andras/great-ai
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases 4 Packages Wiki Activity Actions

Improve dashboard

Browse source
This commit is contained in:
Andras Schmelczer 2022-06-04 14:06:32 +02:00
parent 471c258cb0
commit 75a33544ad
30 changed files with 690 additions and 416 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/simple/deploy.ipynb
View file

@ -133,14 +133,14 @@
}
],
"source": [
"result = predict_domain(\n",
" \"\"\"\n",
" State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-training and only consuming words and characters. Our proposed models train end-to-end to align with the fine-grained and category-specific content of images. Natural language provides a flexible and compact way of encoding only the salient visual aspects for distinguishing categories. By training on raw text, our model can do inference on raw text as well, providing humans a familiar mode both for annotation and retrieval. Our model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero-shot classification on the CaltechUCSD Birds 200-2011 dataset. \"\"\"\n",
")\n",
"# result = predict_domain(\n",
"# \"\"\"\n",
"# State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-training and only consuming words and characters. Our proposed models train end-to-end to align with the fine-grained and category-specific content of images. Natural language provides a flexible and compact way of encoding only the salient visual aspects for distinguishing categories. By training on raw text, our model can do inference on raw text as well, providing humans a familiar mode both for annotation and retrieval. Our model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero-shot classification on the CaltechUCSD Birds 200-2011 dataset. \"\"\"\n",
"# )\n",
"\n",
"from pprint import pprint\n",
"# from pprint import pprint\n",
"\n",
"# pprint(result.dict(), width=120)"
"# # pprint(result.dict(), width=120)"
]
}
],