sys.platform: linux
Python: 3.6.9 (default, Apr 18 2020, 01:56:04) [GCC 8.4.0]
CUDA available: True
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 10.1, V10.1.243
GPU 0: Tesla K80
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.4.0+cu100
PyTorch compiling details: PyTorch built with:
- GCC 7.3
- Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CUDA Runtime 10.0
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
- CuDNN 7.6.3
- Magma 2.5.1
- Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,
TorchVision: 0.5.0+cu100
OpenCV: 4.1.2
MMCV: 0.5.9
MMDetection: 1.1.0+bccc528
MMDetection Compiler: GCC 7.5
MMDetection CUDA Compiler: 10.1
------------------------------------------------------------
2020-06-08 08:59:36,404 - mmdet - INFO - Distributed training: False
2020-06-08 08:59:36,404 - mmdet - INFO - Config:
/content/drive/My Drive/DetectoRS/configs/DetectoRS/DetectoRS_mstrain_400_1200_x101_32x4d_40e.py
conv_cfg = dict(type='ConvAWS')
# model settings
model = dict(
type='RecursiveFeaturePyramid',
rfp_steps=2,
rfp_sharing=False,
stage_with_rfp=(False, True, True, True),
num_stages=3,
pretrained='open-mmlab://resnext101_32x4d',
interleaved=True,
mask_info_flow=True,
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
conv_cfg=conv_cfg,
sac=dict(type='SAC', use_deform=True),
stage_with_sac=(False, True, True, True),
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=2,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=2,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=[
dict(
type='HTCMaskHead',
with_conv_res=False,
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=1,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
dict(
type='HTCMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=1,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
dict(
type='HTCMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=1,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))
],
semantic_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[8]),
semantic_head=dict(
type='FusedSemanticHead',
num_ins=5,
fusion_level=1,
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=1,
ignore_label=255,
loss_weight=0.2))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.001,
nms=dict(type='soft_nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = '/content/drive/My Drive/collab/data/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
dict(
type='Resize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
seg_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric=['bbox', 'segm'])
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[36, 39])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 40
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/DetectoRS_mstrain_400_1200_x101_32x4d_40e.py'
load_from = None
resume_from = None
workflow = [('train', 1)]
2020-06-08 08:59:39,001 - mmdet - INFO - load model from: open-mmlab://resnext101_32x4d
2020-06-08 08:59:39,627 - mmdet - WARNING - The model and loaded state dict do not match exactly
missing keys in source state_dict: conv1.weight_gamma, conv1.weight_beta, layer1.0.conv1.weight_gamma, layer1.0.conv1.weight_beta, layer1.0.conv2.weight_gamma, layer1.0.conv2.weight_beta, layer1.0.conv3.weight_gamma, layer1.0.conv3.weight_beta, layer1.0.downsample.0.weight_gamma, layer1.0.downsample.0.weight_beta, layer1.1.conv1.weight_gamma, layer1.1.conv1.weight_beta, layer1.1.conv2.weight_gamma, layer1.1.conv2.weight_beta, layer1.1.conv3.weight_gamma, layer1.1.conv3.weight_beta, layer1.2.conv1.weight_gamma, layer1.2.conv1.weight_beta, layer1.2.conv2.weight_gamma, layer1.2.conv2.weight_beta, layer1.2.conv3.weight_gamma, layer1.2.conv3.weight_beta, layer2.0.conv1.weight_gamma, layer2.0.conv1.weight_beta, layer2.0.conv2.weight_diff, layer2.0.conv2.weight_gamma, layer2.0.conv2.weight_beta, layer2.0.conv2.switch.weight, layer2.0.conv2.switch.bias, layer2.0.conv2.pre_context.weight, layer2.0.conv2.pre_context.bias, layer2.0.conv2.post_context.weight, layer2.0.conv2.post_context.bias, layer2.0.conv2.offset_s.weight, layer2.0.conv2.offset_s.bias, layer2.0.conv2.offset_l.weight, layer2.0.conv2.offset_l.bias, layer2.0.conv3.weight_gamma, layer2.0.conv3.weight_beta, layer2.0.downsample.0.weight_gamma, layer2.0.downsample.0.weight_beta, layer2.1.conv1.weight_gamma, layer2.1.conv1.weight_beta, layer2.1.conv2.weight_diff, layer2.1.conv2.weight_gamma, layer2.1.conv2.weight_beta, layer2.1.conv2.switch.weight, layer2.1.conv2.switch.bias, layer2.1.conv2.pre_context.weight, layer2.1.conv2.pre_context.bias, layer2.1.conv2.post_context.weight, layer2.1.conv2.post_context.bias, layer2.1.conv2.offset_s.weight, layer2.1.conv2.offset_s.bias, layer2.1.conv2.offset_l.weight, layer2.1.conv2.offset_l.bias, layer2.1.conv3.weight_gamma, layer2.1.conv3.weight_beta, layer2.2.conv1.weight_gamma, layer2.2.conv1.weight_beta, layer2.2.conv2.weight_diff, layer2.2.conv2.weight_gamma, layer2.2.conv2.weight_beta, layer2.2.conv2.switch.weight, layer2.2.conv2.switch.bias, layer2.2.conv2.pre_context.weight, layer2.2.conv2.pre_context.bias, layer2.2.conv2.post_context.weight, layer2.2.conv2.post_context.bias, layer2.2.conv2.offset_s.weight, layer2.2.conv2.offset_s.bias, layer2.2.conv2.offset_l.weight, layer2.2.conv2.offset_l.bias, layer2.2.conv3.weight_gamma, layer2.2.conv3.weight_beta, layer2.3.conv1.weight_gamma, layer2.3.conv1.weight_beta, layer2.3.conv2.weight_diff, layer2.3.conv2.weight_gamma, layer2.3.conv2.weight_beta, layer2.3.conv2.switch.weight, layer2.3.conv2.switch.bias, layer2.3.conv2.pre_context.weight, layer2.3.conv2.pre_context.bias, layer2.3.conv2.post_context.weight, layer2.3.conv2.post_context.bias, layer2.3.conv2.offset_s.weight, layer2.3.conv2.offset_s.bias, layer2.3.conv2.offset_l.weight, layer2.3.conv2.offset_l.bias, layer2.3.conv3.weight_gamma, layer2.3.conv3.weight_beta, layer3.0.conv1.weight_gamma, layer3.0.conv1.weight_beta, layer3.0.conv2.weight_diff, layer3.0.conv2.weight_gamma, layer3.0.conv2.weight_beta, layer3.0.conv2.switch.weight, layer3.0.conv2.switch.bias, layer3.0.conv2.pre_context.weight, layer3.0.conv2.pre_context.bias, layer3.0.conv2.post_context.weight, layer3.0.conv2.post_context.bias, layer3.0.conv2.offset_s.weight, layer3.0.conv2.offset_s.bias, layer3.0.conv2.offset_l.weight, layer3.0.conv2.offset_l.bias, layer3.0.conv3.weight_gamma, layer3.0.conv3.weight_beta, layer3.0.downsample.0.weight_gamma, layer3.0.downsample.0.weight_beta, layer3.1.conv1.weight_gamma, layer3.1.conv1.weight_beta, layer3.1.conv2.weight_diff, layer3.1.conv2.weight_gamma, layer3.1.conv2.weight_beta, layer3.1.conv2.switch.weight, layer3.1.conv2.switch.bias, layer3.1.conv2.pre_context.weight, layer3.1.conv2.pre_context.bias, layer3.1.conv2.post_context.weight, layer3.1.conv2.post_context.bias, layer3.1.conv2.offset_s.weight, layer3.1.conv2.offset_s.bias, layer3.1.conv2.offset_l.weight, layer3.1.conv2.offset_l.bias, layer3.1.conv3.weight_gamma, layer3.1.conv3.weight_beta, layer3.2.conv1.weight_gamma, layer3.2.conv1.weight_beta, layer3.2.conv2.weight_diff, layer3.2.conv2.weight_gamma, layer3.2.conv2.weight_beta, layer3.2.conv2.switch.weight, layer3.2.conv2.switch.bias, layer3.2.conv2.pre_context.weight, layer3.2.conv2.pre_context.bias, layer3.2.conv2.post_context.weight, layer3.2.conv2.post_context.bias, layer3.2.conv2.offset_s.weight, layer3.2.conv2.offset_s.bias, layer3.2.conv2.offset_l.weight, layer3.2.conv2.offset_l.bias, layer3.2.conv3.weight_gamma, layer3.2.conv3.weight_beta, layer3.3.conv1.weight_gamma, layer3.3.conv1.weight_beta, layer3.3.conv2.weight_diff, layer3.3.conv2.weight_gamma, layer3.3.conv2.weight_beta, layer3.3.conv2.switch.weight, layer3.3.conv2.switch.bias, layer3.3.conv2.pre_context.weight, layer3.3.conv2.pre_context.bias, layer3.3.conv2.post_context.weight, layer3.3.conv2.post_context.bias, layer3.3.conv2.offset_s.weight, layer3.3.conv2.offset_s.bias, layer3.3.conv2.offset_l.weight, layer3.3.conv2.offset_l.bias, layer3.3.conv3.weight_gamma, layer3.3.conv3.weight_beta, layer3.4.conv1.weight_gamma, layer3.4.conv1.weight_beta, layer3.4.conv2.weight_diff, layer3.4.conv2.weight_gamma, layer3.4.conv2.weight_beta, layer3.4.conv2.switch.weight, layer3.4.conv2.switch.bias, layer3.4.conv2.pre_context.weight, layer3.4.conv2.pre_context.bias, layer3.4.conv2.post_context.weight, layer3.4.conv2.post_context.bias, layer3.4.conv2.offset_s.weight, layer3.4.conv2.offset_s.bias, layer3.4.conv2.offset_l.weight, layer3.4.conv2.offset_l.bias, layer3.4.conv3.weight_gamma, layer3.4.conv3.weight_beta, layer3.5.conv1.weight_gamma, layer3.5.conv1.weight_beta, layer3.5.conv2.weight_diff, layer3.5.conv2.weight_gamma, layer3.5.conv2.weight_beta, layer3.5.conv2.switch.weight, layer3.5.conv2.switch.bias, layer3.5.conv2.pre_context.weight, layer3.5.conv2.pre_context.bias, layer3.5.conv2.post_context.weight, layer3.5.conv2.post_context.bias, layer3.5.conv2.offset_s.weight, layer3.5.conv2.offset_s.bias, layer3.5.conv2.offset_l.weight, layer3.5.conv2.offset_l.bias, layer3.5.conv3.weight_gamma, layer3.5.conv3.weight_beta, layer3.6.conv1.weight_gamma, layer3.6.conv1.weight_beta, layer3.6.conv2.weight_diff, layer3.6.conv2.weight_gamma, layer3.6.conv2.weight_beta, layer3.6.conv2.switch.weight, layer3.6.conv2.switch.bias, layer3.6.conv2.pre_context.weight, layer3.6.conv2.pre_context.bias, layer3.6.conv2.post_context.weight, layer3.6.conv2.post_context.bias, layer3.6.conv2.offset_s.weight, layer3.6.conv2.offset_s.bias, layer3.6.conv2.offset_l.weight, layer3.6.conv2.offset_l.bias, layer3.6.conv3.weight_gamma, layer3.6.conv3.weight_beta, layer3.7.conv1.weight_gamma, layer3.7.conv1.weight_beta, layer3.7.conv2.weight_diff, layer3.7.conv2.weight_gamma, layer3.7.conv2.weight_beta, layer3.7.conv2.switch.weight, layer3.7.conv2.switch.bias, layer3.7.conv2.pre_context.weight, layer3.7.conv2.pre_context.bias, layer3.7.conv2.post_context.weight, layer3.7.conv2.post_context.bias, layer3.7.conv2.offset_s.weight, layer3.7.conv2.offset_s.bias, layer3.7.conv2.offset_l.weight, layer3.7.conv2.offset_l.bias, layer3.7.conv3.weight_gamma, layer3.7.conv3.weight_beta, layer3.8.conv1.weight_gamma, layer3.8.conv1.weight_beta, layer3.8.conv2.weight_diff, layer3.8.conv2.weight_gamma, layer3.8.conv2.weight_beta, layer3.8.conv2.switch.weight, layer3.8.conv2.switch.bias, layer3.8.conv2.pre_context.weight, layer3.8.conv2.pre_context.bias, layer3.8.conv2.post_context.weight, layer3.8.conv2.post_context.bias, layer3.8.conv2.offset_s.weight, layer3.8.conv2.offset_s.bias, layer3.8.conv2.offset_l.weight, layer3.8.conv2.offset_l.bias, layer3.8.conv3.weight_gamma, layer3.8.conv3.weight_beta, layer3.9.conv1.weight_gamma, layer3.9.conv1.weight_beta, layer3.9.conv2.weight_diff, layer3.9.conv2.weight_gamma, layer3.9.conv2.weight_beta, layer3.9.conv2.switch.weight, layer3.9.conv2.switch.bias, layer3.9.conv2.pre_context.weight, layer3.9.conv2.pre_context.bias, layer3.9.conv2.post_context.weight, layer3.9.conv2.post_context.bias, layer3.9.conv2.offset_s.weight, layer3.9.conv2.offset_s.bias, layer3.9.conv2.offset_l.weight, layer3.9.conv2.offset_l.bias, layer3.9.conv3.weight_gamma, layer3.9.conv3.weight_beta, layer3.10.conv1.weight_gamma, layer3.10.conv1.weight_beta, layer3.10.conv2.weight_diff, layer3.10.conv2.weight_gamma, layer3.10.conv2.weight_beta, layer3.10.conv2.switch.weight, layer3.10.conv2.switch.bias, layer3.10.conv2.pre_context.weight, layer3.10.conv2.pre_context.bias, layer3.10.conv2.post_context.weight, layer3.10.conv2.post_context.bias, layer3.10.conv2.offset_s.weight, layer3.10.conv2.offset_s.bias, layer3.10.conv2.offset_l.weight, layer3.10.conv2.offset_l.bias, layer3.10.conv3.weight_gamma, layer3.10.conv3.weight_beta, layer3.11.conv1.weight_gamma, layer3.11.conv1.weight_beta, layer3.11.conv2.weight_diff, layer3.11.conv2.weight_gamma, layer3.11.conv2.weight_beta, layer3.11.conv2.switch.weight, layer3.11.conv2.switch.bias, layer3.11.conv2.pre_context.weight, layer3.11.conv2.pre_context.bias, layer3.11.conv2.post_context.weight, layer3.11.conv2.post_context.bias, layer3.11.conv2.offset_s.weight, layer3.11.conv2.offset_s.bias, layer3.11.conv2.offset_l.weight, layer3.11.conv2.offset_l.bias, layer3.11.conv3.weight_gamma, layer3.11.conv3.weight_beta, layer3.12.conv1.weight_gamma, layer3.12.conv1.weight_beta, layer3.12.conv2.weight_diff, layer3.12.conv2.weight_gamma, layer3.12.conv2.weight_beta, layer3.12.conv2.switch.weight, layer3.12.conv2.switch.bias, layer3.12.conv2.pre_context.weight, layer3.12.conv2.pre_context.bias, layer3.12.conv2.post_context.weight, layer3.12.conv2.post_context.bias, layer3.12.conv2.offset_s.weight, layer3.12.conv2.offset_s.bias, layer3.12.conv2.offset_l.weight, layer3.12.conv2.offset_l.bias, layer3.12.conv3.weight_gamma, layer3.12.conv3.weight_beta, layer3.13.conv1.weight_gamma, layer3.13.conv1.weight_beta, layer3.13.conv2.weight_diff, layer3.13.conv2.weight_gamma, layer3.13.conv2.weight_beta, layer3.13.conv2.switch.weight, layer3.13.conv2.switch.bias, layer3.13.conv2.pre_context.weight, layer3.13.conv2.pre_context.bias, layer3.13.conv2.post_context.weight, layer3.13.conv2.post_context.bias, layer3.13.conv2.offset_s.weight, layer3.13.conv2.offset_s.bias, layer3.13.conv2.offset_l.weight, layer3.13.conv2.offset_l.bias, layer3.13.conv3.weight_gamma, layer3.13.conv3.weight_beta, layer3.14.conv1.weight_gamma, layer3.14.conv1.weight_beta, layer3.14.conv2.weight_diff, layer3.14.conv2.weight_gamma, layer3.14.conv2.weight_beta, layer3.14.conv2.switch.weight, layer3.14.conv2.switch.bias, layer3.14.conv2.pre_context.weight, layer3.14.conv2.pre_context.bias, layer3.14.conv2.post_context.weight, layer3.14.conv2.post_context.bias, layer3.14.conv2.offset_s.weight, layer3.14.conv2.offset_s.bias, layer3.14.conv2.offset_l.weight, layer3.14.conv2.offset_l.bias, layer3.14.conv3.weight_gamma, layer3.14.conv3.weight_beta, layer3.15.conv1.weight_gamma, layer3.15.conv1.weight_beta, layer3.15.conv2.weight_diff, layer3.15.conv2.weight_gamma, layer3.15.conv2.weight_beta, layer3.15.conv2.switch.weight, layer3.15.conv2.switch.bias, layer3.15.conv2.pre_context.weight, layer3.15.conv2.pre_context.bias, layer3.15.conv2.post_context.weight, layer3.15.conv2.post_context.bias, layer3.15.conv2.offset_s.weight, layer3.15.conv2.offset_s.bias, layer3.15.conv2.offset_l.weight, layer3.15.conv2.offset_l.bias, layer3.15.conv3.weight_gamma, layer3.15.conv3.weight_beta, layer3.16.conv1.weight_gamma, layer3.16.conv1.weight_beta, layer3.16.conv2.weight_diff, layer3.16.conv2.weight_gamma, layer3.16.conv2.weight_beta, layer3.16.conv2.switch.weight, layer3.16.conv2.switch.bias, layer3.16.conv2.pre_context.weight, layer3.16.conv2.pre_context.bias, layer3.16.conv2.post_context.weight, layer3.16.conv2.post_context.bias, layer3.16.conv2.offset_s.weight, layer3.16.conv2.offset_s.bias, layer3.16.conv2.offset_l.weight, layer3.16.conv2.offset_l.bias, layer3.16.conv3.weight_gamma, layer3.16.conv3.weight_beta, layer3.17.conv1.weight_gamma, layer3.17.conv1.weight_beta, layer3.17.conv2.weight_diff, layer3.17.conv2.weight_gamma, layer3.17.conv2.weight_beta, layer3.17.conv2.switch.weight, layer3.17.conv2.switch.bias, layer3.17.conv2.pre_context.weight, layer3.17.conv2.pre_context.bias, layer3.17.conv2.post_context.weight, layer3.17.conv2.post_context.bias, layer3.17.conv2.offset_s.weight, layer3.17.conv2.offset_s.bias, layer3.17.conv2.offset_l.weight, layer3.17.conv2.offset_l.bias, layer3.17.conv3.weight_gamma, layer3.17.conv3.weight_beta, layer3.18.conv1.weight_gamma, layer3.18.conv1.weight_beta, layer3.18.conv2.weight_diff, layer3.18.conv2.weight_gamma, layer3.18.conv2.weight_beta, layer3.18.conv2.switch.weight, layer3.18.conv2.switch.bias, layer3.18.conv2.pre_context.weight, layer3.18.conv2.pre_context.bias, layer3.18.conv2.post_context.weight, layer3.18.conv2.post_context.bias, layer3.18.conv2.offset_s.weight, layer3.18.conv2.offset_s.bias, layer3.18.conv2.offset_l.weight, layer3.18.conv2.offset_l.bias, layer3.18.conv3.weight_gamma, layer3.18.conv3.weight_beta, layer3.19.conv1.weight_gamma, layer3.19.conv1.weight_beta, layer3.19.conv2.weight_diff, layer3.19.conv2.weight_gamma, layer3.19.conv2.weight_beta, layer3.19.conv2.switch.weight, layer3.19.conv2.switch.bias, layer3.19.conv2.pre_context.weight, layer3.19.conv2.pre_context.bias, layer3.19.conv2.post_context.weight, layer3.19.conv2.post_context.bias, layer3.19.conv2.offset_s.weight, layer3.19.conv2.offset_s.bias, layer3.19.conv2.offset_l.weight, layer3.19.conv2.offset_l.bias, layer3.19.conv3.weight_gamma, layer3.19.conv3.weight_beta, layer3.20.conv1.weight_gamma, layer3.20.conv1.weight_beta, layer3.20.conv2.weight_diff, layer3.20.conv2.weight_gamma, layer3.20.conv2.weight_beta, layer3.20.conv2.switch.weight, layer3.20.conv2.switch.bias, layer3.20.conv2.pre_context.weight, layer3.20.conv2.pre_context.bias, layer3.20.conv2.post_context.weight, layer3.20.conv2.post_context.bias, layer3.20.conv2.offset_s.weight, layer3.20.conv2.offset_s.bias, layer3.20.conv2.offset_l.weight, layer3.20.conv2.offset_l.bias, layer3.20.conv3.weight_gamma, layer3.20.conv3.weight_beta, layer3.21.conv1.weight_gamma, layer3.21.conv1.weight_beta, layer3.21.conv2.weight_diff, layer3.21.conv2.weight_gamma, layer3.21.conv2.weight_beta, layer3.21.conv2.switch.weight, layer3.21.conv2.switch.bias, layer3.21.conv2.pre_context.weight, layer3.21.conv2.pre_context.bias, layer3.21.conv2.post_context.weight, layer3.21.conv2.post_context.bias, layer3.21.conv2.offset_s.weight, layer3.21.conv2.offset_s.bias, layer3.21.conv2.offset_l.weight, layer3.21.conv2.offset_l.bias, layer3.21.conv3.weight_gamma, layer3.21.conv3.weight_beta, layer3.22.conv1.weight_gamma, layer3.22.conv1.weight_beta, layer3.22.conv2.weight_diff, layer3.22.conv2.weight_gamma, layer3.22.conv2.weight_beta, layer3.22.conv2.switch.weight, layer3.22.conv2.switch.bias, layer3.22.conv2.pre_context.weight, layer3.22.conv2.pre_context.bias, layer3.22.conv2.post_context.weight, layer3.22.conv2.post_context.bias, layer3.22.conv2.offset_s.weight, layer3.22.conv2.offset_s.bias, layer3.22.conv2.offset_l.weight, layer3.22.conv2.offset_l.bias, layer3.22.conv3.weight_gamma, layer3.22.conv3.weight_beta, layer4.0.conv1.weight_gamma, layer4.0.conv1.weight_beta, layer4.0.conv2.weight_diff, layer4.0.conv2.weight_gamma, layer4.0.conv2.weight_beta, layer4.0.conv2.switch.weight, layer4.0.conv2.switch.bias, layer4.0.conv2.pre_context.weight, layer4.0.conv2.pre_context.bias, layer4.0.conv2.post_context.weight, layer4.0.conv2.post_context.bias, layer4.0.conv2.offset_s.weight, layer4.0.conv2.offset_s.bias, layer4.0.conv2.offset_l.weight, layer4.0.conv2.offset_l.bias, layer4.0.conv3.weight_gamma, layer4.0.conv3.weight_beta, layer4.0.downsample.0.weight_gamma, layer4.0.downsample.0.weight_beta, layer4.1.conv1.weight_gamma, layer4.1.conv1.weight_beta, layer4.1.conv2.weight_diff, layer4.1.conv2.weight_gamma, layer4.1.conv2.weight_beta, layer4.1.conv2.switch.weight, layer4.1.conv2.switch.bias, layer4.1.conv2.pre_context.weight, layer4.1.conv2.pre_context.bias, layer4.1.conv2.post_context.weight, layer4.1.conv2.post_context.bias, layer4.1.conv2.offset_s.weight, layer4.1.conv2.offset_s.bias, layer4.1.conv2.offset_l.weight, layer4.1.conv2.offset_l.bias, layer4.1.conv3.weight_gamma, layer4.1.conv3.weight_beta, layer4.2.conv1.weight_gamma, layer4.2.conv1.weight_beta, layer4.2.conv2.weight_diff, layer4.2.conv2.weight_gamma, layer4.2.conv2.weight_beta, layer4.2.conv2.switch.weight, layer4.2.conv2.switch.bias, layer4.2.conv2.pre_context.weight, layer4.2.conv2.pre_context.bias, layer4.2.conv2.post_context.weight, layer4.2.conv2.post_context.bias, layer4.2.conv2.offset_s.weight, layer4.2.conv2.offset_s.bias, layer4.2.conv2.offset_l.weight, layer4.2.conv2.offset_l.bias, layer4.2.conv3.weight_gamma, layer4.2.conv3.weight_beta
2020-06-08 08:59:42,601 - mmdet - WARNING - The model and loaded state dict do not match exactly
missing keys in source state_dict: conv1.weight_gamma, conv1.weight_beta, layer1.0.conv1.weight_gamma, layer1.0.conv1.weight_beta, layer1.0.conv2.weight_gamma, layer1.0.conv2.weight_beta, layer1.0.conv3.weight_gamma, layer1.0.conv3.weight_beta, layer1.0.downsample.0.weight_gamma, layer1.0.downsample.0.weight_beta, layer1.1.conv1.weight_gamma, layer1.1.conv1.weight_beta, layer1.1.conv2.weight_gamma, layer1.1.conv2.weight_beta, layer1.1.conv3.weight_gamma, layer1.1.conv3.weight_beta, layer1.2.conv1.weight_gamma, layer1.2.conv1.weight_beta, layer1.2.conv2.weight_gamma, layer1.2.conv2.weight_beta, layer1.2.conv3.weight_gamma, layer1.2.conv3.weight_beta, layer2.0.conv1.weight_gamma, layer2.0.conv1.weight_beta, layer2.0.conv2.weight_diff, layer2.0.conv2.weight_gamma, layer2.0.conv2.weight_beta, layer2.0.conv2.switch.weight, layer2.0.conv2.switch.bias, layer2.0.conv2.pre_context.weight, layer2.0.conv2.pre_context.bias, layer2.0.conv2.post_context.weight, layer2.0.conv2.post_context.bias, layer2.0.conv2.offset_s.weight, layer2.0.conv2.offset_s.bias, layer2.0.conv2.offset_l.weight, layer2.0.conv2.offset_l.bias, layer2.0.conv3.weight_gamma, layer2.0.conv3.weight_beta, layer2.0.downsample.0.weight_gamma, layer2.0.downsample.0.weight_beta, layer2.0.rfp_conv.weight, layer2.0.rfp_conv.bias, layer2.1.conv1.weight_gamma, layer2.1.conv1.weight_beta, layer2.1.conv2.weight_diff, layer2.1.conv2.weight_gamma, layer2.1.conv2.weight_beta, layer2.1.conv2.switch.weight, layer2.1.conv2.switch.bias, layer2.1.conv2.pre_context.weight, layer2.1.conv2.pre_context.bias, layer2.1.conv2.post_context.weight, layer2.1.conv2.post_context.bias, layer2.1.conv2.offset_s.weight, layer2.1.conv2.offset_s.bias, layer2.1.conv2.offset_l.weight, layer2.1.conv2.offset_l.bias, layer2.1.conv3.weight_gamma, layer2.1.conv3.weight_beta, layer2.2.conv1.weight_gamma, layer2.2.conv1.weight_beta, layer2.2.conv2.weight_diff, layer2.2.conv2.weight_gamma, layer2.2.conv2.weight_beta, layer2.2.conv2.switch.weight, layer2.2.conv2.switch.bias, layer2.2.conv2.pre_context.weight, layer2.2.conv2.pre_context.bias, layer2.2.conv2.post_context.weight, layer2.2.conv2.post_context.bias, layer2.2.conv2.offset_s.weight, layer2.2.conv2.offset_s.bias, layer2.2.conv2.offset_l.weight, layer2.2.conv2.offset_l.bias, layer2.2.conv3.weight_gamma, layer2.2.conv3.weight_beta, layer2.3.conv1.weight_gamma, layer2.3.conv1.weight_beta, layer2.3.conv2.weight_diff, layer2.3.conv2.weight_gamma, layer2.3.conv2.weight_beta, layer2.3.conv2.switch.weight, layer2.3.conv2.switch.bias, layer2.3.conv2.pre_context.weight, layer2.3.conv2.pre_context.bias, layer2.3.conv2.post_context.weight, layer2.3.conv2.post_context.bias, layer2.3.conv2.offset_s.weight, layer2.3.conv2.offset_s.bias, layer2.3.conv2.offset_l.weight, layer2.3.conv2.offset_l.bias, layer2.3.conv3.weight_gamma, layer2.3.conv3.weight_beta, layer3.0.conv1.weight_gamma, layer3.0.conv1.weight_beta, layer3.0.conv2.weight_diff, layer3.0.conv2.weight_gamma, layer3.0.conv2.weight_beta, layer3.0.conv2.switch.weight, layer3.0.conv2.switch.bias, layer3.0.conv2.pre_context.weight, layer3.0.conv2.pre_context.bias, layer3.0.conv2.post_context.weight, layer3.0.conv2.post_context.bias, layer3.0.conv2.offset_s.weight, layer3.0.conv2.offset_s.bias, layer3.0.conv2.offset_l.weight, layer3.0.conv2.offset_l.bias, layer3.0.conv3.weight_gamma, layer3.0.conv3.weight_beta, layer3.0.downsample.0.weight_gamma, layer3.0.downsample.0.weight_beta, layer3.0.rfp_conv.weight, layer3.0.rfp_conv.bias, layer3.1.conv1.weight_gamma, layer3.1.conv1.weight_beta, layer3.1.conv2.weight_diff, layer3.1.conv2.weight_gamma, layer3.1.conv2.weight_beta, layer3.1.conv2.switch.weight, layer3.1.conv2.switch.bias, layer3.1.conv2.pre_context.weight, layer3.1.conv2.pre_context.bias, layer3.1.conv2.post_context.weight, layer3.1.conv2.post_context.bias, layer3.1.conv2.offset_s.weight, layer3.1.conv2.offset_s.bias, layer3.1.conv2.offset_l.weight, layer3.1.conv2.offset_l.bias, layer3.1.conv3.weight_gamma, layer3.1.conv3.weight_beta, layer3.2.conv1.weight_gamma, layer3.2.conv1.weight_beta, layer3.2.conv2.weight_diff, layer3.2.conv2.weight_gamma, layer3.2.conv2.weight_beta, layer3.2.conv2.switch.weight, layer3.2.conv2.switch.bias, layer3.2.conv2.pre_context.weight, layer3.2.conv2.pre_context.bias, layer3.2.conv2.post_context.weight, layer3.2.conv2.post_context.bias, layer3.2.conv2.offset_s.weight, layer3.2.conv2.offset_s.bias, layer3.2.conv2.offset_l.weight, layer3.2.conv2.offset_l.bias, layer3.2.conv3.weight_gamma, layer3.2.conv3.weight_beta, layer3.3.conv1.weight_gamma, layer3.3.conv1.weight_beta, layer3.3.conv2.weight_diff, layer3.3.conv2.weight_gamma, layer3.3.conv2.weight_beta, layer3.3.conv2.switch.weight, layer3.3.conv2.switch.bias, layer3.3.conv2.pre_context.weight, layer3.3.conv2.pre_context.bias, layer3.3.conv2.post_context.weight, layer3.3.conv2.post_context.bias, layer3.3.conv2.offset_s.weight, layer3.3.conv2.offset_s.bias, layer3.3.conv2.offset_l.weight, layer3.3.conv2.offset_l.bias, layer3.3.conv3.weight_gamma, layer3.3.conv3.weight_beta, layer3.4.conv1.weight_gamma, layer3.4.conv1.weight_beta, layer3.4.conv2.weight_diff, layer3.4.conv2.weight_gamma, layer3.4.conv2.weight_beta, layer3.4.conv2.switch.weight, layer3.4.conv2.switch.bias, layer3.4.conv2.pre_context.weight, layer3.4.conv2.pre_context.bias, layer3.4.conv2.post_context.weight, layer3.4.conv2.post_context.bias, layer3.4.conv2.offset_s.weight, layer3.4.conv2.offset_s.bias, layer3.4.conv2.offset_l.weight, layer3.4.conv2.offset_l.bias, layer3.4.conv3.weight_gamma, layer3.4.conv3.weight_beta, layer3.5.conv1.weight_gamma, layer3.5.conv1.weight_beta, layer3.5.conv2.weight_diff, layer3.5.conv2.weight_gamma, layer3.5.conv2.weight_beta, layer3.5.conv2.switch.weight, layer3.5.conv2.switch.bias, layer3.5.conv2.pre_context.weight, layer3.5.conv2.pre_context.bias, layer3.5.conv2.post_context.weight, layer3.5.conv2.post_context.bias, layer3.5.conv2.offset_s.weight, layer3.5.conv2.offset_s.bias, layer3.5.conv2.offset_l.weight, layer3.5.conv2.offset_l.bias, layer3.5.conv3.weight_gamma, layer3.5.conv3.weight_beta, layer3.6.conv1.weight_gamma, layer3.6.conv1.weight_beta, layer3.6.conv2.weight_diff, layer3.6.conv2.weight_gamma, layer3.6.conv2.weight_beta, layer3.6.conv2.switch.weight, layer3.6.conv2.switch.bias, layer3.6.conv2.pre_context.weight, layer3.6.conv2.pre_context.bias, layer3.6.conv2.post_context.weight, layer3.6.conv2.post_context.bias, layer3.6.conv2.offset_s.weight, layer3.6.conv2.offset_s.bias, layer3.6.conv2.offset_l.weight, layer3.6.conv2.offset_l.bias, layer3.6.conv3.weight_gamma, layer3.6.conv3.weight_beta, layer3.7.conv1.weight_gamma, layer3.7.conv1.weight_beta, layer3.7.conv2.weight_diff, layer3.7.conv2.weight_gamma, layer3.7.conv2.weight_beta, layer3.7.conv2.switch.weight, layer3.7.conv2.switch.bias, layer3.7.conv2.pre_context.weight, layer3.7.conv2.pre_context.bias, layer3.7.conv2.post_context.weight, layer3.7.conv2.post_context.bias, layer3.7.conv2.offset_s.weight, layer3.7.conv2.offset_s.bias, layer3.7.conv2.offset_l.weight, layer3.7.conv2.offset_l.bias, layer3.7.conv3.weight_gamma, layer3.7.conv3.weight_beta, layer3.8.conv1.weight_gamma, layer3.8.conv1.weight_beta, layer3.8.conv2.weight_diff, layer3.8.conv2.weight_gamma, layer3.8.conv2.weight_beta, layer3.8.conv2.switch.weight, layer3.8.conv2.switch.bias, layer3.8.conv2.pre_context.weight, layer3.8.conv2.pre_context.bias, layer3.8.conv2.post_context.weight, layer3.8.conv2.post_context.bias, layer3.8.conv2.offset_s.weight, layer3.8.conv2.offset_s.bias, layer3.8.conv2.offset_l.weight, layer3.8.conv2.offset_l.bias, layer3.8.conv3.weight_gamma, layer3.8.conv3.weight_beta, layer3.9.conv1.weight_gamma, layer3.9.conv1.weight_beta, layer3.9.conv2.weight_diff, layer3.9.conv2.weight_gamma, layer3.9.conv2.weight_beta, layer3.9.conv2.switch.weight, layer3.9.conv2.switch.bias, layer3.9.conv2.pre_context.weight, layer3.9.conv2.pre_context.bias, layer3.9.conv2.post_context.weight, layer3.9.conv2.post_context.bias, layer3.9.conv2.offset_s.weight, layer3.9.conv2.offset_s.bias, layer3.9.conv2.offset_l.weight, layer3.9.conv2.offset_l.bias, layer3.9.conv3.weight_gamma, layer3.9.conv3.weight_beta, layer3.10.conv1.weight_gamma, layer3.10.conv1.weight_beta, layer3.10.conv2.weight_diff, layer3.10.conv2.weight_gamma, layer3.10.conv2.weight_beta, layer3.10.conv2.switch.weight, layer3.10.conv2.switch.bias, layer3.10.conv2.pre_context.weight, layer3.10.conv2.pre_context.bias, layer3.10.conv2.post_context.weight, layer3.10.conv2.post_context.bias, layer3.10.conv2.offset_s.weight, layer3.10.conv2.offset_s.bias, layer3.10.conv2.offset_l.weight, layer3.10.conv2.offset_l.bias, layer3.10.conv3.weight_gamma, layer3.10.conv3.weight_beta, layer3.11.conv1.weight_gamma, layer3.11.conv1.weight_beta, layer3.11.conv2.weight_diff, layer3.11.conv2.weight_gamma, layer3.11.conv2.weight_beta, layer3.11.conv2.switch.weight, layer3.11.conv2.switch.bias, layer3.11.conv2.pre_context.weight, layer3.11.conv2.pre_context.bias, layer3.11.conv2.post_context.weight, layer3.11.conv2.post_context.bias, layer3.11.conv2.offset_s.weight, layer3.11.conv2.offset_s.bias, layer3.11.conv2.offset_l.weight, layer3.11.conv2.offset_l.bias, layer3.11.conv3.weight_gamma, layer3.11.conv3.weight_beta, layer3.12.conv1.weight_gamma, layer3.12.conv1.weight_beta, layer3.12.conv2.weight_diff, layer3.12.conv2.weight_gamma, layer3.12.conv2.weight_beta, layer3.12.conv2.switch.weight, layer3.12.conv2.switch.bias, layer3.12.conv2.pre_context.weight, layer3.12.conv2.pre_context.bias, layer3.12.conv2.post_context.weight, layer3.12.conv2.post_context.bias, layer3.12.conv2.offset_s.weight, layer3.12.conv2.offset_s.bias, layer3.12.conv2.offset_l.weight, layer3.12.conv2.offset_l.bias, layer3.12.conv3.weight_gamma, layer3.12.conv3.weight_beta, layer3.13.conv1.weight_gamma, layer3.13.conv1.weight_beta, layer3.13.conv2.weight_diff, layer3.13.conv2.weight_gamma, layer3.13.conv2.weight_beta, layer3.13.conv2.switch.weight, layer3.13.conv2.switch.bias, layer3.13.conv2.pre_context.weight, layer3.13.conv2.pre_context.bias, layer3.13.conv2.post_context.weight, layer3.13.conv2.post_context.bias, layer3.13.conv2.offset_s.weight, layer3.13.conv2.offset_s.bias, layer3.13.conv2.offset_l.weight, layer3.13.conv2.offset_l.bias, layer3.13.conv3.weight_gamma, layer3.13.conv3.weight_beta, layer3.14.conv1.weight_gamma, layer3.14.conv1.weight_beta, layer3.14.conv2.weight_diff, layer3.14.conv2.weight_gamma, layer3.14.conv2.weight_beta, layer3.14.conv2.switch.weight, layer3.14.conv2.switch.bias, layer3.14.conv2.pre_context.weight, layer3.14.conv2.pre_context.bias, layer3.14.conv2.post_context.weight, layer3.14.conv2.post_context.bias, layer3.14.conv2.offset_s.weight, layer3.14.conv2.offset_s.bias, layer3.14.conv2.offset_l.weight, layer3.14.conv2.offset_l.bias, layer3.14.conv3.weight_gamma, layer3.14.conv3.weight_beta, layer3.15.conv1.weight_gamma, layer3.15.conv1.weight_beta, layer3.15.conv2.weight_diff, layer3.15.conv2.weight_gamma, layer3.15.conv2.weight_beta, layer3.15.conv2.switch.weight, layer3.15.conv2.switch.bias, layer3.15.conv2.pre_context.weight, layer3.15.conv2.pre_context.bias, layer3.15.conv2.post_context.weight, layer3.15.conv2.post_context.bias, layer3.15.conv2.offset_s.weight, layer3.15.conv2.offset_s.bias, layer3.15.conv2.offset_l.weight, layer3.15.conv2.offset_l.bias, layer3.15.conv3.weight_gamma, layer3.15.conv3.weight_beta, layer3.16.conv1.weight_gamma, layer3.16.conv1.weight_beta, layer3.16.conv2.weight_diff, layer3.16.conv2.weight_gamma, layer3.16.conv2.weight_beta, layer3.16.conv2.switch.weight, layer3.16.conv2.switch.bias, layer3.16.conv2.pre_context.weight, layer3.16.conv2.pre_context.bias, layer3.16.conv2.post_context.weight, layer3.16.conv2.post_context.bias, layer3.16.conv2.offset_s.weight, layer3.16.conv2.offset_s.bias, layer3.16.conv2.offset_l.weight, layer3.16.conv2.offset_l.bias, layer3.16.conv3.weight_gamma, layer3.16.conv3.weight_beta, layer3.17.conv1.weight_gamma, layer3.17.conv1.weight_beta, layer3.17.conv2.weight_diff, layer3.17.conv2.weight_gamma, layer3.17.conv2.weight_beta, layer3.17.conv2.switch.weight, layer3.17.conv2.switch.bias, layer3.17.conv2.pre_context.weight, layer3.17.conv2.pre_context.bias, layer3.17.conv2.post_context.weight, layer3.17.conv2.post_context.bias, layer3.17.conv2.offset_s.weight, layer3.17.conv2.offset_s.bias, layer3.17.conv2.offset_l.weight, layer3.17.conv2.offset_l.bias, layer3.17.conv3.weight_gamma, layer3.17.conv3.weight_beta, layer3.18.conv1.weight_gamma, layer3.18.conv1.weight_beta, layer3.18.conv2.weight_diff, layer3.18.conv2.weight_gamma, layer3.18.conv2.weight_beta, layer3.18.conv2.switch.weight, layer3.18.conv2.switch.bias, layer3.18.conv2.pre_context.weight, layer3.18.conv2.pre_context.bias, layer3.18.conv2.post_context.weight, layer3.18.conv2.post_context.bias, layer3.18.conv2.offset_s.weight, layer3.18.conv2.offset_s.bias, layer3.18.conv2.offset_l.weight, layer3.18.conv2.offset_l.bias, layer3.18.conv3.weight_gamma, layer3.18.conv3.weight_beta, layer3.19.conv1.weight_gamma, layer3.19.conv1.weight_beta, layer3.19.conv2.weight_diff, layer3.19.conv2.weight_gamma, layer3.19.conv2.weight_beta, layer3.19.conv2.switch.weight, layer3.19.conv2.switch.bias, layer3.19.conv2.pre_context.weight, layer3.19.conv2.pre_context.bias, layer3.19.conv2.post_context.weight, layer3.19.conv2.post_context.bias, layer3.19.conv2.offset_s.weight, layer3.19.conv2.offset_s.bias, layer3.19.conv2.offset_l.weight, layer3.19.conv2.offset_l.bias, layer3.19.conv3.weight_gamma, layer3.19.conv3.weight_beta, layer3.20.conv1.weight_gamma, layer3.20.conv1.weight_beta, layer3.20.conv2.weight_diff, layer3.20.conv2.weight_gamma, layer3.20.conv2.weight_beta, layer3.20.conv2.switch.weight, layer3.20.conv2.switch.bias, layer3.20.conv2.pre_context.weight, layer3.20.conv2.pre_context.bias, layer3.20.conv2.post_context.weight, layer3.20.conv2.post_context.bias, layer3.20.conv2.offset_s.weight, layer3.20.conv2.offset_s.bias, layer3.20.conv2.offset_l.weight, layer3.20.conv2.offset_l.bias, layer3.20.conv3.weight_gamma, layer3.20.conv3.weight_beta, layer3.21.conv1.weight_gamma, layer3.21.conv1.weight_beta, layer3.21.conv2.weight_diff, layer3.21.conv2.weight_gamma, layer3.21.conv2.weight_beta, layer3.21.conv2.switch.weight, layer3.21.conv2.switch.bias, layer3.21.conv2.pre_context.weight, layer3.21.conv2.pre_context.bias, layer3.21.conv2.post_context.weight, layer3.21.conv2.post_context.bias, layer3.21.conv2.offset_s.weight, layer3.21.conv2.offset_s.bias, layer3.21.conv2.offset_l.weight, layer3.21.conv2.offset_l.bias, layer3.21.conv3.weight_gamma, layer3.21.conv3.weight_beta, layer3.22.conv1.weight_gamma, layer3.22.conv1.weight_beta, layer3.22.conv2.weight_diff, layer3.22.conv2.weight_gamma, layer3.22.conv2.weight_beta, layer3.22.conv2.switch.weight, layer3.22.conv2.switch.bias, layer3.22.conv2.pre_context.weight, layer3.22.conv2.pre_context.bias, layer3.22.conv2.post_context.weight, layer3.22.conv2.post_context.bias, layer3.22.conv2.offset_s.weight, layer3.22.conv2.offset_s.bias, layer3.22.conv2.offset_l.weight, layer3.22.conv2.offset_l.bias, layer3.22.conv3.weight_gamma, layer3.22.conv3.weight_beta, layer4.0.conv1.weight_gamma, layer4.0.conv1.weight_beta, layer4.0.conv2.weight_diff, layer4.0.conv2.weight_gamma, layer4.0.conv2.weight_beta, layer4.0.conv2.switch.weight, layer4.0.conv2.switch.bias, layer4.0.conv2.pre_context.weight, layer4.0.conv2.pre_context.bias, layer4.0.conv2.post_context.weight, layer4.0.conv2.post_context.bias, layer4.0.conv2.offset_s.weight, layer4.0.conv2.offset_s.bias, layer4.0.conv2.offset_l.weight, layer4.0.conv2.offset_l.bias, layer4.0.conv3.weight_gamma, layer4.0.conv3.weight_beta, layer4.0.downsample.0.weight_gamma, layer4.0.downsample.0.weight_beta, layer4.0.rfp_conv.weight, layer4.0.rfp_conv.bias, layer4.1.conv1.weight_gamma, layer4.1.conv1.weight_beta, layer4.1.conv2.weight_diff, layer4.1.conv2.weight_gamma, layer4.1.conv2.weight_beta, layer4.1.conv2.switch.weight, layer4.1.conv2.switch.bias, layer4.1.conv2.pre_context.weight, layer4.1.conv2.pre_context.bias, layer4.1.conv2.post_context.weight, layer4.1.conv2.post_context.bias, layer4.1.conv2.offset_s.weight, layer4.1.conv2.offset_s.bias, layer4.1.conv2.offset_l.weight, layer4.1.conv2.offset_l.bias, layer4.1.conv3.weight_gamma, layer4.1.conv3.weight_beta, layer4.2.conv1.weight_gamma, layer4.2.conv1.weight_beta, layer4.2.conv2.weight_diff, layer4.2.conv2.weight_gamma, layer4.2.conv2.weight_beta, layer4.2.conv2.switch.weight, layer4.2.conv2.switch.bias, layer4.2.conv2.pre_context.weight, layer4.2.conv2.pre_context.bias, layer4.2.conv2.post_context.weight, layer4.2.conv2.post_context.bias, layer4.2.conv2.offset_s.weight, layer4.2.conv2.offset_s.bias, layer4.2.conv2.offset_l.weight, layer4.2.conv2.offset_l.bias, layer4.2.conv3.weight_gamma, layer4.2.conv3.weight_beta
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
2020-06-08 08:59:45,129 - mmdet - INFO - Start running, host: root@c73feb983947, work_dir: /content/drive/My Drive/DetectoRS/work_dirs/DetectoRS_mstrain_400_1200_x101_32x4d_40e.py
2020-06-08 08:59:45,130 - mmdet - INFO - workflow: [('train', 1)], max: 40 epochs
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
error in deformable_im2col: no kernel image is available for execution on the device
/pytorch/aten/src/THCUNN/SpatialClassNLLCriterion.cu:104: void cunn_SpatialClassNLLCriterion_updateOutput_kernel(T *, T *, T *, long *, T *, int, int, int, int, int, long) [with T = float, AccumT = float]: block: [0,0,0], thread: [93,0,0] Assertion `t >= 0 && t < n_classes` failed.
/pytorch/aten/src/THCUNN/SpatialClassNLLCriterion.cu:104: void cunn_SpatialClassNLLCriterion_updateOutput_kernel(T *, T *, T *, long *, T *, int, int, int, int, int, long) [with T = float, AccumT = float]: block: [0,0,0], thread: [94,0,0] Assertion `t >= 0 && t < n_classes` failed.
/pytorch/aten/src/THCUNN/SpatialClassNLLCriterion.cu:104: void cunn_SpatialClassNLLCriterion_updateOutput_kernel(T *, T *, T *, long *, T *, int, int, int, int, int, long) [with T = float, AccumT = float]: block: [0,0,0], thread: [95,0,0] Assertion `t >= 0 && t < n_classes` failed.
Traceback (most recent call last):
File "/content/drive/My Drive/DetectoRS/tools/train.py", line 142, in <module>
main()
File "/content/drive/My Drive/DetectoRS/tools/train.py", line 138, in main
meta=meta)
File "/content/drive/My Drive/DetectoRS/mmdet/apis/train.py", line 111, in train_detector
meta=meta)
File "/content/drive/My Drive/DetectoRS/mmdet/apis/train.py", line 242, in _non_dist_train
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/usr/local/lib/python3.6/dist-packages/mmcv/runner/runner.py", line 384, in run
epoch_runner(data_loaders[i], **kwargs)
File "/usr/local/lib/python3.6/dist-packages/mmcv/runner/runner.py", line 283, in train
self.model, data_batch, train_mode=True, **kwargs)
File "/content/drive/My Drive/DetectoRS/mmdet/apis/train.py", line 75, in batch_processor
losses = model(**data)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/parallel/data_parallel.py", line 150, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__
result = self.forward(*input, **kwargs)
File "/content/drive/My Drive/DetectoRS/mmdet/core/fp16/decorators.py", line 49, in new_func
return old_func(*args, **kwargs)
File "/content/drive/My Drive/DetectoRS/mmdet/models/detectors/base.py", line 147, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/content/drive/My Drive/DetectoRS/mmdet/models/detectors/htc.py", line 252, in forward_train
gt_labels[j])
File "/content/drive/My Drive/DetectoRS/mmdet/core/bbox/assigners/max_iou_assigner.py", line 113, in assign
assign_result = self.assign_wrt_overlaps(overlaps, gt_labels)
File "/content/drive/My Drive/DetectoRS/mmdet/core/bbox/assigners/max_iou_assigner.py", line 166, in assign_wrt_overlaps
& (max_overlaps < self.neg_iou_thr)] = 0
RuntimeError: copy_if failed to synchronize: device-side assert triggered
terminate called after throwing an instance of 'c10::Error'
what(): CUDA error: device-side assert triggered (insert_events at /pytorch/c10/cuda/CUDACachingAllocator.cpp:764)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7f200fd5c193 in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10.so)
frame #1: <unknown function> + 0x17f66 (0x7f200ff99f66 in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10_cuda.so)
frame #2: <unknown function> + 0x19cbd (0x7f200ff9bcbd in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10_cuda.so)
frame #3: c10::TensorImpl::release_resources() + 0x4d (0x7f200fd4c63d in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10.so)
frame #4: <unknown function> + 0x67a902 (0x7f2058d83902 in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch_python.so)
frame #5: <unknown function> + 0x67a9a6 (0x7f2058d839a6 in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch_python.so)
frame #6: python3() [0x54ef16]
frame #7: python3() [0x572890]
frame #8: python3() [0x54ec1b]
frame #9: python3() [0x588948]
frame #10: python3() [0x5ad438]
frame #11: python3() [0x5ad44e]
frame #12: python3() [0x5ad44e]
frame #13: python3() [0x5ad44e]
frame #14: python3() [0x5ad44e]
frame #15: python3() [0x5ad44e]
frame #16: python3() [0x5ad44e]
frame #17: python3() [0x5ad44e]
frame #18: python3() [0x5ad44e]
frame #19: python3() [0x56b276]
<omitting python frames>
frame #25: __libc_start_main + 0xe7 (0x7f20643f3b97 in /lib/x86_64-linux-gnu/libc.so.6)