installed packages

core/database/__init__.py

@@ -5,6 +5,7 @@ from .classes import NoDocumentFoundException
 from .classes import VisualCommunication
 from .database import connect
 from .utils import get_visual_communication
+from .utils import list_names
 from .utils import total_annotated
 from .utils import total_documents
 from .utils import upsert_annotations

core/database/database.py

@@ -1,24 +1,27 @@
-from pymongo import MongoClient
-from dotenv import load_dotenv
+from __future__ import annotations
+
 import logging
 import os
 
+from dotenv import load_dotenv
+from pymongo import MongoClient
+
 
 def connect():
     """Connect to MongoDB."""
     # load env vars
     load_dotenv()
     necessary_env_vars = [
-        "MONGO_HOST",
-        "MONGO_DB",
-        "MONGO_COLLECTION"
+        'MONGO_HOST',
+        'MONGO_DB',
+        'MONGO_COLLECTION',
     ]
     for env_var in necessary_env_vars:
         assert env_var in os.environ, f"{env_var} not found"
     # connect to database
-    client = MongoClient(os.getenv("MONGO_HOST"))
-    db = client[os.getenv("MONGO_DB")]
-    collection = db[os.getenv("MONGO_COLLECTION")]
-    collection.create_index("name", unique=True)
-    logging.info("connected to database")
+    client = MongoClient(os.getenv('MONGO_HOST'))
+    db = client[os.getenv('MONGO_DB')]
+    collection = db[os.getenv('MONGO_COLLECTION')]
+    collection.create_index('name', unique=True)
+    logging.info('connected to database')
     return collection, db, client

core/database/utils.py

@@ -9,6 +9,44 @@ from .classes import NoDocumentFoundException
 from .classes import VisualCommunication
 
 
+def count_documents(
+    collection: Collection,
+    has_annotation: bool = False,
+) -> int:
+    """
+    Get the total number of documents
+    in database that matches the filters.
+    """
+    assert isinstance(collection, Collection)
+    assert isinstance(has_annotation, bool)
+    # build query
+    query = {}
+    if has_annotation:
+        query['annotation'] = {'$ne': None}
+    return collection.count_documents(filter=query)
+
+
+def list_names(
+    collection: Collection,
+    has_annotation: bool = True,
+) -> list[str]:
+    """List the names of entries that match the filters."""
+    assert isinstance(collection, Collection)
+    assert isinstance(has_annotation, bool)
+    # build query
+    query = {}
+    if has_annotation:
+        query['annotation'] = {'$ne': None}
+    res_list = collection.find(
+        filter=query,
+        projection={
+            '_id': False,
+            'name': True,
+        },
+    )
+    return list(res_list)
+
+
 def total_documents(
     collection: Collection,
 ) -> int:

model/src/dataloader.py

@@ -0,0 +1,151 @@
+from __future__ import annotations
+
+import random
+from io import BytesIO
+
+from torch import Tensor
+from torch.utils.data import Dataset
+from torchvision.io import read_image
+from torchvision.transforms import ColorJitter
+from torchvision.transforms import InterpolationMode
+from torchvision.transforms import Normalize
+from torchvision.transforms.functional import hflip
+from torchvision.transforms.functional import pad
+from torchvision.transforms.functional import resize
+from torchvision.transforms.functional import rotate
+
+from core.database import connect
+from core.database import list_names
+
+# resnet18 original normalization values
+RESNET_NORMALIZE_MEAN = [0.485, 0.456, 0.406]
+RESNET_NORMALIZE_STD = [0.229, 0.224, 0.225]
+
+
+class VCDADataset(Dataset):
+    def __init__(
+        self,
+        do_augment: bool = False,
+        random_annotations: bool = False,
+        normalize_mean: list[float] = RESNET_NORMALIZE_MEAN,
+        normalize_std: list[float] = RESNET_NORMALIZE_STD,
+    ):
+        super().__init__()
+        self.do_augment = do_augment
+        self.random_annotations = random_annotations
+        self.normalize_mean = normalize_mean
+        self.normalize_std = normalize_std
+        # prepare augmentation functions
+        self.normalize = Normalize(
+            mean=normalize_mean,
+            std=normalize_std,
+        )
+        self.color_jitter = ColorJitter(
+            brightness=1e-1,
+            contrast=8e-2,
+            saturation=8e-2,
+        )
+        # connect to database
+        collection, _, _ = connect()
+        self.collection = collection
+        # load data names
+        has_annotation = False if self.random_annotations else True
+        self.data_name_list = list_names(
+            collection=self.collection,
+            has_annotation=has_annotation,
+        )
+
+    def __len__(self):
+        return len(self.data_name_list)
+
+    def __getitem__(self, idx):
+        # get image from database
+        name = self.data_name_list[idx]
+        query = {
+            'name': name,
+        }
+        projection = {
+            '_id': False,
+            'image': True,
+        }
+        img_bytes = self.collection.find_one(
+            filter=query,
+            projection=projection,
+        )
+        img = self.load_image(img_bytes)
+        if self.do_augment:
+            img = self.augment(img)
+        return img
+
+    def load_image(
+        self,
+        data: bytes,
+    ) -> Tensor:
+        """Load images tensor from bytes."""
+        assert isinstance(data, bytes)
+        img = read_image(BytesIO(data))
+        img /= 255  # normalize 8-bit image
+        img = self.square_pad(img)
+        img = resize(
+            img=img,
+            size=(512, 512),
+            interpolation=InterpolationMode.BICUBIC,
+        )
+        return img
+
+    @staticmethod
+    def square_pad(
+        img: Tensor,
+    ) -> Tensor:
+        """
+        Pads image to a square with side length
+        equal to the largest side of the input image.
+        """
+        assert isinstance(img, Tensor)
+        # B, nc, w, h = img.shape
+        h = img.shape[-2]
+        w = img.shape[-1]
+        if h == w:
+            return img
+        max_wh = max([h, w])
+        hp = int((max_wh - w) / 2)
+        vp = int((max_wh - h) / 2)
+        padding = (hp, vp, hp, vp)
+        return pad(img, padding, 0, 'constant')
+
+    def augment(
+        self,
+        img: Tensor,
+    ) -> Tensor:
+        """
+        Augment image with random horizontal flips,
+        rotations and color jitter.
+        """
+        assert isinstance(img, Tensor)
+        # left-right flip
+        if random.random() >= 0.5:
+            img = hflip(img)
+        # rotation
+        rnd = random.random()
+        if rnd < 0.25:
+            img = rotate(img, angle=90)
+        if rnd < 0.5:
+            img = rotate(img, angle=180)
+        if rnd < 0.75:
+            img = rotate(img, angle=270)
+        # color jitter
+        img = self.color_jitter(img)
+        return img
+
+    def reverse_normalise(
+        self,
+        img: Tensor,
+    ) -> Tensor:
+        """
+        Reverse normalization to get an image
+        that can be interpreted by humans.
+        """
+        assert isinstance(img, Tensor)
+        img *= Tensor(self.normalize_std).reshape((3, 1, 1))
+        img += Tensor(self.normalize_mean).reshape((3, 1, 1))
+        return img

model/src/loss_fn.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+import torch.nn as nn
+
+
+def setup_criterion():
+    return nn.MSELoss()

model/src/model.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+import torch.nn as nn
+import torchvision
+
+
+class ResNet18Head(nn.Module):
+    def __init__(self):
+        super().__init__()
+        # copy out parts from ResNet18 with weights
+        resnet18 = torchvision.models.resnet18(
+            weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1,
+        )
+        # save relevant layers
+        self.conv1 = resnet18.conv1
+        self.bn1 = resnet18.bn1
+        self.relu = resnet18.relu
+        self.maxpool = resnet18.maxpool
+        self.layer1 = resnet18.layer1
+        self.layer2 = resnet18.layer2
+        self.layer3 = resnet18.layer3
+        self.layer4 = resnet18.layer4
+        self.avgpool = resnet18.avgpool
+        self.flat = nn.Flatten()    # size 512
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+        x = self.maxpool(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+        x = self.avgpool(x)
+        x = self.flat(x)
+        return x

model/src/train.py

@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+from dataloader import VCDADataset  # noqa: F401
+from loss_fn import setup_criterion  # noqa: F401
+
+from model import ResNet18Head  # noqa: F401

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -381,6 +381,22 @@ idna = ["idna (>=3.6)"]
 trio = ["trio (>=0.23)"]
 wmi = ["wmi (>=1.5.1)"]
 
+[[package]]
+name = "filelock"
+version = "3.13.1"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "filelock-3.13.1-py3-none-any.whl", hash = "sha256:57dbda9b35157b05fb3e58ee91448612eb674172fab98ee235ccb0b5bee19a1c"},
+    {file = "filelock-3.13.1.tar.gz", hash = "sha256:521f5f56c50f8426f5e03ad3b281b490a87ef15bc6c526f168290f0c7148d44e"},
+]
+
+[package.extras]
+docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.24)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
+typing = ["typing-extensions (>=4.8)"]
+
 [[package]]
 name = "flake8"
 version = "7.0.0"
@@ -419,6 +435,41 @@ Werkzeug = ">=3.0.0"
 async = ["asgiref (>=3.2)"]
 dotenv = ["python-dotenv"]
 
+[[package]]
+name = "fsspec"
+version = "2024.2.0"
+description = "File-system specification"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fsspec-2024.2.0-py3-none-any.whl", hash = "sha256:817f969556fa5916bc682e02ca2045f96ff7f586d45110fcb76022063ad2c7d8"},
+    {file = "fsspec-2024.2.0.tar.gz", hash = "sha256:b6ad1a679f760dda52b1168c859d01b7b80648ea6f7f7c7f5a8a91dc3f3ecb84"},
+]
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+devel = ["pytest", "pytest-cov"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
+
 [[package]]
 name = "gunicorn"
 version = "21.2.0"
@@ -588,6 +639,23 @@ files = [
     {file = "mccabe-0.7.0.tar.gz", hash = "sha256:348e0240c33b60bbdf4e523192ef919f28cb2c3d7d5c7794f74009290f236325"},
 ]
 
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+optional = false
+python-versions = "*"
+files = [
+    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
 [[package]]
 name = "mypy"
 version = "1.8.0"
@@ -656,6 +724,24 @@ files = [
     {file = "nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe"},
 ]
 
+[[package]]
+name = "networkx"
+version = "3.2.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"},
+    {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"},
+]
+
+[package.extras]
+default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"]
+developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"]
+doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"]
+test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
 [[package]]
 name = "numpy"
 version = "1.26.4"
@@ -701,6 +787,147 @@ files = [
     {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
 ]
 
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+description = "CUBLAS native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
+]
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.1.105"
+description = "CUDA profiling tools runtime libs."
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
+]
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.1.105"
+description = "NVRTC native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
+]
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.1.105"
+description = "CUDA Runtime native Libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
+]
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "8.9.2.26"
+description = "cuDNN runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+description = "CUFFT native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.2.106"
+description = "CURAND native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
+]
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.4.5.107"
+description = "CUDA solver native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+nvidia-cusparse-cu12 = "*"
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+description = "CUSPARSE native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
+]
+
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.19.3"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:a9734707a2c96443331c1e48c717024aa6678a0e2a4cb66b2c364d18cee6b48d"},
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.4.99"
+description = "Nvidia JIT LTO Library"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvjitlink_cu12-12.4.99-py3-none-manylinux2014_x86_64.whl", hash = "sha256:c6428836d20fe7e327191c175791d38570e10762edc588fb46749217cd444c74"},
+    {file = "nvidia_nvjitlink_cu12-12.4.99-py3-none-win_amd64.whl", hash = "sha256:991905ffa2144cb603d8ca7962d75c35334ae82bf92820b6ba78157277da1ad2"},
+]
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.1.105"
+description = "NVIDIA Tools Extension"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
+]
+
 [[package]]
 name = "outcome"
 version = "1.3.0.post0"
@@ -1320,6 +1547,20 @@ files = [
     {file = "sortedcontainers-2.4.0.tar.gz", hash = "sha256:25caa5a06cc30b6b83d11423433f65d1f9d76c4c6a0c90e3379eaa43b9bfdb88"},
 ]
 
+[[package]]
+name = "sympy"
+version = "1.12"
+description = "Computer algebra system (CAS) in Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
+    {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"},
+]
+
+[package.dependencies]
+mpmath = ">=0.19"
+
 [[package]]
 name = "tenacity"
 version = "8.2.3"
@@ -1334,6 +1575,105 @@ files = [
 [package.extras]
 doc = ["reno", "sphinx", "tornado (>=4.5)"]
 
+[[package]]
+name = "torch"
+version = "2.2.1"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "torch-2.2.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:8d3bad336dd2c93c6bcb3268e8e9876185bda50ebde325ef211fb565c7d15273"},
+    {file = "torch-2.2.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:5297f13370fdaca05959134b26a06a7f232ae254bf2e11a50eddec62525c9006"},
+    {file = "torch-2.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:5f5dee8433798888ca1415055f5e3faf28a3bad660e4c29e1014acd3275ab11a"},
+    {file = "torch-2.2.1-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:b6d78338acabf1fb2e88bf4559d837d30230cf9c3e4337261f4d83200df1fcbe"},
+    {file = "torch-2.2.1-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:6ab3ea2e29d1aac962e905142bbe50943758f55292f1b4fdfb6f4792aae3323e"},
+    {file = "torch-2.2.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:d86664ec85902967d902e78272e97d1aff1d331f7619d398d3ffab1c9b8e9157"},
+    {file = "torch-2.2.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:d6227060f268894f92c61af0a44c0d8212e19cb98d05c20141c73312d923bc0a"},
+    {file = "torch-2.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:77e990af75fb1675490deb374d36e726f84732cd5677d16f19124934b2409ce9"},
+    {file = "torch-2.2.1-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:46085e328d9b738c261f470231e987930f4cc9472d9ffb7087c7a1343826ac51"},
+    {file = "torch-2.2.1-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:2d9e7e5ecbb002257cf98fae13003abbd620196c35f85c9e34c2adfb961321ec"},
+    {file = "torch-2.2.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:ada53aebede1c89570e56861b08d12ba4518a1f8b82d467c32665ec4d1f4b3c8"},
+    {file = "torch-2.2.1-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:be21d4c41ecebed9e99430dac87de1439a8c7882faf23bba7fea3fea7b906ac1"},
+    {file = "torch-2.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:79848f46196750367dcdf1d2132b722180b9d889571e14d579ae82d2f50596c5"},
+    {file = "torch-2.2.1-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:7ee804847be6be0032fbd2d1e6742fea2814c92bebccb177f0d3b8e92b2d2b18"},
+    {file = "torch-2.2.1-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:84b2fb322ab091039fdfe74e17442ff046b258eb5e513a28093152c5b07325a7"},
+    {file = "torch-2.2.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:5c0c83aa7d94569997f1f474595e808072d80b04d34912ce6f1a0e1c24b0c12a"},
+    {file = "torch-2.2.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:91a1b598055ba06b2c386415d2e7f6ac818545e94c5def597a74754940188513"},
+    {file = "torch-2.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:8f93ddf3001ecec16568390b507652644a3a103baa72de3ad3b9c530e3277098"},
+    {file = "torch-2.2.1-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:0e8bdd4c77ac2584f33ee14c6cd3b12767b4da508ec4eed109520be7212d1069"},
+    {file = "torch-2.2.1-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:6a21bcd7076677c97ca7db7506d683e4e9db137e8420eb4a68fb67c3668232a7"},
+    {file = "torch-2.2.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:f1b90ac61f862634039265cd0f746cc9879feee03ff962c803486301b778714b"},
+    {file = "torch-2.2.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:ed9e29eb94cd493b36bca9cb0b1fd7f06a0688215ad1e4b3ab4931726e0ec092"},
+    {file = "torch-2.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:c47bc25744c743f3835831a20efdcfd60aeb7c3f9804a213f61e45803d16c2a5"},
+    {file = "torch-2.2.1-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:0952549bcb43448c8d860d5e3e947dd18cbab491b14638e21750cb3090d5ad3e"},
+    {file = "torch-2.2.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:26bd2272ec46fc62dcf7d24b2fb284d44fcb7be9d529ebf336b9860350d674ed"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+jinja2 = "*"
+networkx = "*"
+nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+typing-extensions = ">=4.8.0"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+optree = ["optree (>=0.9.1)"]
+
+[[package]]
+name = "torchvision"
+version = "0.17.1"
+description = "image and video datasets and models for torch deep learning"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "torchvision-0.17.1-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:06418880212b66e45e855dd39f536e7fd48b4e6b034a11dd9fe9e2384afb51ec"},
+    {file = "torchvision-0.17.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:33d65d0c7fdcb3f7bc1dd8ed30ea3cd7e0587b4ad1b104b5677c8191a8bad9f1"},
+    {file = "torchvision-0.17.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:aaefef2be6a02f206085ce4bb6c0078b03ebf48cb6ff82bd762ff6248475e08e"},
+    {file = "torchvision-0.17.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:ebe5fdb466aff8a8e8e755de84a843418b6f8d500624752c05eaa638d7700f3d"},
+    {file = "torchvision-0.17.1-cp310-cp310-win_amd64.whl", hash = "sha256:9d4d45a996f4313e9c5db4da71d31508d44f7ccfbf29d3442bdcc2ad13e0b6f3"},
+    {file = "torchvision-0.17.1-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:ea2ccdbf5974e0bf27fd6644a33b19cb0700297cf397bb0469e762c11c6c4105"},
+    {file = "torchvision-0.17.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9106e32c9f1e70afa8172cf1b064cf9c2998d8dff0769ec69d537b20209ee43d"},
+    {file = "torchvision-0.17.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:5966936c669a08870f6547cd0a90d08b157aeda03293f79e2adbb934687175ed"},
+    {file = "torchvision-0.17.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:e74f5a26ef8190eab0c38b3f63914fea94e58e3b2f0e5466611c9f63bd91a80b"},
+    {file = "torchvision-0.17.1-cp311-cp311-win_amd64.whl", hash = "sha256:a2109c1a1dcf71e8940d43e91f78c4dd5bf0fcefb3a0a42244102752009f5862"},
+    {file = "torchvision-0.17.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5d241d2a5fb4e608677fccf6f80b34a124446d324ee40c7814ce54bce888275b"},
+    {file = "torchvision-0.17.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e0fe98d9d92c23d2262ff82f973242951b9357fb640f8888ac50848bd00f5b45"},
+    {file = "torchvision-0.17.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:32dc5de86d2ade399e11087095674ca08a1649fb322cfe69336d28add467edcb"},
+    {file = "torchvision-0.17.1-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:54902877410ffb5458ee52b6d0de4b25cf01496bee736d6825301a5f0398536e"},
+    {file = "torchvision-0.17.1-cp312-cp312-win_amd64.whl", hash = "sha256:cc22c1ed0f1aba3f98fd72b6f60021f57aec1d2f6af518522e8a0a83848de3a8"},
+    {file = "torchvision-0.17.1-cp38-cp38-macosx_10_13_x86_64.whl", hash = "sha256:2621097065fa1c827885e2b52102e839a3541b933b7a90e0fa3c42c3de1bc3cf"},
+    {file = "torchvision-0.17.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5ce76466af2b5a30573939cae1e6e62e29316ceb3ee748091002f312ab0912f6"},
+    {file = "torchvision-0.17.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:bd5dcd14a32945c72f5c19341add94aa7c23dd7bca2bafde44d0f3c4344d17ed"},
+    {file = "torchvision-0.17.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:dca22795cc02ca0d5ddc08c1422ff620bc9899f63d15dc36f71ef37250e17b75"},
+    {file = "torchvision-0.17.1-cp38-cp38-win_amd64.whl", hash = "sha256:524405457dd97d9ab0e48df502f819d0f41a113ce8f00470bb9926d9d36efcf1"},
+    {file = "torchvision-0.17.1-cp39-cp39-macosx_10_13_x86_64.whl", hash = "sha256:58299a724b37b893c7ce4d0b32ea1480c30e467cc114167964b45f6013f6c2d3"},
+    {file = "torchvision-0.17.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8a1b17fb158b2b881f2c8796fe1839a624e49d5fd07aa61f6dae60ba4819421a"},
+    {file = "torchvision-0.17.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:429d63eb7551aa4d8f6cdf08d109b5570c20cbcce36d9cb95b24556418e4dc82"},
+    {file = "torchvision-0.17.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:0ecc9a58171bd555aed583bf2f72e7fd6cc4f767c14f8b80b6a8725eacf4ceb1"},
+    {file = "torchvision-0.17.1-cp39-cp39-win_amd64.whl", hash = "sha256:5f427ebee15521edcd836bfe05e86feb5189b5c943b9e3999ed0e3f391fbaa1d"},
+]
+
+[package.dependencies]
+numpy = "*"
+pillow = ">=5.3.0,<8.3.dev0 || >=8.4.dev0"
+torch = "2.2.1"
+
+[package.extras]
+scipy = ["scipy"]
+
 [[package]]
 name = "trio"
 version = "0.24.0"
@@ -1486,4 +1826,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.12"
-content-hash = "849178e665e9a43935d7508528a82d8e0e173020b9ee4256e6a25d3e607f1bd8"
+content-hash = "6c4bb66c774e93a08e4180f3148942edf91e2b5620ea1f6c3e4c30045bb643e5"

pyproject.toml

@@ -33,6 +33,11 @@ selenium = "^4.18.1"
 webdriver-manager = "^4.0.1"
 retry = "^0.9.2"
 
+
+[tool.poetry.group.model.dependencies]
+torch = "^2.2.1"
+torchvision = "^0.17.1"
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"