{ "cells": [ { "cell_type": "markdown", "id": "322ba6ee-22f3-4cf5-9281-89b4c06ffe5c", "metadata": {}, "source": [ "# Download of DocLayNet large (April 21, 2023)" ] }, { "cell_type": "markdown", "id": "17596ea7-9aee-490f-a0a1-e205d3425302", "metadata": {}, "source": [ "- By Pierre Guillou\n", "- Instance: NVIDIA A10 of https://cloud.lambdalabs.com/instances (VRAM per GPU: 24 GB, vCPUs: 30, RAM: 200 GiB, Storage, 1.4 TiB, Price: $0.60 / hr)" ] }, { "cell_type": "code", "execution_count": 1, "id": "6785ddb9-f82b-4baf-b762-f3628abea6bf", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/ubuntu/.local/lib/python3.8/site-packages/pandas/core/computation/expressions.py:20: UserWarning: Pandas requires version '2.7.3' or newer of 'numexpr' (version '2.7.1' currently installed).\n", " from pandas.core.computation.check import NUMEXPR_INSTALLED\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "2a6989d93e7540778adee3aa26e58573", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Downloading builder script: 0%| | 0.00/15.6k [00:00" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset_large[\"train\"][0][\"image\"]" ] }, { "cell_type": "code", "execution_count": null, "id": "f565b756-83dd-4bee-9ff8-e74afd60e1da", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "df1227ab-2177-493e-9dc5-5f7c5c69873c", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }