ValueError: Cannot feed value of shape (48, 48, 1) for Tensor u'InputData/X:0', which has shape '(?, 48, 48, 1)'

[RABAJ]

hi! I am getting this error after running poc.py .Please help me .

[jalajthanaki]

Can you help me with the which Tensorflow version and TFLearn version are you using?

Meanwhile you can check this Stackoverflow thread to resolve this issue.

I'm trying to recreate the same error at my end so I can provide the solution of it.

[RABAJ]

first i was working on tensorflow version 1.7 but now i upgraded it to 1.10 still getting error:-
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tflearn/initializations.py:119: UniformUnitScaling.init (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tflearn/objectives.py:66: calling reduce_sum (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead

[RABAJ]

I had already reshaped using( image = image.reshape([-1, SIZE_FACE, SIZE_FACE, 1])
print(image.shape))and getting output(1,48,48,1)but after it when it goes to model.predict it raises the error :- Cannot feed value of shape (48, 48, 1) for Tensor u'InputData/X:0', which has shape '(?, 48, 48, 1)'

[RABAJ]

using these-
absl-py==0.2.0
astor==0.6.2
bleach==1.5.0
gast==0.2.0
grpcio==1.11.0
html5lib==0.9999999
Keras==2.1.5
Markdown==2.6.11
numpy==1.14.2
opencv-python==3.4.0.12
pandas==0.22.0
Pillow==5.1.0
protobuf==3.5.2.post1
python-dateutil==2.7.2
pytz==2018.4
PyYAML==3.12
scikit-learn==0.19.1
scipy==1.0.1
six==1.11.0
sklearn==0.0
tensorboard==1.7.0
tensorflow==1.7.0
termcolor==1.1.0
tflearn==0.3.2
Werkzeug==0.14.1

[jalajthanaki]

I'm running the same code which I have uploaded and unfortunetly I couldn't recreate the same error which you are getting.

I'm using tensorflow-gpu==1.9.0

You can see this solution as well

Try to pass image[none,48,48,1] and check.

Bare with me for a day or two I will setup the same enviornment which you had and get back to you.

[jalajthanaki]

I have checked the code from my side. I used the library specifications which you have posted and the code is running perfectly fine. I haven't changed anything so I guess if you can experiment with reshape then this issue will be solved. If you should probably use the batch dimension that may help. More details about this is given here and here

[jalajthanaki]

@RABAJ: If I get to know the entire error log then it would be great. So I can try another time to see what is creating problem in your case.

My assumptions:
The input image size in your case is also 48 X 48
You haven't change the defination of neural network