forked from huggingface/controlnet_aux
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
1e6bdc0
commit 98a88ca
Showing
7 changed files
with
1,037 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| # Openpose | ||
| # Original from CMU https://github.com/CMU-Perceptual-Computing-Lab/openpose | ||
| # 2nd Edited by https://github.com/Hzzone/pytorch-openpose | ||
| # 3rd Edited by ControlNet | ||
| # 4th Edited by ControlNet (added face and correct hands) | ||
|
|
||
| import os | ||
| os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" | ||
|
|
||
| import cv2 | ||
| import torch | ||
| import numpy as np | ||
| from PIL import Image | ||
|
|
||
| from . import util | ||
| from .wholebody import Wholebody | ||
|
|
||
|
|
||
| def draw_pose(pose, H, W): | ||
| bodies = pose['bodies'] | ||
| faces = pose['faces'] | ||
| hands = pose['hands'] | ||
| candidate = bodies['candidate'] | ||
| subset = bodies['subset'] | ||
|
|
||
| canvas = np.zeros(shape=(H, W, 3), dtype=np.uint8) | ||
| canvas = util.draw_bodypose(canvas, candidate, subset) | ||
| canvas = util.draw_handpose(canvas, hands) | ||
| canvas = util.draw_facepose(canvas, faces) | ||
|
|
||
| return canvas | ||
|
|
||
| class DWposeDetector: | ||
| def __init__(self, det_config, det_ckpt, pose_config, pose_ckpt, device): | ||
|
|
||
| self.pose_estimation = Wholebody(det_config, det_ckpt, pose_config, pose_ckpt, device) | ||
|
|
||
| def __call__(self, oriImg, output_type="pil", detect_resolution=512, image_resolution=512): | ||
|
|
||
| oriImg = oriImg.copy() | ||
| input_image = cv2.cvtColor(np.array(oriImg), cv2.COLOR_RGB2BGR) | ||
|
|
||
| input_image = util.HWC3(input_image) | ||
| input_image = util.resize_image(input_image, detect_resolution) | ||
| H, W, C = input_image.shape | ||
|
|
||
| with torch.no_grad(): | ||
| candidate, subset = self.pose_estimation(input_image) | ||
| nums, keys, locs = candidate.shape | ||
| candidate[..., 0] /= float(W) | ||
| candidate[..., 1] /= float(H) | ||
| body = candidate[:,:18].copy() | ||
| body = body.reshape(nums*18, locs) | ||
| score = subset[:,:18] | ||
|
|
||
| for i in range(len(score)): | ||
| for j in range(len(score[i])): | ||
| if score[i][j] > 0.3: | ||
| score[i][j] = int(18*i+j) | ||
| else: | ||
| score[i][j] = -1 | ||
|
|
||
| un_visible = subset<0.3 | ||
| candidate[un_visible] = -1 | ||
|
|
||
| foot = candidate[:,18:24] | ||
|
|
||
| faces = candidate[:,24:92] | ||
|
|
||
| hands = candidate[:,92:113] | ||
| hands = np.vstack([hands, candidate[:,113:]]) | ||
|
|
||
| bodies = dict(candidate=body, subset=score) | ||
| pose = dict(bodies=bodies, hands=hands, faces=faces) | ||
|
|
||
| detected_map = draw_pose(pose, H, W) | ||
| detected_map = util.HWC3(detected_map) | ||
|
|
||
| img = util.resize_image(input_image, image_resolution) | ||
| H, W, C = img.shape | ||
|
|
||
| detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_LINEAR) | ||
|
|
||
| if output_type == "pil": | ||
| detected_map = Image.fromarray(cv2.cvtColor(detected_map, cv2.COLOR_BGR2RGB)) | ||
|
|
||
| return detected_map |
257 changes: 257 additions & 0 deletions
257
src/controlnet_aux/dwpose/dwpose_config/dwpose-l_384x288.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,257 @@ | ||
| # runtime | ||
| max_epochs = 270 | ||
| stage2_num_epochs = 30 | ||
| base_lr = 4e-3 | ||
|
|
||
| train_cfg = dict(max_epochs=max_epochs, val_interval=10) | ||
| randomness = dict(seed=21) | ||
|
|
||
| # optimizer | ||
| optim_wrapper = dict( | ||
| type='OptimWrapper', | ||
| optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05), | ||
| paramwise_cfg=dict( | ||
| norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True)) | ||
|
|
||
| # learning rate | ||
| param_scheduler = [ | ||
| dict( | ||
| type='LinearLR', | ||
| start_factor=1.0e-5, | ||
| by_epoch=False, | ||
| begin=0, | ||
| end=1000), | ||
| dict( | ||
| # use cosine lr from 150 to 300 epoch | ||
| type='CosineAnnealingLR', | ||
| eta_min=base_lr * 0.05, | ||
| begin=max_epochs // 2, | ||
| end=max_epochs, | ||
| T_max=max_epochs // 2, | ||
| by_epoch=True, | ||
| convert_to_iter_based=True), | ||
| ] | ||
|
|
||
| # automatically scaling LR based on the actual training batch size | ||
| auto_scale_lr = dict(base_batch_size=512) | ||
|
|
||
| # codec settings | ||
| codec = dict( | ||
| type='SimCCLabel', | ||
| input_size=(288, 384), | ||
| sigma=(6., 6.93), | ||
| simcc_split_ratio=2.0, | ||
| normalize=False, | ||
| use_dark=False) | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='TopdownPoseEstimator', | ||
| data_preprocessor=dict( | ||
| type='PoseDataPreprocessor', | ||
| mean=[123.675, 116.28, 103.53], | ||
| std=[58.395, 57.12, 57.375], | ||
| bgr_to_rgb=True), | ||
| backbone=dict( | ||
| _scope_='mmdet', | ||
| type='CSPNeXt', | ||
| arch='P5', | ||
| expand_ratio=0.5, | ||
| deepen_factor=1., | ||
| widen_factor=1., | ||
| out_indices=(4, ), | ||
| channel_attention=True, | ||
| norm_cfg=dict(type='SyncBN'), | ||
| act_cfg=dict(type='SiLU'), | ||
| init_cfg=dict( | ||
| type='Pretrained', | ||
| prefix='backbone.', | ||
| checkpoint='https://download.openmmlab.com/mmpose/v1/projects/' | ||
| 'rtmpose/cspnext-l_udp-aic-coco_210e-256x192-273b7631_20230130.pth' # noqa | ||
| )), | ||
| head=dict( | ||
| type='RTMCCHead', | ||
| in_channels=1024, | ||
| out_channels=133, | ||
| input_size=codec['input_size'], | ||
| in_featuremap_size=(9, 12), | ||
| simcc_split_ratio=codec['simcc_split_ratio'], | ||
| final_layer_kernel_size=7, | ||
| gau_cfg=dict( | ||
| hidden_dims=256, | ||
| s=128, | ||
| expansion_factor=2, | ||
| dropout_rate=0., | ||
| drop_path=0., | ||
| act_fn='SiLU', | ||
| use_rel_bias=False, | ||
| pos_enc=False), | ||
| loss=dict( | ||
| type='KLDiscretLoss', | ||
| use_target_weight=True, | ||
| beta=10., | ||
| label_softmax=True), | ||
| decoder=codec), | ||
| test_cfg=dict(flip_test=True, )) | ||
|
|
||
| # base dataset settings | ||
| dataset_type = 'CocoWholeBodyDataset' | ||
| data_mode = 'topdown' | ||
| data_root = '/data/' | ||
|
|
||
| backend_args = dict(backend='local') | ||
| # backend_args = dict( | ||
| # backend='petrel', | ||
| # path_mapping=dict({ | ||
| # f'{data_root}': 's3://openmmlab/datasets/detection/coco/', | ||
| # f'{data_root}': 's3://openmmlab/datasets/detection/coco/' | ||
| # })) | ||
|
|
||
| # pipelines | ||
| train_pipeline = [ | ||
| dict(type='LoadImage', backend_args=backend_args), | ||
| dict(type='GetBBoxCenterScale'), | ||
| dict(type='RandomFlip', direction='horizontal'), | ||
| dict(type='RandomHalfBody'), | ||
| dict( | ||
| type='RandomBBoxTransform', scale_factor=[0.6, 1.4], rotate_factor=80), | ||
| dict(type='TopdownAffine', input_size=codec['input_size']), | ||
| dict(type='mmdet.YOLOXHSVRandomAug'), | ||
| dict( | ||
| type='Albumentation', | ||
| transforms=[ | ||
| dict(type='Blur', p=0.1), | ||
| dict(type='MedianBlur', p=0.1), | ||
| dict( | ||
| type='CoarseDropout', | ||
| max_holes=1, | ||
| max_height=0.4, | ||
| max_width=0.4, | ||
| min_holes=1, | ||
| min_height=0.2, | ||
| min_width=0.2, | ||
| p=1.0), | ||
| ]), | ||
| dict(type='GenerateTarget', encoder=codec), | ||
| dict(type='PackPoseInputs') | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='LoadImage', backend_args=backend_args), | ||
| dict(type='GetBBoxCenterScale'), | ||
| dict(type='TopdownAffine', input_size=codec['input_size']), | ||
| dict(type='PackPoseInputs') | ||
| ] | ||
|
|
||
| train_pipeline_stage2 = [ | ||
| dict(type='LoadImage', backend_args=backend_args), | ||
| dict(type='GetBBoxCenterScale'), | ||
| dict(type='RandomFlip', direction='horizontal'), | ||
| dict(type='RandomHalfBody'), | ||
| dict( | ||
| type='RandomBBoxTransform', | ||
| shift_factor=0., | ||
| scale_factor=[0.75, 1.25], | ||
| rotate_factor=60), | ||
| dict(type='TopdownAffine', input_size=codec['input_size']), | ||
| dict(type='mmdet.YOLOXHSVRandomAug'), | ||
| dict( | ||
| type='Albumentation', | ||
| transforms=[ | ||
| dict(type='Blur', p=0.1), | ||
| dict(type='MedianBlur', p=0.1), | ||
| dict( | ||
| type='CoarseDropout', | ||
| max_holes=1, | ||
| max_height=0.4, | ||
| max_width=0.4, | ||
| min_holes=1, | ||
| min_height=0.2, | ||
| min_width=0.2, | ||
| p=0.5), | ||
| ]), | ||
| dict(type='GenerateTarget', encoder=codec), | ||
| dict(type='PackPoseInputs') | ||
| ] | ||
|
|
||
| datasets = [] | ||
| dataset_coco=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| data_mode=data_mode, | ||
| ann_file='coco/annotations/coco_wholebody_train_v1.0.json', | ||
| data_prefix=dict(img='coco/train2017/'), | ||
| pipeline=[], | ||
| ) | ||
| datasets.append(dataset_coco) | ||
|
|
||
| scene = ['Magic_show', 'Entertainment', 'ConductMusic', 'Online_class', | ||
| 'TalkShow', 'Speech', 'Fitness', 'Interview', 'Olympic', 'TVShow', | ||
| 'Singing', 'SignLanguage', 'Movie', 'LiveVlog', 'VideoConference'] | ||
|
|
||
| for i in range(len(scene)): | ||
| datasets.append( | ||
| dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| data_mode=data_mode, | ||
| ann_file='UBody/annotations/'+scene[i]+'/keypoint_annotation.json', | ||
| data_prefix=dict(img='UBody/images/'+scene[i]+'/'), | ||
| pipeline=[], | ||
| ) | ||
| ) | ||
|
|
||
| # data loaders | ||
| train_dataloader = dict( | ||
| batch_size=32, | ||
| num_workers=10, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=dict( | ||
| type='CombinedDataset', | ||
| metainfo=dict(from_file='configs/_base_/datasets/coco_wholebody.py'), | ||
| datasets=datasets, | ||
| pipeline=train_pipeline, | ||
| test_mode=False, | ||
| )) | ||
| val_dataloader = dict( | ||
| batch_size=32, | ||
| num_workers=10, | ||
| persistent_workers=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| data_mode=data_mode, | ||
| ann_file='coco/annotations/coco_wholebody_val_v1.0.json', | ||
| bbox_file=f'{data_root}coco/person_detection_results/' | ||
| 'COCO_val2017_detections_AP_H_56_person.json', | ||
| data_prefix=dict(img='coco/val2017/'), | ||
| test_mode=True, | ||
| pipeline=val_pipeline, | ||
| )) | ||
| test_dataloader = val_dataloader | ||
|
|
||
| # hooks | ||
| default_hooks = dict( | ||
| checkpoint=dict( | ||
| save_best='coco-wholebody/AP', rule='greater', max_keep_ckpts=1)) | ||
|
|
||
| custom_hooks = [ | ||
| dict( | ||
| type='EMAHook', | ||
| ema_type='ExpMomentumEMA', | ||
| momentum=0.0002, | ||
| update_buffers=True, | ||
| priority=49), | ||
| dict( | ||
| type='mmdet.PipelineSwitchHook', | ||
| switch_epoch=max_epochs - stage2_num_epochs, | ||
| switch_pipeline=train_pipeline_stage2) | ||
| ] | ||
|
|
||
| # evaluators | ||
| val_evaluator = dict( | ||
| type='CocoWholeBodyMetric', | ||
| ann_file=data_root + 'coco/annotations/coco_wholebody_val_v1.0.json') | ||
| test_evaluator = val_evaluator |
Oops, something went wrong.