Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Cannot reproduce the fcaf-based results . #12

Open
LIZECHUAN opened this issue Nov 6, 2023 · 0 comments
Open

Cannot reproduce the fcaf-based results . #12

LIZECHUAN opened this issue Nov 6, 2023 · 0 comments

Comments

@LIZECHUAN
Copy link

Hi, you guys have done an outstanding job! Your work inspires me a lot. However, I'm having some problems reproducing paper. When I trained the fcaf-based model, I get the following results, which is different from the expected outcome of [email protected] and [email protected] as reported in the paper.Even lower than the FCAF3D. I have listed my confing file below, could you please tell me if i'm missing something ?
+-------------+---------+---------+---------+---------+
| classes | AP_0.25 | AR_0.25 | AP_0.50 | AR_0.50 |
+-------------+---------+---------+---------+---------+
| bed | 0.8811 | 0.9767 | 0.6398 | 0.7359 |
| table | 0.4980 | 0.9059 | 0.2817 | 0.5988 |
| sofa | 0.7217 | 0.9490 | 0.5002 | 0.7161 |
| chair | 0.8150 | 0.9016 | 0.6704 | 0.7695 |
| toilet | 0.9287 | 0.9862 | 0.7106 | 0.8000 |
| desk | 0.3208 | 0.8379 | 0.0992 | 0.4299 |
| dresser | 0.4735 | 0.8991 | 0.2514 | 0.5963 |
| night_stand | 0.7013 | 0.9490 | 0.5532 | 0.7569 |
| bookshelf | 0.2982 | 0.7340 | 0.0587 | 0.2305 |
| bathtub | 0.8098 | 0.9592 | 0.4944 | 0.6939 |
+-------------+---------+---------+---------+---------+
| Overall | 0.6448 | 0.9099 | 0.4259 | 0.6328 |
+-------------+---------+---------+---------+---------+

n_points = 100000
dataset_type = 'SUNRGBDDataset'
data_root = '/home/hy/ssd1/lzc/DeMF/sunrgbd/'
class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub')
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations3D'),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.0),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='IndoorPointSample', num_points=100000),
dict(type='RandomFlip3D', sync_2d=False, flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.523599, 0.523599],
scale_ratio_range=[0.85, 1.15],
translation_std=[0.1, 0.1, 0.1],
shift_height=False),
dict(
type='DefaultFormatBundle3D',
class_names=('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
'dresser', 'night_stand', 'bookshelf', 'bathtub')),
dict(
type='Collect3D',
keys=['points', 'gt_bboxes_3d', 'gt_labels_3d', 'img'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.0),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(type='IndoorPointSample', num_points=100000),
dict(
type='DefaultFormatBundle3D',
class_names=('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
'dresser', 'night_stand', 'bookshelf', 'bathtub'),
with_label=False),
dict(type='Collect3D', keys=['points', 'img'])
])
]
data = dict(
samples_per_gpu=8,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type='SUNRGBDDataset',
modality=dict(use_camera=True, use_lidar=True),
data_root='/home/hy/ssd1/lzc/DeMF/sunrgbd/',
ann_file='/home/hy/ssd1/lzc/DeMF/sunrgbd/sunrgbd_infos_train.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations3D'),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.0),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='IndoorPointSample', num_points=100000),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.523599, 0.523599],
scale_ratio_range=[0.85, 1.15],
translation_std=[0.1, 0.1, 0.1],
shift_height=False),
dict(
type='DefaultFormatBundle3D',
class_names=('bed', 'table', 'sofa', 'chair', 'toilet',
'desk', 'dresser', 'night_stand', 'bookshelf',
'bathtub')),
dict(
type='Collect3D',
keys=['points', 'gt_bboxes_3d', 'gt_labels_3d', 'img'])
],
filter_empty_gt=True,
classes=('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
'dresser', 'night_stand', 'bookshelf', 'bathtub'),
box_type_3d='Depth')),
val=dict(
type='SUNRGBDDataset',
modality=dict(use_camera=True, use_lidar=True),
data_root='/home/hy/ssd1/lzc/DeMF/sunrgbd/',
ann_file='/home/hy/ssd1/lzc/DeMF/sunrgbd/sunrgbd_infos_val.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.0),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(type='IndoorPointSample', num_points=100000),
dict(
type='DefaultFormatBundle3D',
class_names=('bed', 'table', 'sofa', 'chair', 'toilet',
'desk', 'dresser', 'night_stand',
'bookshelf', 'bathtub'),
with_label=False),
dict(type='Collect3D', keys=['points', 'img'])
])
],
classes=('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub'),
test_mode=True,
box_type_3d='Depth'),
test=dict(
type='SUNRGBDDataset',
modality=dict(use_camera=True, use_lidar=True),
data_root='/home/hy/ssd1/lzc/DeMF/sunrgbd/',
ann_file='/home/hy/ssd1/lzc/DeMF/sunrgbd/sunrgbd_infos_val.pkl',
pipeline=[
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.0),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1.0, 1.0],
translation_std=[0, 0, 0]),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(type='IndoorPointSample', num_points=100000),
dict(
type='DefaultFormatBundle3D',
class_names=('bed', 'table', 'sofa', 'chair', 'toilet',
'desk', 'dresser', 'night_stand',
'bookshelf', 'bathtub'),
with_label=False),
dict(type='Collect3D', keys=['points', 'img'])
])
],
classes=('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub'),
test_mode=True,
box_type_3d='Depth'))
voxel_size = 0.01
model = dict(
type='TwoStageSparse3DDetector',
voxel_size=0.01,
backbone=dict(type='MEResNet3D', in_channels=3, depth=34),
neck_with_head=dict(
type='Fcaf3DNeckWithHead_my',
in_channels=(64, 128, 256, 512),
out_channels=128,
pts_threshold=100000,
n_classes=10,
n_reg_outs=8,
voxel_size=0.01,
assigner=dict(type='Fcaf3DAssigner', limit=27, topk=18, n_scales=4),
loss_bbox=dict(type='IoU3DLoss', loss_weight=1.0)),
train_cfg=dict(),
test_cfg=dict(
nms_pre=1000, iou_thr=0.5, score_thr=0.01, ensemble_stages=[2]),
img_encoder=dict(
type='DeformableDetrEncoder',
encoder=dict(
type='DetrTransformerEncoder',
num_layers=6,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=dict(
type='MultiScaleDeformableAttention', embed_dims=256),
feedforward_channels=1024,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
positional_encoding=dict(
type='SinePositionalEncoding',
num_feats=128,
normalize=True,
offset=-0.5),
num_feature_levels=4,
embed_dims=256),
img_backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='pytorch'),
img_neck=dict(
type='ChannelMapper',
in_channels=[512, 1024, 2048],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=dict(type='GN', num_groups=32),
num_outs=4),
stage2_head=dict(
type='CAHeadIter',
decoder=dict(
type='TransformerDecoderLayerWithPos',
num_layers=1,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
dropout=0.1),
dict(type='MultiScaleDeformableAttention', embed_dims=256)
],
feedforward_channels=1024,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')),
posembed=dict(input_channel=9, num_pos_feats=256))),
freeze_img_branch=True)
find_unused_parameters = True
optimizer = dict(
type='AdamW',
lr=0.001,
weight_decay=0.0001,
paramwise_cfg=dict(
custom_keys=dict(decoder=dict(lr_mult=0.05, decay_mult=1.0))))
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
checkpoint_config = dict(interval=1, max_keep_ckpts=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = '1105/raw/base'
load_from = '/home/hy/ssd1/lzc/DeMF/deform_detr-epoch_10.pth'
resume_from = None
workflow = [('train', 1)]
lr = 0.001
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
evaluation = dict(interval=1)
gpu_ids = range(0, 4)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@LIZECHUAN