kdwonn / sag Goto Github PK

I'm encountering an OSError: [Errno 9] Bad file descriptor error when running the code after a few epochs. Could you please suggest what might be causing this error? Thanks!

Thank you, author, for sharing the code! Could you please provide details about the essential Python dependencies, including their versions?

Hi authors,

Thanks for the work and releasing the code!

I am curious to understand the effect of pre-training on PhraseCut dataset.
In case if you have tried in your experiments, could you please let me know if PharseCut pre-training is necessary?
Will directly training from scratch on RefCOCO/+/gref result in poor performance (Table 1)?

Thanks, Authors for sharing the codes.

After running these two lines below:

python build_batches.py -d Gref -t train 
python build_batches.py -d Gref -t val 

it results in a "train_batch" folder with 85,474 files and "val_batch" folder with 9,536 files". However, according to the paper, Gref should contain 104,560 expressions. Could you kindly provide clarification on this inconsistency? Thank you!

Hi,

Very interesting work, we are eager to reproduce it!

But we found no build_batches.py. We tried to use a file with the same name in TF-phrasecut-public, but didn't get the same dataset structure as Readme under this repository (We only get the batch folder, not image and label.).

We are very worried that the data processing is different from yours. If it is convenient could you provide the missing build_batches.py.

Best Regards.