viktor/wrongmove
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

adding floorplans, detail json, refactored the folders

Browse source
This commit is contained in:
Kadir 2024-03-07 22:02:09 +00:00
parent e2f7998ee9
commit 46bb641026
215 changed files with 481 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

168
vqa/Untitled.ipynb
View file

@ -16,19 +16,20 @@
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/kadir/code/vqa/venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
"/Users/kadir/code/realestate/vqa/venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from transformers import Pix2StructProcessor, Pix2StructForConditionalGeneration\n",
"from PIL import Image\n"
"from PIL import Image\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 2,
"id": "74e4a41f-2dfc-428e-8bca-4e9cc1c076c6",
"metadata": {},
"outputs": [],
@ -39,7 +40,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 3,
"id": "c24b1560-563b-4ff2-8744-4591ac1cc57b",
"metadata": {
"editable": true,
@ -59,7 +60,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 11,
"id": "ea990e1f-a660-4efb-be48-d095ab05b50d",
"metadata": {
"editable": true,
@ -70,19 +71,61 @@
},
"outputs": [
{
"data": {
"text/plain": [
"'TITLE | <0x0A> Fifth Floor<0x0A>Floor Area 642 Sq Ft - 59.64 Sq M | Licence<0x0A>Remung<0x0A>Floor Area 642 Sq Ft - 59.64 Sq M <0x0A> Reception Room<0x0A>1210 x 12.10%<0x0A>39 x 39m | 1280 <0x0A> Balcony<0x0A>Reception Room<0x0A>1210 x 12.10%<0x0A>39 x 39m | 1280 <0x0A> Property<0x0A>Measurer | 1280 <0x0A> Ipaplus.com | 1280'"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
"name": "stdout",
"output_type": "stream",
"text": [
"TITLE | <0x0A> Fifth Floor<0x0A>Floor Area 642 Sq Ft - 59.64 Sq M | LUX<0x0A>Floor Area 642 Sq Ft - 59.64 Sq M<0x0A>Reception Room<0x0A>1210×1210<0x0A>3.9×3.9m | 12.10×1210<0x0A>Reception Room<0x0A>3.9×3.9m | 12.10×1210<0x0A>Balcony<0x0A>1.5×4.5′ | 1.5×4.5 <0x0A> Bathroom<0x0A>131°×102°<0x0A>4.0×3.1m | 1.40×2.7m | 1.40×2.7m <0x0A> Kitchen<0x0A>102°×710°<0x0A>3.1×2.4m | 1.10×3.1m | 1.00×3.1m <0x0A> Bedroom<0x0A>131°×810<0x0A>4.0×2.7m | 1.00×3.1m | 1.00×3.1m <0x0A> Kitchen<0x0A>102°×710<0x0A>3.1×2.4m | 1.00×3.1m | 1.00×3.1m <0x0A> Reception Room<0x0A>1210×1210<0x0A>3.9×3.9m | 1.50×4.5 | 1.00×3.5m <0x0A> Balcony<0x0A>1.5×4.5 | 1.50×4.5 | 1.00×3.5m\n"
]
}
],
"source": [
"x = processor.decode(predictions[0], skip_special_tokens=True)\n",
"x"
"print(x)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "b4a8b5fb-7cc5-441d-ad60-cff7c03a103e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"TITLE | \n",
" Fifth Floor\n",
"Floor Area 642 Sq Ft - 59.64 Sq M | LUX\n",
"Floor Area 642 Sq Ft - 59.64 Sq M\n",
"Reception Room\n",
"1210×1210\n",
"3.9×3.9m | 12.10×1210\n",
"Reception Room\n",
"3.9×3.9m | 12.10×1210\n",
"Balcony\n",
"1.5×4.5′ | 1.5×4.5 \n",
" Bathroom\n",
"131°×102°\n",
"4.0×3.1m | 1.40×2.7m | 1.40×2.7m \n",
" Kitchen\n",
"102°×710°\n",
"3.1×2.4m | 1.10×3.1m | 1.00×3.1m \n",
" Bedroom\n",
"131°×810\n",
"4.0×2.7m | 1.00×3.1m | 1.00×3.1m \n",
" Kitchen\n",
"102°×710\n",
"3.1×2.4m | 1.00×3.1m | 1.00×3.1m \n",
" Reception Room\n",
"1210×1210\n",
"3.9×3.9m | 1.50×4.5 | 1.00×3.5m \n",
" Balcony\n",
"1.5×4.5 | 1.50×4.5 | 1.00×3.5m\n"
]
}
],
"source": [
"x = r'\\d+.\\d*'"
]
},
{
@ -274,6 +317,103 @@
"\n",
"print(processor.batch_decode(generated_ids, skip_special_tokens=True))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8b5b4fd0-1152-4834-9e3f-89be944bad16",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "4fef9f95-22c3-4fd9-907d-471520494533",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "1e56a1f7-c10f-4169-a7c1-a862937c22ba",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "b6eec969-ebd6-4dac-8ca6-17569a9a3f8a",
"metadata": {},
"source": [
"# asd"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "7c0a2360-5de2-475b-9d10-d84bb5bede17",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"a diagram of a floor plan of a two bedroom apartment\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/kadir/code/realestate/vqa/venv/lib/python3.12/site-packages/transformers/generation/configuration_utils.py:410: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `1.2` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is an image of a floor plan of a two bedroom apartment\n"
]
}
],
"source": [
"from transformers import BlipProcessor, BlipForConditionalGeneration\n",
"\n",
"processor = BlipProcessor.from_pretrained(\"Salesforce/blip-image-captioning-large\")\n",
"model = BlipForConditionalGeneration.from_pretrained(\"Salesforce/blip-image-captioning-large\")\n",
"\n",
"# conditional image captioning\n",
"text = \"\"\n",
"inputs = processor(image, text, return_tensors=\"pt\")\n",
"\n",
"out = model.generate(**inputs)\n",
"print(processor.decode(out[0], skip_special_tokens=True))\n",
"\n",
"# unconditional image captioning\n",
"inputs = processor(image, return_tensors=\"pt\")\n",
"\n",
"out = model.generate(**inputs)\n",
"print(processor.decode(out[0], skip_special_tokens=True))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f5a7d57-30f3-4b1b-bc07-dbf076d41792",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "41c23bf0-cf64-4c71-9bc0-57f78af609b4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {

93
vqa/poetry.lock generated
View file

@ -1487,6 +1487,75 @@ files = [
{file = "packaging-23.2.tar.gz", hash = "sha256:048fb0e9405036518eaaf48a55953c750c11e1a1b68e0dd1a9d62ed0c092cfc5"},
]
[[package]]
name = "pandas"
version = "2.2.1"
description = "Powerful data structures for data analysis, time series, and statistics"
optional = false
python-versions = ">=3.9"
files = [
{file = "pandas-2.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8df8612be9cd1c7797c93e1c5df861b2ddda0b48b08f2c3eaa0702cf88fb5f88"},
{file = "pandas-2.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0f573ab277252ed9aaf38240f3b54cfc90fff8e5cab70411ee1d03f5d51f3944"},
{file = "pandas-2.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f02a3a6c83df4026e55b63c1f06476c9aa3ed6af3d89b4f04ea656ccdaaaa359"},
{file = "pandas-2.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c38ce92cb22a4bea4e3929429aa1067a454dcc9c335799af93ba9be21b6beb51"},
{file = "pandas-2.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:c2ce852e1cf2509a69e98358e8458775f89599566ac3775e70419b98615f4b06"},
{file = "pandas-2.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:53680dc9b2519cbf609c62db3ed7c0b499077c7fefda564e330286e619ff0dd9"},
{file = "pandas-2.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:94e714a1cca63e4f5939cdce5f29ba8d415d85166be3441165edd427dc9f6bc0"},
{file = "pandas-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f821213d48f4ab353d20ebc24e4faf94ba40d76680642fb7ce2ea31a3ad94f9b"},
{file = "pandas-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c70e00c2d894cb230e5c15e4b1e1e6b2b478e09cf27cc593a11ef955b9ecc81a"},
{file = "pandas-2.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e97fbb5387c69209f134893abc788a6486dbf2f9e511070ca05eed4b930b1b02"},
{file = "pandas-2.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:101d0eb9c5361aa0146f500773395a03839a5e6ecde4d4b6ced88b7e5a1a6403"},
{file = "pandas-2.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:7d2ed41c319c9fb4fd454fe25372028dfa417aacb9790f68171b2e3f06eae8cd"},
{file = "pandas-2.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:af5d3c00557d657c8773ef9ee702c61dd13b9d7426794c9dfeb1dc4a0bf0ebc7"},
{file = "pandas-2.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:06cf591dbaefb6da9de8472535b185cba556d0ce2e6ed28e21d919704fef1a9e"},
{file = "pandas-2.2.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:88ecb5c01bb9ca927ebc4098136038519aa5d66b44671861ffab754cae75102c"},
{file = "pandas-2.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:04f6ec3baec203c13e3f8b139fb0f9f86cd8c0b94603ae3ae8ce9a422e9f5bee"},
{file = "pandas-2.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a935a90a76c44fe170d01e90a3594beef9e9a6220021acfb26053d01426f7dc2"},
{file = "pandas-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c391f594aae2fd9f679d419e9a4d5ba4bce5bb13f6a989195656e7dc4b95c8f0"},
{file = "pandas-2.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9d1265545f579edf3f8f0cb6f89f234f5e44ba725a34d86535b1a1d38decbccc"},
{file = "pandas-2.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:11940e9e3056576ac3244baef2fedade891977bcc1cb7e5cc8f8cc7d603edc89"},
{file = "pandas-2.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:4acf681325ee1c7f950d058b05a820441075b0dd9a2adf5c4835b9bc056bf4fb"},
{file = "pandas-2.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9bd8a40f47080825af4317d0340c656744f2bfdb6819f818e6ba3cd24c0e1397"},
{file = "pandas-2.2.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:df0c37ebd19e11d089ceba66eba59a168242fc6b7155cba4ffffa6eccdfb8f16"},
{file = "pandas-2.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:739cc70eaf17d57608639e74d63387b0d8594ce02f69e7a0b046f117974b3019"},
{file = "pandas-2.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9d3558d263073ed95e46f4650becff0c5e1ffe0fc3a015de3c79283dfbdb3df"},
{file = "pandas-2.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:4aa1d8707812a658debf03824016bf5ea0d516afdea29b7dc14cf687bc4d4ec6"},
{file = "pandas-2.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:76f27a809cda87e07f192f001d11adc2b930e93a2b0c4a236fde5429527423be"},
{file = "pandas-2.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:1ba21b1d5c0e43416218db63037dbe1a01fc101dc6e6024bcad08123e48004ab"},
{file = "pandas-2.2.1.tar.gz", hash = "sha256:0ab90f87093c13f3e8fa45b48ba9f39181046e8f3317d3aadb2fffbb1b978572"},
]
[package.dependencies]
numpy = {version = ">=1.26.0,<2", markers = "python_version >= \"3.12\""}
python-dateutil = ">=2.8.2"
pytz = ">=2020.1"
tzdata = ">=2022.7"
[package.extras]
all = ["PyQt5 (>=5.15.9)", "SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)", "beautifulsoup4 (>=4.11.2)", "bottleneck (>=1.3.6)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=2022.12.0)", "fsspec (>=2022.11.0)", "gcsfs (>=2022.11.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.9.2)", "matplotlib (>=3.6.3)", "numba (>=0.56.4)", "numexpr (>=2.8.4)", "odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "pandas-gbq (>=0.19.0)", "psycopg2 (>=2.9.6)", "pyarrow (>=10.0.1)", "pymysql (>=1.0.2)", "pyreadstat (>=1.2.0)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "qtpy (>=2.3.0)", "s3fs (>=2022.11.0)", "scipy (>=1.10.0)", "tables (>=3.8.0)", "tabulate (>=0.9.0)", "xarray (>=2022.12.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)", "zstandard (>=0.19.0)"]
aws = ["s3fs (>=2022.11.0)"]
clipboard = ["PyQt5 (>=5.15.9)", "qtpy (>=2.3.0)"]
compression = ["zstandard (>=0.19.0)"]
computation = ["scipy (>=1.10.0)", "xarray (>=2022.12.0)"]
consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)"]
feather = ["pyarrow (>=10.0.1)"]
fss = ["fsspec (>=2022.11.0)"]
gcp = ["gcsfs (>=2022.11.0)", "pandas-gbq (>=0.19.0)"]
hdf5 = ["tables (>=3.8.0)"]
html = ["beautifulsoup4 (>=4.11.2)", "html5lib (>=1.1)", "lxml (>=4.9.2)"]
mysql = ["SQLAlchemy (>=2.0.0)", "pymysql (>=1.0.2)"]
output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.9.0)"]
parquet = ["pyarrow (>=10.0.1)"]
performance = ["bottleneck (>=1.3.6)", "numba (>=0.56.4)", "numexpr (>=2.8.4)"]
plot = ["matplotlib (>=3.6.3)"]
postgresql = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "psycopg2 (>=2.9.6)"]
pyarrow = ["pyarrow (>=10.0.1)"]
spss = ["pyreadstat (>=1.2.0)"]
sql-other = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)"]
test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"]
xml = ["lxml (>=4.9.2)"]
[[package]]
name = "pandocfilters"
version = "1.5.1"
@ -1759,6 +1828,17 @@ files = [
{file = "python_json_logger-2.0.7-py3-none-any.whl", hash = "sha256:f380b826a991ebbe3de4d897aeec42760035ac760345e57b812938dc8b35e2bd"},
]
[[package]]
name = "pytz"
version = "2024.1"
description = "World timezone definitions, modern and historical"
optional = false
python-versions = "*"
files = [
{file = "pytz-2024.1-py2.py3-none-any.whl", hash = "sha256:328171f4e3623139da4983451950b28e95ac706e13f3f2630a879749e7a8b319"},
{file = "pytz-2024.1.tar.gz", hash = "sha256:2a29735ea9c18baf14b448846bde5a48030ed267578472d8955cd0e7443a9812"},
]
[[package]]
name = "pywin32"
version = "306"
@ -2894,6 +2974,17 @@ files = [
{file = "typing_extensions-4.10.0.tar.gz", hash = "sha256:b0abd7c89e8fb96f98db18d86106ff1d90ab692004eb746cf6eda2682f91b3cb"},
]
[[package]]
name = "tzdata"
version = "2024.1"
description = "Provider of IANA time zone data"
optional = false
python-versions = ">=2"
files = [
{file = "tzdata-2024.1-py2.py3-none-any.whl", hash = "sha256:9068bc196136463f5245e51efda838afa15aaeca9903f49050dfa2679db4d252"},
{file = "tzdata-2024.1.tar.gz", hash = "sha256:2674120f8d891909751c38abcdfd386ac0a5a1127954fbc332af6b5ceae07efd"},
]
[[package]]
name = "uri-template"
version = "1.3.0"
@ -2981,4 +3072,4 @@ test = ["websockets"]
[metadata]
lock-version = "2.0"
python-versions = "^3.12"
content-hash = "cda4ae72dcade6cad311cef1e8cb3c07a7d553980f823ef764b6377e03e2d1ab"
content-hash = "ec7099d470acdee1c418ff102390f5a71764b90628f9523eff9f22a8fb3e5018"

1
vqa/pyproject.toml
View file

@ -14,6 +14,7 @@ torch = "^2.2.1"
torchvision = "^0.17.1"
torchaudio = "^2.2.1"
jupyterlab = "^4.1.2"
pandas = "^2.2.1"
[build-system]