model = dict(
type='FastRCNN',
backbone=dict(
type='ResNet3dSlowFast',
pretrained=None,
resample_rate=8,
speed_ratio=8,
channel_ratio=8,
slow_pathway=dict(
type='resnet3d',
depth=50,
pretrained=None,
lateral=True,
conv1_kernel=(1, 7, 7),
dilations=(1, 1, 1, 1),
conv1_stride_t=1,
pool1_stride_t=1,
inflate=(0, 0, 1, 1),
spatial_strides=(1, 2, 2, 1)),
fast_pathway=dict(
type='resnet3d',
depth=50,
pretrained=None,
lateral=False,
base_channels=8,
conv1_kernel=(5, 7, 7),
conv1_stride_t=1,
pool1_stride_t=1,
spatial_strides=(1, 2, 2, 1))),
roi_head=dict(
type='AVARoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor3D',
roi_layer_type='RoIAlign',
output_size=8,
with_temporal_pool=True),
bbox_head=dict(
type='BBoxHeadAVA',
in_channels=2304,
num_classes=81,
multilabel=True,
dropout_ratio=0.5)),
train_cfg=dict(
rcnn=dict(
assigner=dict(
type='MaxIoUAssignerAVA',
pos_iou_thr=0.9,
neg_iou_thr=0.9,
min_pos_iou=0.9),
sampler=dict(
type='RandomSampler',
num=32,
pos_fraction=1,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=1.0,
debug=False)),
test_cfg=dict(rcnn=dict(action_thr=0.002)))
dataset_type = 'AVADataset'
data_root = '/home/MPCLST/Dataset/rawframes'
anno_root = '/home/MPCLST/Dataset/annotations'
ann_file_train = '/home/MPCLST/Dataset/annotations/train.csv'
ann_file_val = '/home/MPCLST/Dataset/annotations/val.csv'
exclude_file_train = '/home/MPCLST/Dataset/annotations/train_excluded_timestamps.csv'
exclude_file_val = '/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv'
label_file = '/home/MPCLST/Dataset/annotations/action_list.pbtxt'
proposal_file_train = '/home/MPCLST/Dataset/annotations/dense_proposals_train.pkl'
proposal_file_val = '/home/MPCLST/Dataset/annotations/dense_proposals_val.pkl'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
dict(type='RawFrameDecode'),
dict(type='RandomRescale', scale_range=(256, 320)),
dict(type='RandomCrop', size=256),
dict(type='Flip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_bgr=False),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='Rename', mapping=dict(imgs='img')),
dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
dict(
type='ToDataContainer',
fields=[
dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
]),
dict(
type='Collect',
keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
meta_keys=['scores', 'entity_ids'])
]
val_pipeline = [
dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_bgr=False),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='Rename', mapping=dict(imgs='img')),
dict(type='ToTensor', keys=['img', 'proposals']),
dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
dict(
type='Collect',
keys=['img', 'proposals'],
meta_keys=['scores', 'img_shape'],
nested=True)
]
data = dict(
videos_per_gpu=5,
workers_per_gpu=2,
val_dataloader=dict(videos_per_gpu=1),
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type='AVADataset',
ann_file='/home/MPCLST/Dataset/annotations/train.csv',
exclude_file=
'/home/MPCLST/Dataset/annotations/train_excluded_timestamps.csv',
pipeline=[
dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
dict(type='RawFrameDecode'),
dict(type='RandomRescale', scale_range=(256, 320)),
dict(type='RandomCrop', size=256),
dict(type='Flip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_bgr=False),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='Rename', mapping=dict(imgs='img')),
dict(
type='ToTensor',
keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
dict(
type='ToDataContainer',
fields=[
dict(
key=['proposals', 'gt_bboxes', 'gt_labels'],
stack=False)
]),
dict(
type='Collect',
keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
meta_keys=['scores', 'entity_ids'])
],
label_file='/home/MPCLST/Dataset/annotations/action_list.pbtxt',
proposal_file=
'/home/MPCLST/Dataset/annotations/dense_proposals_train.pkl',
person_det_score_thr=0.9,
data_prefix='/home/MPCLST/Dataset/rawframes',
start_index=1),
val=dict(
type='AVADataset',
ann_file='/home/MPCLST/Dataset/annotations/val.csv',
exclude_file=
'/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv',
pipeline=[
dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_bgr=False),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='Rename', mapping=dict(imgs='img')),
dict(type='ToTensor', keys=['img', 'proposals']),
dict(
type='ToDataContainer',
fields=[dict(key='proposals', stack=False)]),
dict(
type='Collect',
keys=['img', 'proposals'],
meta_keys=['scores', 'img_shape'],
nested=True)
],
label_file='/home/MPCLST/Dataset/annotations/action_list.pbtxt',
proposal_file=
'/home/MPCLST/Dataset/annotations/dense_proposals_val.pkl',
person_det_score_thr=0.9,
data_prefix='/home/MPCLST/Dataset/rawframes',
start_index=1),
test=dict(
type='AVADataset',
ann_file='/home/MPCLST/Dataset/annotations/val.csv',
exclude_file=
'/home/MPCLST/Dataset/annotations/val_excluded_timestamps.csv',
pipeline=[
dict(type='SampleAVAFrames', clip_len=32, frame_interval=2),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_bgr=False),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='Rename', mapping=dict(imgs='img')),
dict(type='ToTensor', keys=['img', 'proposals']),
dict(
type='ToDataContainer',
fields=[dict(key='proposals', stack=False)]),
没有合适的资源?快使用搜索试试~ 我知道了~
22-8-4 mmaction2 slowfast训练日志
共3个文件
json:1个
py:1个
pkl:1个
需积分: 0 14 下载量 198 浏览量
2022-08-05
01:50:08
上传
评论
收藏 358KB ZIP 举报
温馨提示
22-8-4 mmaction2 slowfast训练日志 包含配置文件:my_slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py 训练结束后使用最好的checkpoint的参数进行测试,将测试结果存储在:part_0.pkl 训练过程的记录:20220804_185539.log.json
资源详情
资源评论
资源推荐
收起资源包目录
22-8-4 mmaction2 slowfast训练日志.zip (3个子文件)
22-8-4 mmaction2 slowfast训练日志
my_slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py 9KB
part_0.pkl 1.27MB
20220804_185539.log.json 117KB
共 3 条
- 1
计算机视觉-杨帆
- 粉丝: 1461
- 资源: 43
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0