Upload current files

added_tokens.json

@@ -0,0 +1,34 @@
+{
+  "</s_bkg_no>": 57529,
+  "</s_bkg_no_series>": 57547,
+  "</s_com>": 57543,
+  "</s_dp>": 57537,
+  "</s_fd>": 57539,
+  "</s_filetype>": 57525,
+  "</s_info>": 57549,
+  "</s_name>": 57545,
+  "</s_phone>": 57551,
+  "</s_ref>": 57531,
+  "</s_shipper>": 57527,
+  "</s_size_type>": 57541,
+  "</s_vessel_name>": 57533,
+  "</s_voyage_no>": 57535,
+  "<s_Booking>": 57553,
+  "<s_bkg_no>": 57530,
+  "<s_bkg_no_series>": 57548,
+  "<s_com>": 57544,
+  "<s_dp>": 57538,
+  "<s_fd>": 57540,
+  "<s_filetype>": 57526,
+  "<s_iitcdip>": 57523,
+  "<s_info>": 57550,
+  "<s_name>": 57546,
+  "<s_phone>": 57552,
+  "<s_ref>": 57532,
+  "<s_shipper>": 57528,
+  "<s_size_type>": 57542,
+  "<s_synthdog>": 57524,
+  "<s_vessel_name>": 57534,
+  "<s_voyage_no>": 57536,
+  "<sep/>": 57522
+}

artifacts.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d459fc434e7aaef97d797e4d4289a92cb3b3f83130a783a4fa819febe522faaf
+size 1609085328

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "align_long_axis": false,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    1280,
+    960
+  ],
+  "max_length": 768,
+  "max_position_embeddings": 768,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "window_size": 10
+}

config.yaml

@@ -0,0 +1,29 @@
+resume_from_checkpoint_path: None
+result_path: './result'
+pretrained_model_name_or_path: 'naver-clova-ix/donut-base'
+dataset_name_or_paths: 
+  - 'dataset/Booking'
+sort_json_key: False
+train_batch_sizes: 
+  - 2
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 1280
+  - 960
+max_length: 768
+align_long_axis: False
+num_nodes: 1
+seed: 2022
+lr: 3e-05
+warmup_steps: 550
+num_training_samples_per_epoch: 1100
+max_epochs: 10
+max_steps: -1
+num_workers: 8
+val_check_interval: 1.0
+check_val_every_n_epoch: 3
+gradient_clip_val: 1.0
+verbose: True
+exp_name: 'train_Booking'
+exp_version: '20240327_133350'

donut_simple.ipynb

@@ -0,0 +1,113 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "1. Download the donut folder from Github https://github.com/clovaai/donut\n",
+        "2. Copy a config file in folder and change the name to hold your configuration.\n",
+        "3. Place your dataset (train, validation, test) along with JSONL files on the dataset folder.\n",
+        "4. Refer to donut_training.ipynb to train your model. Use A-100/V-100 GPU to avoid troublesome settings / slow training time.\n",
+        "5. Run the trained model using this ipynb file."
+      ],
+      "metadata": {
+        "id": "L5U1ACZZBxfh"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Enable Google Drive and Go to the donut folder\n",
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive')\n",
+        "%cd /content/drive/MyDrive/donut"
+      ],
+      "metadata": {
+        "id": "-BZ2HFB9OtWP"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SJpD4AAj7qeZ"
+      },
+      "outputs": [],
+      "source": [
+        "#Install all necessary modules. Don't change the version number!\n",
+        "!pip install transformers==4.25.1\n",
+        "!pip install timm==0.5.4\n",
+        "!pip install donut-python"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# import necessary modules\n",
+        "from donut import DonutModel\n",
+        "from PIL import Image\n",
+        "import torch"
+      ],
+      "metadata": {
+        "id": "gSatjcDn5S89"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Test the model with testing data. Just to initiate model.\n",
+        "!python test.py --task_name Booking --dataset_name_or_path dataset/Booking --pretrained_model_name_or_path ./result/train_Booking/donut-booking-extract"
+      ],
+      "metadata": {
+        "id": "dyOv9Omo8dJU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "model = DonutModel.from_pretrained(\"./result/train_Booking/donut-booking-extract\")\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()\n",
+        "\n",
+        "image = Image.open(\"/content/drive/MyDrive/donut/test/4.jpg\").convert(\"RGB\")\n",
+        "\n",
+        "with torch.no_grad():\n",
+        "  output = model.inference(image=image, prompt=\"<s_Booking>\")\n",
+        "output"
+      ],
+      "metadata": {
+        "id": "dFfm72T93Z8G"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "gpuType": "V100",
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

donut_train.ipynb

@@ -0,0 +1,110 @@
+{
+  "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
+}

events.out.tfevents.1711546518.0dee2374164e.17241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb74293bd8a2b529e2de2c7a612d471fa7bab334a546eca42bbbb8d84c2fb21
+size 21222

hparams.yaml

@@ -0,0 +1 @@
+{}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<s_Booking>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "from_slow": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "naver-clova-ix/donut-base",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}