dnt 0.2.1__py3-none-any.whl → 0.3.1.8__py3-none-any.whl

dnt/third_party/fast-reid/fastreid/data/datasets/veri.py

@@ -0,0 +1,69 @@
+# encoding: utf-8
+"""
+@author:  Jinkai Zheng
+@contact: 1315673509@qq.com
+"""
+
+import glob
+import os.path as osp
+import re
+
+from .bases import ImageDataset
+from ..datasets import DATASET_REGISTRY
+
+
+@DATASET_REGISTRY.register()
+class VeRi(ImageDataset):
+    """VeRi.
+
+    Reference:
+        Xinchen Liu et al. A Deep Learning based Approach for Progressive Vehicle Re-Identification. ECCV 2016.
+        Xinchen Liu et al. PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance. IEEE TMM 2018.
+
+    URL: `<https://vehiclereid.github.io/VeRi/>`_
+
+    Dataset statistics:
+        - identities: 775.
+        - images: 37778 (train) + 1678 (query) + 11579 (gallery).
+    """
+    dataset_dir = "veri"
+    dataset_name = "veri"
+
+    def __init__(self, root='datasets', **kwargs):
+        self.dataset_dir = osp.join(root, self.dataset_dir)
+
+        self.train_dir = osp.join(self.dataset_dir, 'image_train')
+        self.query_dir = osp.join(self.dataset_dir, 'image_query')
+        self.gallery_dir = osp.join(self.dataset_dir, 'image_test')
+
+        required_files = [
+            self.dataset_dir,
+            self.train_dir,
+            self.query_dir,
+            self.gallery_dir,
+        ]
+        self.check_before_run(required_files)
+
+        train = self.process_dir(self.train_dir)
+        query = self.process_dir(self.query_dir, is_train=False)
+        gallery = self.process_dir(self.gallery_dir, is_train=False)
+
+        super(VeRi, self).__init__(train, query, gallery, **kwargs)
+
+    def process_dir(self, dir_path, is_train=True):
+        img_paths = glob.glob(osp.join(dir_path, '*.jpg'))
+        pattern = re.compile(r'([\d]+)_c(\d\d\d)')
+
+        data = []
+        for img_path in img_paths:
+            pid, camid = map(int, pattern.search(img_path).groups())
+            if pid == -1: continue  # junk images are just ignored
+            assert 0 <= pid <= 776
+            assert 1 <= camid <= 20
+            camid -= 1  # index starts from 0
+            if is_train:
+                pid = self.dataset_name + "_" + str(pid)
+                camid = self.dataset_name + "_" + str(camid)
+            data.append((img_path, pid, camid))
+
+        return data

dnt/third_party/fast-reid/fastreid/data/datasets/veriwild.py

@@ -0,0 +1,140 @@
+# encoding: utf-8
+"""
+@author:  Jinkai Zheng
+@contact: 1315673509@qq.com
+"""
+
+import os.path as osp
+
+from .bases import ImageDataset
+from ..datasets import DATASET_REGISTRY
+
+
+@DATASET_REGISTRY.register()
+class VeRiWild(ImageDataset):
+    """VeRi-Wild.
+
+    Reference:
+        Lou et al. A Large-Scale Dataset for Vehicle Re-Identification in the Wild. CVPR 2019.
+
+    URL: `<https://github.com/PKU-IMRE/VERI-Wild>`_
+
+    Train dataset statistics:
+        - identities: 30671.
+        - images: 277797.
+    """
+    dataset_dir = "VERI-Wild"
+    dataset_name = "veriwild"
+
+    def __init__(self, root='datasets', query_list='', gallery_list='', **kwargs):
+        self.dataset_dir = osp.join(root, self.dataset_dir)
+
+        self.image_dir = osp.join(self.dataset_dir, 'images')
+        self.train_list = osp.join(self.dataset_dir, 'train_test_split/train_list.txt')
+        self.vehicle_info = osp.join(self.dataset_dir, 'train_test_split/vehicle_info.txt')
+        if query_list and gallery_list:
+            self.query_list = query_list
+            self.gallery_list = gallery_list
+        else:
+            self.query_list = osp.join(self.dataset_dir, 'train_test_split/test_10000_query.txt')
+            self.gallery_list = osp.join(self.dataset_dir, 'train_test_split/test_10000.txt')
+
+        required_files = [
+            self.image_dir,
+            self.train_list,
+            self.query_list,
+            self.gallery_list,
+            self.vehicle_info,
+        ]
+        self.check_before_run(required_files)
+
+        self.imgid2vid, self.imgid2camid, self.imgid2imgpath = self.process_vehicle(self.vehicle_info)
+
+        train = self.process_dir(self.train_list)
+        query = self.process_dir(self.query_list, is_train=False)
+        gallery = self.process_dir(self.gallery_list, is_train=False)
+
+        super(VeRiWild, self).__init__(train, query, gallery, **kwargs)
+
+    def process_dir(self, img_list, is_train=True):
+        img_list_lines = open(img_list, 'r').readlines()
+
+        dataset = []
+        for idx, line in enumerate(img_list_lines):
+            line = line.strip()
+            vid = int(line.split('/')[0])
+            imgid = line.split('/')[1].split('.')[0]
+            camid = int(self.imgid2camid[imgid])
+            if is_train:
+                vid = f"{self.dataset_name}_{vid}"
+                camid = f"{self.dataset_name}_{camid}"
+            dataset.append((self.imgid2imgpath[imgid], vid, camid))
+
+        assert len(dataset) == len(img_list_lines)
+        return dataset
+
+    def process_vehicle(self, vehicle_info):
+        imgid2vid = {}
+        imgid2camid = {}
+        imgid2imgpath = {}
+        vehicle_info_lines = open(vehicle_info, 'r').readlines()
+
+        for idx, line in enumerate(vehicle_info_lines[1:]):
+            vid = line.strip().split('/')[0]
+            imgid = line.strip().split(';')[0].split('/')[1]
+            camid = line.strip().split(';')[1]
+            img_path = osp.join(self.image_dir, vid, imgid + '.jpg')
+            imgid2vid[imgid] = vid
+            imgid2camid[imgid] = camid
+            imgid2imgpath[imgid] = img_path
+
+        assert len(imgid2vid) == len(vehicle_info_lines) - 1
+        return imgid2vid, imgid2camid, imgid2imgpath
+
+
+@DATASET_REGISTRY.register()
+class SmallVeRiWild(VeRiWild):
+    """VeRi-Wild.
+    Small test dataset statistics:
+        - identities: 3000.
+        - images: 41861.
+    """
+
+    def __init__(self, root='datasets', **kwargs):
+        dataset_dir = osp.join(root, self.dataset_dir)
+        self.query_list = osp.join(dataset_dir, 'train_test_split/test_3000_query.txt')
+        self.gallery_list = osp.join(dataset_dir, 'train_test_split/test_3000.txt')
+
+        super(SmallVeRiWild, self).__init__(root, self.query_list, self.gallery_list, **kwargs)
+
+
+@DATASET_REGISTRY.register()
+class MediumVeRiWild(VeRiWild):
+    """VeRi-Wild.
+    Medium test dataset statistics:
+        - identities: 5000.
+        - images: 69389.
+    """
+
+    def __init__(self, root='datasets', **kwargs):
+        dataset_dir = osp.join(root, self.dataset_dir)
+        self.query_list = osp.join(dataset_dir, 'train_test_split/test_5000_query.txt')
+        self.gallery_list = osp.join(dataset_dir, 'train_test_split/test_5000.txt')
+
+        super(MediumVeRiWild, self).__init__(root, self.query_list, self.gallery_list, **kwargs)
+
+
+@DATASET_REGISTRY.register()
+class LargeVeRiWild(VeRiWild):
+    """VeRi-Wild.
+    Large test dataset statistics:
+        - identities: 10000.
+        - images: 138517.
+    """
+
+    def __init__(self, root='datasets', **kwargs):
+        dataset_dir = osp.join(root, self.dataset_dir)
+        self.query_list = osp.join(dataset_dir, 'train_test_split/test_10000_query.txt')
+        self.gallery_list = osp.join(dataset_dir, 'train_test_split/test_10000.txt')
+
+        super(LargeVeRiWild, self).__init__(root, self.query_list, self.gallery_list, **kwargs)

dnt/third_party/fast-reid/fastreid/data/datasets/viper.py

@@ -0,0 +1,45 @@
+# encoding: utf-8
+"""
+@author:  xingyu liao
+@contact: sherlockliao01@gmail.com
+"""
+
+import os
+from glob import glob
+
+from fastreid.data.datasets import DATASET_REGISTRY
+from fastreid.data.datasets.bases import ImageDataset
+
+__all__ = ['VIPeR', ]
+
+
+@DATASET_REGISTRY.register()
+class VIPeR(ImageDataset):
+    dataset_dir = "VIPeR"
+    dataset_name = "viper"
+
+    def __init__(self, root='datasets', **kwargs):
+        self.root = root
+        self.train_path = os.path.join(self.root, self.dataset_dir)
+
+        required_files = [self.train_path]
+        self.check_before_run(required_files)
+
+        train = self.process_train(self.train_path)
+
+        super().__init__(train, [], [], **kwargs)
+
+    def process_train(self, train_path):
+        data = []
+
+        file_path_list = ['cam_a', 'cam_b']
+
+        for file_path in file_path_list:
+            camid = self.dataset_name + "_" + file_path
+            img_list = glob(os.path.join(train_path, file_path, "*.bmp"))
+            for img_path in img_list:
+                img_name = img_path.split('/')[-1]
+                pid = self.dataset_name + "_" + img_name.split('_')[0]
+                data.append([img_path, pid, camid])
+
+        return data

dnt/third_party/fast-reid/fastreid/data/datasets/wildtracker.py

@@ -0,0 +1,59 @@
+# encoding: utf-8
+"""
+@author:  wangguanan
+@contact: guan.wang0706@gmail.com
+"""
+
+import glob
+import os
+
+from .bases import ImageDataset
+from ..datasets import DATASET_REGISTRY
+
+
+@DATASET_REGISTRY.register()
+class WildTrackCrop(ImageDataset):
+    """WildTrack.
+    Reference:
+        WILDTRACK: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection
+            T. Chavdarova; P. Baqué; A. Maksai; S. Bouquet; C. Jose et al.
+    URL: `<https://www.epfl.ch/labs/cvlab/data/data-wildtrack/>`_
+    Dataset statistics:
+        - identities: 313
+        - images: 33979 (train only)
+        - cameras: 7
+    Args:
+        data_path(str): path to WildTrackCrop dataset
+        combineall(bool): combine train and test sets as train set if True
+    """
+    dataset_url = None
+    dataset_dir = 'Wildtrack_crop_dataset'
+    dataset_name = 'wildtrack'
+
+    def __init__(self, root='datasets', **kwargs):
+        self.root = root
+        self.dataset_dir = os.path.join(self.root, self.dataset_dir)
+
+        self.train_dir = os.path.join(self.dataset_dir, "crop")
+
+        train = self.process_dir(self.train_dir)
+        query = []
+        gallery = []
+
+        super(WildTrackCrop, self).__init__(train, query, gallery, **kwargs)
+
+    def process_dir(self, dir_path):
+        r"""
+        :param dir_path: directory path saving images
+        Returns
+            data(list) = [img_path, pid, camid]
+        """
+        data = []
+        for dir_name in os.listdir(dir_path):
+            img_lists = glob.glob(os.path.join(dir_path, dir_name, "*.png"))
+            for img_path in img_lists:
+                pid = self.dataset_name + "_" + dir_name
+                camid = img_path.split('/')[-1].split('_')[0]
+                camid = self.dataset_name + "_" + camid
+                data.append([img_path, pid, camid])
+        return data

dnt/third_party/fast-reid/fastreid/data/samplers/__init__.py

@@ -0,0 +1,18 @@
+# encoding: utf-8
+"""
+@author:  liaoxingyu
+@contact: sherlockliao01@gmail.com
+"""
+
+from .triplet_sampler import BalancedIdentitySampler, NaiveIdentitySampler, SetReWeightSampler
+from .data_sampler import TrainingSampler, InferenceSampler
+from .imbalance_sampler import ImbalancedDatasetSampler
+
+__all__ = [
+    "BalancedIdentitySampler",
+    "NaiveIdentitySampler",
+    "SetReWeightSampler",
+    "TrainingSampler",
+    "InferenceSampler",
+    "ImbalancedDatasetSampler",
+]

dnt/third_party/fast-reid/fastreid/data/samplers/data_sampler.py

@@ -0,0 +1,85 @@
+# encoding: utf-8
+"""
+@author:  l1aoxingyu
+@contact: sherlockliao01@gmail.com
+"""
+import itertools
+from typing import Optional
+
+import numpy as np
+from torch.utils.data import Sampler
+
+from fastreid.utils import comm
+
+
+class TrainingSampler(Sampler):
+    """
+    In training, we only care about the "infinite stream" of training data.
+    So this sampler produces an infinite stream of indices and
+    all workers cooperate to correctly shuffle the indices and sample different indices.
+    The samplers in each worker effectively produces `indices[worker_id::num_workers]`
+    where `indices` is an infinite stream of indices consisting of
+    `shuffle(range(size)) + shuffle(range(size)) + ...` (if shuffle is True)
+    or `range(size) + range(size) + ...` (if shuffle is False)
+    """
+
+    def __init__(self, size: int, shuffle: bool = True, seed: Optional[int] = None):
+        """
+        Args:
+            size (int): the total number of data of the underlying dataset to sample from
+            shuffle (bool): whether to shuffle the indices or not
+            seed (int): the initial seed of the shuffle. Must be the same
+                across all workers. If None, will use a random seed shared
+                among workers (require synchronization among all workers).
+        """
+        self._size = size
+        assert size > 0
+        self._shuffle = shuffle
+        if seed is None:
+            seed = comm.shared_random_seed()
+        self._seed = int(seed)
+
+        self._rank = comm.get_rank()
+        self._world_size = comm.get_world_size()
+
+    def __iter__(self):
+        start = self._rank
+        yield from itertools.islice(self._infinite_indices(), start, None, self._world_size)
+
+    def _infinite_indices(self):
+        np.random.seed(self._seed)
+        while True:
+            if self._shuffle:
+                yield from np.random.permutation(self._size)
+            else:
+                yield from np.arange(self._size)
+
+
+class InferenceSampler(Sampler):
+    """
+    Produce indices for inference.
+    Inference needs to run on the __exact__ set of samples,
+    therefore when the total number of samples is not divisible by the number of workers,
+    this sampler produces different number of samples on different workers.
+    """
+
+    def __init__(self, size: int):
+        """
+        Args:
+            size (int): the total number of data of the underlying dataset to sample from
+        """
+        self._size = size
+        assert size > 0
+        self._rank = comm.get_rank()
+        self._world_size = comm.get_world_size()
+
+        shard_size = (self._size - 1) // self._world_size + 1
+        begin = shard_size * self._rank
+        end = min(shard_size * (self._rank + 1), self._size)
+        self._local_indices = range(begin, end)
+
+    def __iter__(self):
+        yield from self._local_indices
+
+    def __len__(self):
+        return len(self._local_indices)

dnt/third_party/fast-reid/fastreid/data/samplers/imbalance_sampler.py

@@ -0,0 +1,67 @@
+# encoding: utf-8
+"""
+@author:  xingyu liao
+@contact: sherlockliao01@gmail.com
+"""
+
+# based on:
+# https://github.com/ufoym/imbalanced-dataset-sampler/blob/master/torchsampler/imbalanced.py
+
+
+import itertools
+from typing import Optional, List, Callable
+
+import numpy as np
+import torch
+from torch.utils.data.sampler import Sampler
+
+from fastreid.utils import comm
+
+
+class ImbalancedDatasetSampler(Sampler):
+    """Samples elements randomly from a given list of indices for imbalanced dataset
+    Arguments:
+        data_source: a list of data items
+        size: number of samples to draw
+    """
+
+    def __init__(self, data_source: List, size: int = None, seed: Optional[int] = None,
+                 callback_get_label: Callable = None):
+        self.data_source = data_source
+        # consider all elements in the dataset
+        self.indices = list(range(len(data_source)))
+        # if num_samples is not provided, draw `len(indices)` samples in each iteration
+        self._size = len(self.indices) if size is None else size
+        self.callback_get_label = callback_get_label
+
+        # distribution of classes in the dataset
+        label_to_count = {}
+        for idx in self.indices:
+            label = self._get_label(data_source, idx)
+            label_to_count[label] = label_to_count.get(label, 0) + 1
+
+        # weight for each sample
+        weights = [1.0 / label_to_count[self._get_label(data_source, idx)] for idx in self.indices]
+        self.weights = torch.DoubleTensor(weights)
+
+        if seed is None:
+            seed = comm.shared_random_seed()
+        self._seed = int(seed)
+        self._rank = comm.get_rank()
+        self._world_size = comm.get_world_size()
+
+    def _get_label(self, dataset, idx):
+        if self.callback_get_label:
+            return self.callback_get_label(dataset, idx)
+        else:
+            return dataset[idx][1]
+
+    def __iter__(self):
+        start = self._rank
+        yield from itertools.islice(self._infinite_indices(), start, None, self._world_size)
+
+    def _infinite_indices(self):
+        np.random.seed(self._seed)
+        while True:
+            for i in torch.multinomial(self.weights, self._size, replacement=True):
+                yield self.indices[i]