Iván G. Pérez

Hi, thanks for creating `company-box`! Sadly I'm also experiencing this issue. Actually I had 2 problems, one of these is described in [this](https://github.com/sebastiencs/company-box/issues/44) ticket but I was able to resolve...

Thank you @ianpan870102 I just tried that out and worked perfectly!.

I also wanted to change the font face of the documentation and candidates list. I thought that was defined by `company` but it seems `company-box` overrides those faces, so thanks...

Hi, thanks for building this and sharing it. I just want to know if you were able to make any progress with this? I want to run some inference using...

I can try locally (CPU only). BTW, how can I take a small subset of coco?

Awesome, thanks and sorry for the basic question. I'm new on the vision domain.

Thanks Romain. Low scale will indeed be useful for research and learning.

Hey @rom1504 Colab took about 2h but it seems it downloaded all images. This is the latest logged output: ``` 60it [1:09:18, 69.30s/it] worker - success: 0.000 - failed to...

**Update:** Even after updating `albumentations` to its latest version (it also required to update `opencv-python`) I get the same error (`TypeError: 'NoneType' object is not iterable` at `clip_inference.py, line 69`)...

Previously I run: ```shell !img2dataset \ --url_list /content/sample_data/mscoco.parquet \ --input_format "parquet" \ --url_col "URL" \ --caption_col "TEXT" \ --output_format webdataset \ --output_folder /content/sample_data/mscoco \ --processes_count 16 \ --thread_count 64 \...