pixel
pixel copied to clipboard
xplip
Research code for pixel-based encoders of language (PIXEL)
Trying to install this repository: ```bash pip install git+https://github.com/xplip/pixel ``` > > Collecting git+https://github.com/xplip/pixel > Cloning https://github.com/xplip/pixel to ./tmp/pip-req-build-ijxd55pn > Running command git clone --quiet https://github.com/xplip/pixel /home/nlp/amit/tmp/pip-req-build-ijxd55pn > Resolved https://github.com/xplip/pixel...
you would need to set `PYPI_API_TOKEN`, and every time you create a github "release" it would release to pypi
I work with a 2D script (Sutton SignWriting), which specifies characters, and their 2D position. Linearly looks like this  but can be rendered like this  I am wondering...
In your work, it seems like the decoder is only used to pre-train the model, and then discarded for downstream tasks, and only the encoder is being used. Is there...
Hi @xplip , thanks for sharing your code. I'm currently running the pre-training scripts, and have met the issues with finding validation dataset. I got errors like "Repository Not Found...
Hi, when I run "python scripts/training/run_pos.py \ --model_name_or_path="Team-PIXEL/pixel-base-finetuned-pos-ud-vietnamese-vtb" \ --data_dir="data/ud-treebanks-v2.10/UD_Vietnamese-VTB" \ --remove_unused_columns=False \ --output_dir="sanity_check" \ --do_eval \ --max_seq_length=256 \ --overwrite_cache", there is a following error: Traceback (most recent call last):...
Dear Author, I tried to pre-train the model on book-corpus data only, whose training config is exactly the same as yours. But I found that the training loss is around...
``` File "scripts/training/run_pretraining.py", line 465, in preprocess_images examples["pixel_values"] = [transforms(image) for image in examples[image_column_name]] # bytes, path File "scripts/training/run_pretraining.py", line 465, in examples["pixel_values"] = [transforms(image) for image in examples[image_column_name]] #...