omrishsu

Results 8 comments of omrishsu

Adding new aggregation operation

Thank you @eisenjulian . I was actually asking about the first option you suggested. I don't know how (programmatically) do it. otherwise I'm "losing" the weights that you already trained...

Using ochre to evaluate synthetic ocr post processing dataset generation

Thanks a lot! Now I understand the folder structure, and I've updated my code to work with ochre's structure. I'll try the workflows as soon as possible and update on...

Cannot push:failed to write chunk header

Same here

ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float64: 'Tensor("strided_slice_2/stack_1:0", dtype=float64)'

I was able to solve it by changing `half = self.batch_size / 2` to `half = tf.cast((self.batch_size / 2),tf.int32)`

ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float64: 'Tensor("strided_slice_2/stack_1:0", dtype=float64)'

style_transfer.py

All chars assumption

I've solved this issue by adding another param with chars to include. BTW, do you want me to contribute these changes? I fill like it is very specific to my...

Error in align_output_to_input

I'm using python 3.6. I've fixed it by commenting the following lines: t_output_str = output_str.encode('ASCII', 'replace') t_input_str = input_str.encode('ASCII', 'replace') Well, I found this project interesting and i'm testing all...

Working without aligned file

Hi, Sorry for disappearing (working on another research). I've updated my question in a separate post: https://github.com/KBNLresearch/ochre/issues/4 Thanks!