits in "I don't want to ________ on the friendship"?

Reusable spacecraft: why still have fairings detach, instead of open/close?

Dynamic Sql Query - how to add an int to the code?

Find the closest three-digit hex colour

Automorphisms and epimorphisms of finite groups

How useful would a hydroelectric power plant be in the post-apocalypse world?

Is it OK to say "The situation is pregnant with a crisis"?

Why do I keep getting operation attribute error in my tensor flow codes

Why are there no ++ and --​ operators in Python?Why does Python code run faster in a function?using pre-loaded data in TensorFlowSimple Feedforward Neural Network with TensorFlow won't learnTensorFlow multi-GPU InvalidArgumentError : cifar10_multi_gpu.pytrain two seperate tensorflow models at oncePythonshell.parser error using npm python-shellTensorflow Speech Recognition, run sess.run fails with “could not convert string to float”tflite outputs don't match with tensorflow outputs for conv2d_transpose

1

I try to build a hidden layer of neural network with tensorflow but I keep getting error message

"Operation" object has no attribute "dtype".

This is where the code throws the error:

 codings = tf.layers.dense(X, n_hidden, name="hidden")

This is the entire script

 import numpy as np
 import tensorflow as tf
 from PIL import Image


 data = []

 test2 = Image.open("./ters/test2.jpg")
 prepared_data = np.asarray(test2.resize((800, 1000), Image.ANTIALIAS))
 data.append(prepared_data)
 data = np.asarray(data)


 saver = tf.train.import_meta_graph("./my_model.ckpt.meta")


 batch_size, height, width, channels = data.shape


 n_hidden = 400

 X = tf.get_default_graph().get_operation_by_name("Placeholder")
 training_op = tf.get_default_graph().get_operation_by_name("train/Adam")
 codings = tf.layers.dense(X, n_hidden, tf.float32)


 n_iterations = 5


 with tf.Session() as sess:
 saver.restore(sess, "./my_model.ckpt")
 sess.run(training_op)
 test_img = codings.eval(feed_dict=X: X_test)

 print(test_img)

Note:
I have already trained the model and named it my_model.ckpt and I tried importing and using it.
This is the error message:

Traceback (most recent call last):
File "using_img_cleaner.py", line 36, in
codings = tf.layers.dense(X, n_hidden, tf.float32)
File "/home/exceptions/env/lib/python3.5/site-packages/tensorflow/python/layers/core.py", line 250, in dense
dtype=inputs.dtype.base_dtype,
AttributeError: 'Operation' object has no attribute 'dtype'

python tensorflow

share|improve this question

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Can you post the full code in order for me to reproduce the error?
  
  – gorjan
  Mar 25 at 12:39
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  okay, let me edit the question
  
  – Xceptions
  Mar 25 at 12:40
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  So, you trained the model using a separate script and it worked, and this is a script that you are using to retrain your model?
  
  – gorjan
  Mar 25 at 12:53
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Exactly. This is where the error arises. Not retrain the model but to use it on another image as a test file
  
  – Xceptions
  Mar 25 at 12:56
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Then you don't need to create the hidden layer again, it is already present in the graph when you are loading the meta graph. Just load the ops you need (X and training_op) and that should be it.
  
  – gorjan
  Mar 25 at 13:02
  

  
  
  
  

 | 
show 1 more comment

1

I try to build a hidden layer of neural network with tensorflow but I keep getting error message

"Operation" object has no attribute "dtype".

This is where the code throws the error:

 codings = tf.layers.dense(X, n_hidden, name="hidden")

This is the entire script

 import numpy as np
 import tensorflow as tf
 from PIL import Image


 data = []

 test2 = Image.open("./ters/test2.jpg")
 prepared_data = np.asarray(test2.resize((800, 1000), Image.ANTIALIAS))
 data.append(prepared_data)
 data = np.asarray(data)


 saver = tf.train.import_meta_graph("./my_model.ckpt.meta")


 batch_size, height, width, channels = data.shape


 n_hidden = 400

 X = tf.get_default_graph().get_operation_by_name("Placeholder")
 training_op = tf.get_default_graph().get_operation_by_name("train/Adam")
 codings = tf.layers.dense(X, n_hidden, tf.float32)


 n_iterations = 5


 with tf.Session() as sess:
 saver.restore(sess, "./my_model.ckpt")
 sess.run(training_op)
 test_img = codings.eval(feed_dict=X: X_test)

 print(test_img)

Note:
I have already trained the model and named it my_model.ckpt and I tried importing and using it.
This is the error message:

Traceback (most recent call last):
File "using_img_cleaner.py", line 36, in
codings = tf.layers.dense(X, n_hidden, tf.float32)
File "/home/exceptions/env/lib/python3.5/site-packages/tensorflow/python/layers/core.py", line 250, in dense
dtype=inputs.dtype.base_dtype,
AttributeError: 'Operation' object has no attribute 'dtype'

python tensorflow

share|improve this question

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Can you post the full code in order for me to reproduce the error?
  
  – gorjan
  Mar 25 at 12:39
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  okay, let me edit the question
  
  – Xceptions
  Mar 25 at 12:40
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  So, you trained the model using a separate script and it worked, and this is a script that you are using to retrain your model?
  
  – gorjan
  Mar 25 at 12:53
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Exactly. This is where the error arises. Not retrain the model but to use it on another image as a test file
  
  – Xceptions
  Mar 25 at 12:56
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Then you don't need to create the hidden layer again, it is already present in the graph when you are loading the meta graph. Just load the ops you need (X and training_op) and that should be it.
  
  – gorjan
  Mar 25 at 13:02
  

  
  
  
  

 | 
show 1 more comment

I try to build a hidden layer of neural network with tensorflow but I keep getting error message

"Operation" object has no attribute "dtype".

This is where the code throws the error:

 codings = tf.layers.dense(X, n_hidden, name="hidden")

This is the entire script

 import numpy as np
 import tensorflow as tf
 from PIL import Image


 data = []

 test2 = Image.open("./ters/test2.jpg")
 prepared_data = np.asarray(test2.resize((800, 1000), Image.ANTIALIAS))
 data.append(prepared_data)
 data = np.asarray(data)


 saver = tf.train.import_meta_graph("./my_model.ckpt.meta")


 batch_size, height, width, channels = data.shape


 n_hidden = 400

 X = tf.get_default_graph().get_operation_by_name("Placeholder")
 training_op = tf.get_default_graph().get_operation_by_name("train/Adam")
 codings = tf.layers.dense(X, n_hidden, tf.float32)


 n_iterations = 5


 with tf.Session() as sess:
 saver.restore(sess, "./my_model.ckpt")
 sess.run(training_op)
 test_img = codings.eval(feed_dict=X: X_test)

 print(test_img)

Note:
I have already trained the model and named it my_model.ckpt and I tried importing and using it.
This is the error message:

Traceback (most recent call last):
File "using_img_cleaner.py", line 36, in
codings = tf.layers.dense(X, n_hidden, tf.float32)
File "/home/exceptions/env/lib/python3.5/site-packages/tensorflow/python/layers/core.py", line 250, in dense
dtype=inputs.dtype.base_dtype,
AttributeError: 'Operation' object has no attribute 'dtype'

python tensorflow

share|improve this question

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

 codings = tf.layers.dense(X, n_hidden, name="hidden")

 import numpy as np
 import tensorflow as tf
 from PIL import Image


 data = []

 test2 = Image.open("./ters/test2.jpg")
 prepared_data = np.asarray(test2.resize((800, 1000), Image.ANTIALIAS))
 data.append(prepared_data)
 data = np.asarray(data)


 saver = tf.train.import_meta_graph("./my_model.ckpt.meta")


 batch_size, height, width, channels = data.shape


 n_hidden = 400

 X = tf.get_default_graph().get_operation_by_name("Placeholder")
 training_op = tf.get_default_graph().get_operation_by_name("train/Adam")
 codings = tf.layers.dense(X, n_hidden, tf.float32)


 n_iterations = 5


 with tf.Session() as sess:
 saver.restore(sess, "./my_model.ckpt")
 sess.run(training_op)
 test_img = codings.eval(feed_dict=X: X_test)

 print(test_img)

share|improve this question

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

share|improve this question

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

edited Mar 25 at 15:42

VDWWD

25.8k1212 gold badges3939 silver badges5858 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges

asked Mar 25 at 12:37

XceptionsXceptions

2799 bronze badges