File size: 4,278 Bytes
5fdb69e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "6gGKXU5RXORf"
   },
   "outputs": [],
   "source": [
    "# getting the latest transformers first, since this will require a restart\n",
    "\n",
    "!pip install git+https://github.com/huggingface/transformers.git"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "yCRrF4aiXPPo"
   },
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import torch\n",
    "from google.colab import userdata\n",
    "from huggingface_hub import login\n",
    "from transformers import AutoProcessor, AutoModelForImageTextToText\n",
    "from google.colab import files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "AAlOQuCbXcrv"
   },
   "outputs": [],
   "source": [
    "# logging in to HF\n",
    "\n",
    "hf_token = userdata.get('HF_TOKEN')\n",
    "login(hf_token, add_to_git_credential=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "_RRVc2j2Vun-"
   },
   "outputs": [],
   "source": [
    "# this will start an input prompt for uploading local files\n",
    "\n",
    "uploaded = files.upload()\n",
    "print(uploaded.keys()) # this will look sth like dict_keys([\"note2.jpg\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "V_UAuSSkXBKh"
   },
   "outputs": [],
   "source": [
    "'''\n",
    "ChatGPT and Gemini explain the following part roughly like so:\n",
    "The string contained in image_path is the key of the entry in the dictionary of uploaded files (see box above).\n",
    "The value to that key contains the image in binary format.\n",
    "The \"with open(image_path, \"wb\") as f\" part means: Create a new file \"note2.jpg\" on the server, and write to it in binary mode (\"wb\").\n",
    "f.write(image) writes the binary image to that new file. \"note2.jpg\" aka image_path will now contain the image.\n",
    "'''\n",
    "\n",
    "image_path = \"note2.jpg\" # update this string depending on the printout in the previous cell!\n",
    "image = uploaded[image_path]\n",
    "with open(image_path, \"wb\") as f:\n",
    "  f.write(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "AiFP-mQtXrpV"
   },
   "outputs": [],
   "source": [
    "# from HF model instructions\n",
    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
    "model = AutoModelForImageTextToText.from_pretrained(\"stepfun-ai/GOT-OCR-2.0-hf\", device_map=device)\n",
    "processor = AutoProcessor.from_pretrained(\"stepfun-ai/GOT-OCR-2.0-hf\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "7Adr8HB_YNf5"
   },
   "outputs": [],
   "source": [
    "# also from HF documentation about this model, see https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf\n",
    "\n",
    "image = image_path\n",
    "inputs = processor(image, return_tensors=\"pt\").to(device)\n",
    "\n",
    "ocr = model.generate(\n",
    "    **inputs,\n",
    "    do_sample=False,\n",
    "    tokenizer=processor.tokenizer,\n",
    "    stop_strings=\"<|im_end|>\",\n",
    "    max_new_tokens=4096,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "nRsRUIIuYdJ9"
   },
   "outputs": [],
   "source": [
    "# prints out the recognized text. This can read my handwriting pretty well! And it works super quick on the free T4 GPU server here.\n",
    "\n",
    "print(processor.decode(ocr[0, inputs[\"input_ids\"].shape[1]:], skip_special_tokens=True))"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "authorship_tag": "ABX9TyPtAT7Yq5xd4vDcJEZtg69J",
   "gpuType": "T4",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}