Shivam Sharma comments

Results 6 comments of


                                            Shivam Sharma

How do we give input to the model, and where are the processed images stored?

I got it working after few cpu specific modifications for my laptop, using below: Referred from: [An IPYNB](https://github.com/sharmahr/Text-to-Face-Composition.git) Note: Depending upon PT version, few minor changes might be required After...

Image generated not good, not even comparable.

At my end, only 5th depth appears to be generating something meaningful...Nothing before/after this depth....Could someone explain this?

How to get three channels image results?

> please someone tell me where the results are being stored after training and testing of data? Hi, just in case this is still helpful for someone....you can check the...

No such file or directory: 'ckpt/MODELNAME'

It worked for me by giving MODELNAME only instead of ckpt/MODELNAME

TypeError: ('An update must have the same type as the original shared variable (shared_var=<TensorType(float32, matrix)>, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')

Hi, anyone got the solution for this? Kindly help.

TypeError: ('An update must have the same type as the original shared variable (shared_var=<TensorType(float32, matrix)>, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')

Thanks for the response @bchen1116 , this solves it.