Gradio-Blocks / ViTPose deployment on Runpod

_steps.md

Spaces

• Docker Repo registry.hf.space/gradio-blocks-vitpose:latest
• Start Command python -c "import time; time.sleep(86400)" Sleep required to edit the files via web console

// https://pytorch.org/get-started/previous-versions/
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113

wget https://gist.githubusercontent.com/tjunxiang92/5e9f5b003030f2c1b4d29968a2ef73a5/raw/d6f31a7f30899ffc08125572ac40c5cdb427a063/site_packages_builder.py
mv site_packages_builder.py /home/user/.local/lib/python3.10/site-packages/mmdet/datasets/builder.py

wget https://gist.githubusercontent.com/tjunxiang92/5e9f5b003030f2c1b4d29968a2ef73a5/raw/d6f31a7f30899ffc08125572ac40c5cdb427a063/user_app_builder.py
mv user_app_builder.py /home/user/app/ViTPose/mmpose/datasets/builder.py
mv user_app_builder.py /home/user/.local/lib/python3.10/site-packages/mmpose/datasets/builder.py

python app.py

Spaces ViTPose_video

// https://pytorch.org/get-started/previous-versions/
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113

wget https://gist.githubusercontent.com/tjunxiang92/5e9f5b003030f2c1b4d29968a2ef73a5/raw/82fc7862800f5a721d5e8070226c476a3c55bbc0/mmdet_builder.py
cp mmdet_builder.py /home/user/.local/lib/python3.10/site-packages/mmdet/datasets/builder.py
wget https://gist.githubusercontent.com/tjunxiang92/5e9f5b003030f2c1b4d29968a2ef73a5/raw/82fc7862800f5a721d5e8070226c476a3c55bbc0/mmpose_builder.py
cp mmpose_builder.py /home/user/app/ViTPose/mmpose/datasets/builder.py

python app.py

Downloading: "https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_tiny_8x8_300e_coco/yolox_tiny_8x8_300e_coco_20211124_171234-b4047906.pth" to /home/user/.cache/torch/hub/checkpoints/yolox_tiny_8x8_300e_coco_20211124_171234-b4047906.pth
Downloading: "https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth" to /home/user/.cache/torch/hub/checkpoints/yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth
Downloading: "https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_l_8x8_300e_coco/yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth" to /home/user/.cache/torch/hub/checkpoints/yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth
Downloading: "https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth" to /home/user/.cache/torch/hub/checkpoints/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth
Downloading: "https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth" to /home/user/.cache/torch/hub/checkpoints/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth

mmdet_builder.py

# Copyright (c) OpenMMLab. All rights reserved.
import copy
import platform
import random
import warnings
from functools import partial

import numpy as np
import torch
from mmcv.parallel import collate
from mmcv.runner import get_dist_info
from mmcv.utils import TORCH_VERSION, Registry, build_from_cfg, digit_version
from torch.utils.data import DataLoader

from .samplers import (ClassAwareSampler, DistributedGroupSampler,
                       DistributedSampler, GroupSampler, InfiniteBatchSampler,
                       InfiniteGroupBatchSampler)

if platform.system() != 'Windows':
    # https://github.com/pytorch/pytorch/issues/973
    import resource
    rlimit = resource.getrlimit(resource.RLIMIT_NOFILE)
    base_soft_limit = rlimit[0]
    hard_limit = rlimit[1]
    soft_limit = min(max(4096, base_soft_limit), hard_limit)
    # resource.setrlimit(resource.RLIMIT_NOFILE, (soft_limit, hard_limit))

DATASETS = Registry('dataset')
PIPELINES = Registry('pipeline')


def _concat_dataset(cfg, default_args=None):
    from .dataset_wrappers import ConcatDataset
    ann_files = cfg['ann_file']
    img_prefixes = cfg.get('img_prefix', None)
    seg_prefixes = cfg.get('seg_prefix', None)
    proposal_files = cfg.get('proposal_file', None)
    separate_eval = cfg.get('separate_eval', True)

    datasets = []
    num_dset = len(ann_files)
    for i in range(num_dset):
        data_cfg = copy.deepcopy(cfg)
        # pop 'separate_eval' since it is not a valid key for common datasets.
        if 'separate_eval' in data_cfg:
            data_cfg.pop('separate_eval')
        data_cfg['ann_file'] = ann_files[i]
        if isinstance(img_prefixes, (list, tuple)):
            data_cfg['img_prefix'] = img_prefixes[i]
        if isinstance(seg_prefixes, (list, tuple)):
            data_cfg['seg_prefix'] = seg_prefixes[i]
        if isinstance(proposal_files, (list, tuple)):
            data_cfg['proposal_file'] = proposal_files[i]
        datasets.append(build_dataset(data_cfg, default_args))

    return ConcatDataset(datasets, separate_eval)


def build_dataset(cfg, default_args=None):
    from .dataset_wrappers import (ClassBalancedDataset, ConcatDataset,
                                   MultiImageMixDataset, RepeatDataset)
    if isinstance(cfg, (list, tuple)):
        dataset = ConcatDataset([build_dataset(c, default_args) for c in cfg])
    elif cfg['type'] == 'ConcatDataset':
        dataset = ConcatDataset(
            [build_dataset(c, default_args) for c in cfg['datasets']],
            cfg.get('separate_eval', True))
    elif cfg['type'] == 'RepeatDataset':
        dataset = RepeatDataset(
            build_dataset(cfg['dataset'], default_args), cfg['times'])
    elif cfg['type'] == 'ClassBalancedDataset':
        dataset = ClassBalancedDataset(
            build_dataset(cfg['dataset'], default_args), cfg['oversample_thr'])
    elif cfg['type'] == 'MultiImageMixDataset':
        cp_cfg = copy.deepcopy(cfg)
        cp_cfg['dataset'] = build_dataset(cp_cfg['dataset'])
        cp_cfg.pop('type')
        dataset = MultiImageMixDataset(**cp_cfg)
    elif isinstance(cfg.get('ann_file'), (list, tuple)):
        dataset = _concat_dataset(cfg, default_args)
    else:
        dataset = build_from_cfg(cfg, DATASETS, default_args)

    return dataset


def build_dataloader(dataset,
                     samples_per_gpu,
                     workers_per_gpu,
                     num_gpus=1,
                     dist=True,
                     shuffle=True,
                     seed=None,
                     runner_type='EpochBasedRunner',
                     persistent_workers=False,
                     class_aware_sampler=None,
                     **kwargs):
    """Build PyTorch DataLoader.

    In distributed training, each GPU/process has a dataloader.
    In non-distributed training, there is only one dataloader for all GPUs.

    Args:
        dataset (Dataset): A PyTorch dataset.
        samples_per_gpu (int): Number of training samples on each GPU, i.e.,
            batch size of each GPU.
        workers_per_gpu (int): How many subprocesses to use for data loading
            for each GPU.
        num_gpus (int): Number of GPUs. Only used in non-distributed training.
        dist (bool): Distributed training/test or not. Default: True.
        shuffle (bool): Whether to shuffle the data at every epoch.
            Default: True.
        seed (int, Optional): Seed to be used. Default: None.
        runner_type (str): Type of runner. Default: `EpochBasedRunner`
        persistent_workers (bool): If True, the data loader will not shutdown
            the worker processes after a dataset has been consumed once.
            This allows to maintain the workers `Dataset` instances alive.
            This argument is only valid when PyTorch>=1.7.0. Default: False.
        class_aware_sampler (dict): Whether to use `ClassAwareSampler`
            during training. Default: None.
        kwargs: any keyword argument to be used to initialize DataLoader

    Returns:
        DataLoader: A PyTorch dataloader.
    """
    rank, world_size = get_dist_info()

    if dist:
        # When model is :obj:`DistributedDataParallel`,
        # `batch_size` of :obj:`dataloader` is the
        # number of training samples on each GPU.
        batch_size = samples_per_gpu
        num_workers = workers_per_gpu
    else:
        # When model is obj:`DataParallel`
        # the batch size is samples on all the GPUS
        batch_size = num_gpus * samples_per_gpu
        num_workers = num_gpus * workers_per_gpu

    if runner_type == 'IterBasedRunner':
        # this is a batch sampler, which can yield
        # a mini-batch indices each time.
        # it can be used in both `DataParallel` and
        # `DistributedDataParallel`
        if shuffle:
            batch_sampler = InfiniteGroupBatchSampler(
                dataset, batch_size, world_size, rank, seed=seed)
        else:
            batch_sampler = InfiniteBatchSampler(
                dataset,
                batch_size,
                world_size,
                rank,
                seed=seed,
                shuffle=False)
        batch_size = 1
        sampler = None
    else:
        if class_aware_sampler is not None:
            # ClassAwareSampler can be used in both distributed and
            # non-distributed training.
            num_sample_class = class_aware_sampler.get('num_sample_class', 1)
            sampler = ClassAwareSampler(
                dataset,
                samples_per_gpu,
                world_size,
                rank,
                seed=seed,
                num_sample_class=num_sample_class)
        elif dist:
            # DistributedGroupSampler will definitely shuffle the data to
            # satisfy that images on each GPU are in the same group
            if shuffle:
                sampler = DistributedGroupSampler(
                    dataset, samples_per_gpu, world_size, rank, seed=seed)
            else:
                sampler = DistributedSampler(
                    dataset, world_size, rank, shuffle=False, seed=seed)
        else:
            sampler = GroupSampler(dataset,
                                   samples_per_gpu) if shuffle else None
        batch_sampler = None

    init_fn = partial(
        worker_init_fn, num_workers=num_workers, rank=rank,
        seed=seed) if seed is not None else None

    if (TORCH_VERSION != 'parrots'
            and digit_version(TORCH_VERSION) >= digit_version('1.7.0')):
        kwargs['persistent_workers'] = persistent_workers
    elif persistent_workers is True:
        warnings.warn('persistent_workers is invalid because your pytorch '
                      'version is lower than 1.7.0')

    data_loader = DataLoader(
        dataset,
        batch_size=batch_size,
        sampler=sampler,
        num_workers=num_workers,
        batch_sampler=batch_sampler,
        collate_fn=partial(collate, samples_per_gpu=samples_per_gpu),
        pin_memory=kwargs.pop('pin_memory', False),
        worker_init_fn=init_fn,
        **kwargs)

    return data_loader


def worker_init_fn(worker_id, num_workers, rank, seed):
    # The seed of each worker equals to
    # num_worker * rank + worker_id + user_seed
    worker_seed = num_workers * rank + worker_id + seed
    np.random.seed(worker_seed)
    random.seed(worker_seed)
    torch.manual_seed(worker_seed)

mmpose_builder.py

# Copyright (c) OpenMMLab. All rights reserved.
import copy
import platform
import random
from functools import partial

import numpy as np
from mmcv.parallel import collate
from mmcv.runner import get_dist_info
from mmcv.utils import Registry, build_from_cfg, is_seq_of
from mmcv.utils.parrots_wrapper import _get_dataloader
from torch.utils.data.dataset import ConcatDataset

from .samplers import DistributedSampler

if platform.system() != 'Windows':
    # https://github.com/pytorch/pytorch/issues/973
    import resource
    rlimit = resource.getrlimit(resource.RLIMIT_NOFILE)
    base_soft_limit = rlimit[0]
    hard_limit = rlimit[1]
    soft_limit = min(max(4096, base_soft_limit), hard_limit)
    # resource.setrlimit(resource.RLIMIT_NOFILE, (soft_limit, hard_limit))

DATASETS = Registry('dataset')
PIPELINES = Registry('pipeline')


def _concat_dataset(cfg, default_args=None):
    types = cfg['type']
    ann_files = cfg['ann_file']
    img_prefixes = cfg.get('img_prefix', None)
    dataset_infos = cfg.get('dataset_info', None)

    num_joints = cfg['data_cfg'].get('num_joints', None)
    dataset_channel = cfg['data_cfg'].get('dataset_channel', None)

    datasets = []
    num_dset = len(ann_files)
    for i in range(num_dset):
        cfg_copy = copy.deepcopy(cfg)
        cfg_copy['ann_file'] = ann_files[i]

        if isinstance(types, (list, tuple)):
            cfg_copy['type'] = types[i]
        if isinstance(img_prefixes, (list, tuple)):
            cfg_copy['img_prefix'] = img_prefixes[i]
        if isinstance(dataset_infos, (list, tuple)):
            cfg_copy['dataset_info'] = dataset_infos[i]

        if isinstance(num_joints, (list, tuple)):
            cfg_copy['data_cfg']['num_joints'] = num_joints[i]

        if is_seq_of(dataset_channel, list):
            cfg_copy['data_cfg']['dataset_channel'] = dataset_channel[i]

        datasets.append(build_dataset(cfg_copy, default_args))

    return ConcatDataset(datasets)


def build_dataset(cfg, default_args=None):
    """Build a dataset from config dict.

    Args:
        cfg (dict): Config dict. It should at least contain the key "type".
        default_args (dict, optional): Default initialization arguments.
            Default: None.

    Returns:
        Dataset: The constructed dataset.
    """
    from .dataset_wrappers import RepeatDataset

    if isinstance(cfg, (list, tuple)):
        dataset = ConcatDataset([build_dataset(c, default_args) for c in cfg])
    elif cfg['type'] == 'ConcatDataset':
        dataset = ConcatDataset(
            [build_dataset(c, default_args) for c in cfg['datasets']])
    elif cfg['type'] == 'RepeatDataset':
        dataset = RepeatDataset(
            build_dataset(cfg['dataset'], default_args), cfg['times'])
    elif isinstance(cfg.get('ann_file'), (list, tuple)):
        dataset = _concat_dataset(cfg, default_args)
    else:
        dataset = build_from_cfg(cfg, DATASETS, default_args)
    return dataset


def build_dataloader(dataset,
                     samples_per_gpu,
                     workers_per_gpu,
                     num_gpus=1,
                     dist=True,
                     shuffle=True,
                     seed=None,
                     drop_last=True,
                     pin_memory=True,
                     **kwargs):
    """Build PyTorch DataLoader.

    In distributed training, each GPU/process has a dataloader.
    In non-distributed training, there is only one dataloader for all GPUs.

    Args:
        dataset (Dataset): A PyTorch dataset.
        samples_per_gpu (int): Number of training samples on each GPU, i.e.,
            batch size of each GPU.
        workers_per_gpu (int): How many subprocesses to use for data loading
            for each GPU.
        num_gpus (int): Number of GPUs. Only used in non-distributed training.
        dist (bool): Distributed training/test or not. Default: True.
        shuffle (bool): Whether to shuffle the data at every epoch.
            Default: True.
        drop_last (bool): Whether to drop the last incomplete batch in epoch.
            Default: True
        pin_memory (bool): Whether to use pin_memory in DataLoader.
            Default: True
        kwargs: any keyword argument to be used to initialize DataLoader

    Returns:
        DataLoader: A PyTorch dataloader.
    """
    rank, world_size = get_dist_info()
    if dist:
        sampler = DistributedSampler(
            dataset, world_size, rank, shuffle=shuffle, seed=seed)
        shuffle = False
        batch_size = samples_per_gpu
        num_workers = workers_per_gpu
    else:
        sampler = None
        batch_size = num_gpus * samples_per_gpu
        num_workers = num_gpus * workers_per_gpu

    init_fn = partial(
        worker_init_fn, num_workers=num_workers, rank=rank,
        seed=seed) if seed is not None else None

    _, DataLoader = _get_dataloader()
    data_loader = DataLoader(
        dataset,
        batch_size=batch_size,
        sampler=sampler,
        num_workers=num_workers,
        collate_fn=partial(collate, samples_per_gpu=samples_per_gpu),
        pin_memory=pin_memory,
        shuffle=shuffle,
        worker_init_fn=init_fn,
        drop_last=drop_last,
        **kwargs)

    return data_loader


def worker_init_fn(worker_id, num_workers, rank, seed):
    """Init the random seed for various workers."""
    # The seed of each worker equals to
    # num_worker * rank + worker_id + user_seed
    worker_seed = num_workers * rank + worker_id + seed
    np.random.seed(worker_seed)
    random.seed(worker_seed)