mohamed mosad

@YuvalNirkin , i got this error while manually uploading src image ` RuntimeError: Cache file does not exist: src_images/srcimg7/srcimg7_dsfd_seq.pkl`

got this issue while converting stylegan2ada model trained with continue training from ffhq256 on custom dataset `KeyError: 'G_mapping/Dense2/weight'` this is true as weights dict has no such layer

I solved the issue by converting with the original torch2stylegan repo not the fork included in your repo Thanks

i have the same issue , the embeddings are entangled

what is your tensorflow version ? try use tensorflow==1.15 , i think it is the most stable and compatible version

@sevany make sure you run the file demo from project root ``` Python ./main/demo.py ```

@yujmo nms and bbox utils are written in cython, hence you have to build the scripts first have you built them `cd utils/bbox` `chmod +x make.sh` `./make.sh`

i think this network is more suitable to scene text detection , so it performs well in scenes and invoices , but not for documents check official paper https://arxiv.org/abs/1609.03605

Here's the script I am using to generate data , I am training on very powerful cloud machine with 6 cpu cores and around 50 gb ram https://github.com/Mohamed209/TextRecognitionDataGenerator/blob/receipts_ocr/generate_training_lines.py

as workaround i used parallel processing technique to boost generation , gained more speed but its not the optimal as generating my dataset around half million images would take with...