File size: 2,623 Bytes
61655a4 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.\n",
"Some weights of VisionEncoderDecoderModel were not initialized from the model checkpoint at microsoft/trocr-base-printed and are newly initialized: ['encoder.pooler.dense.bias', 'encoder.pooler.dense.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
"/Users/kevin/.pyenv/versions/3.10.6/lib/python3.10/site-packages/transformers/generation/utils.py:1288: UserWarning: Using `max_length`'s default (20) to control the generation length. This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from transformers import TrOCRProcessor, VisionEncoderDecoderModel\n",
"\n",
"processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-printed')\n",
"model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-printed')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'IJ TAUT MIANY TUANJ'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from PIL import Image\n",
"\n",
"image = Image.open(\"cendu_ipas/m.20101029-m300-w001-003013083.gif\").convert(\"RGB\")\n",
"\n",
"pixel_values = processor(images=image, return_tensors=\"pt\").pixel_values\n",
"\n",
"generated_ids = model.generate(pixel_values)\n",
"processor.batch_decode(generated_ids, skip_special_tokens=True)[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.10.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|