Closed afeltham closed 6 years ago
You do not need to add an extra placeholder for the input. The one which your network has for taking in the input image would work. In the feed_dict, you need to pass in the input image to the placeholder in your network which takes in the input image, not into the extra one you added (re iterating - there is no need for that extra placeholder).
Hope this helps. Let us know if you need any further help with the debugging.
HI @falaktheoptimist thanks for the reply... sorry for being basic... but could you put that last paragraph into a code example? As mentioned before... i'm a bit new to all this.... Thanks!
There are 3 example notebooks in the repo ( https://github.com/InFoCusp/tf_cnnvis/tree/master/examples ), which I think would help you understand this idea very clearly. Please have a look and if you have any questions there, I would be happy to clarify.
@afeltham Closing this issue for now. Re-open if you are still facing the issue.
Hello, I'm rather new to all this so forgive me if this is a daft question. However, i just can't get the examples to work with my data. I've basically followed the "Training" section of https://www.tensorflow.org/tutorials/image_retraining and have had some good results from the resulting model. However, i want to visualise them and your library seems perfect for the job!
What am i doing wrong in the code below? I get no errors and 'is_success' is True so it appears to have worked?
The main things i don't seem to understand is the
value_feed_dict
, theinput_tensor
and thet_input / im
variables.I'm sure i'm doing something daft but would be trivial for someone in the know to spot what is wrong.
Thank you!