-
Filtering the images containing characters which are not in opt.character
Filtering the images whose label is longer than opt.batch_max_length
-------------------------------------------------------…
-
i want to fintune the uniter model in my own dataset, how to generate the lmdb dataset for images and text? i generate the image features from faster rcnn, but how to convert the text content and imag…
-
I have trained on IAM words dataset and when I am testing the result from demo.py file. The model gives random results and even different results every time on same image.
So is there any decoder i…
-
I found `lmdb.DiskError` that seems to appear intermittently while I was working with multi-signature AIDs. I could not figure out a script to reproduce this error reliably. Here is the stack trace.
…
-
hi, thank you for sharing your codes.
I try to train densecl on imagenet with 4*2080ti, but it takes about 13 days to finish training, which is much longer time than yours.
Did you use imagenet in l…
-
Sorry i'm new for this. I have this error.
`Read images...
[ ] 0/2653, elapsed: 0s, ETA:
Start...
Traceback (most recent call last):
File "cre…
-
Hi,
I love your work and I believe that your approach has big potential due to its speed. I am looking into retraining FABind with custom data.
Is there somewhere a script to convert data to your…
-
Consider this post about the drawbacks and solutions for [the Meilisearch](https://github.com/meilisearch/meilisearch) document indexer. We'll start with the current situation, explore the techniq…
-
Hi, I've been having this problem for testing my trained model on my own custom dataset. I've been able to train my model with the provided code to format into lmdb. However, when I'm trying to test m…
-
Can you please guide me the way that I need to send data to subprocess.call on windows machine
I suspect that the args/parmater curl should be different format, looks like below format is not accept…