File size: 2,661 Bytes
5ffc566 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "-BZ2HFB9OtWP"
},
"outputs": [],
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"%cd /content/drive/MyDrive/donut"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "SJpD4AAj7qeZ"
},
"outputs": [],
"source": [
"!pip install transformers==4.25.1\n",
"!pip install timm==0.5.4\n",
"!pip install donut-python"
]
},
{
"cell_type": "code",
"source": [
"from donut import DonutModel\n",
"from PIL import Image\n",
"import torch"
],
"metadata": {
"id": "PxFaO3rfDHQJ"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Ro21MdJPSTZs"
},
"outputs": [],
"source": [
"# Copy one default config yaml file and amend to fit your use case.\n",
"!python train.py --config ./config/train_Booking.yaml"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "J1ITHX4jV2Go"
},
"outputs": [],
"source": [
"# After train, you can evaluate and use the model.\n",
"\n",
"model = DonutModel.from_pretrained(\"/content/drive/MyDrive/donut/result/train_Booking/20240327_032854\")\n",
"if torch.cuda.is_available():\n",
" model.half()\n",
" device = torch.device(\"cuda\")\n",
" model.to(device)\n",
"else:\n",
" model.encoder.to(torch.bfloat16)\n",
"\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2UhjFTmrWIrX"
},
"outputs": [],
"source": [
"image = Image.open(\"/content/COSCO_000.jpg\").convert(\"RGB\")\n",
"with torch.no_grad():\n",
" # My dataset name is Booking , tag i.e. <s_Booking>\n",
" output = model.inference(image=image, prompt=\"<s_Booking>\")\n",
"output"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "V100",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |