monajalal
commented
10 months ago @jfitzg7 when I run the command I get this error. Could you please show where you downloaded the image_sets folder of ycbv? I don't have it
(gdrnpp) mona@ada:~/gdrnpp_bop2022$ ./core/gdrn_modeling/train_gdrn.sh configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py 0 --eval-only
++ dirname ./core/gdrn_modeling/train_gdrn.sh
+ this_dir=./core/gdrn_modeling
+ CFG=configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py
+ CUDA_VISIBLE_DEVICES=0
+ IFS=,
+ read -ra GPUS
+ NGPU=1
+ echo 'use gpu ids: 0 num gpus: 1'
use gpu ids: 0 num gpus: 1
+ NCCL_DEBUG=INFO
+ OMP_NUM_THREADS=1
+ MKL_NUM_THREADS=1
+ PYTHONPATH=./core/gdrn_modeling/../..:/home/mona/realsense-ros/install/realsense2_camera_msgs/local/lib/python3.10/dist-packages:/opt/ros/humble/lib/python3.10/site-packages:/opt/ros/humble/local/lib/python3.10/dist-packages
+ CUDA_VISIBLE_DEVICES=0
+ python ./core/gdrn_modeling/main_gdrn.py --config-file configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py --num-gpus 1 --eval-only
/home/mona/.local/lib/python3.10/site-packages/mmcv/__init__.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
warnings.warn(
You requested to import horovod which is missing or not supported for your OS.
/home/mona/.local/lib/python3.10/site-packages/mmcv/device/npu/data_parallel.py:22: UserWarning: Torchaudio's I/O functions now support par-call bakcend dispatch. Importing backend implementation directly is no longer guaranteed to work. Please use `backend` keyword with load/save/info function, instead of calling the udnerlying implementation directly.
if hasattr(sys.modules[m], '_check_balance'):
/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../lib/pysixd/misc.py:586: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
def get_obj_im_c(K, t):
/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../lib/pysixd/misc.py:765: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
def compute_2d_bbox_xyxy_from_pose(points, pose, K, width=640, height=480, clip=False):
/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../lib/pysixd/misc.py:793: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
def compute_2d_bbox_xyxy_from_pose_v2(points, pose, K, width=640, height=480, clip=False):
/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../lib/pysixd/misc.py:822: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
def compute_2d_bbox_xywh_from_pose(points, pose, K, width=640, height=480, clip=False):
[0102_233057@main_gdrn:216] soft limit: 500000 hard limit: 1048576
[0102_233057@main_gdrn:227] Command Line Args: Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resume=False, eval_only=True, launcher='none', local_rank=0, fp16_allreduce=False, use_adasum=False, num_gpus=1, num_machines=1, machine_rank=0, dist_url='tcp://127.0.0.1:50154', opts=None, strategy=None)
[0102_233057@main_gdrn:101] optimizer_cfg: {'type': 'Ranger', 'lr': 0.0008, 'weight_decay': 0.01}
[0102_233057@ycbv_d2:594] DBG register dataset: ycbv_train_real
[0102_233057@ycbv_pbr:359] DBG register dataset: ycbv_train_pbr
[0102_233057@ycbv_d2:594] DBG register dataset: ycbv_test
20240102_103057|core.utils.default_args_setup@123: Rank of current process: 0. World size: 1
20240102_103057|core.utils.default_args_setup@124: Environment info:
------------------------------- -----------------------------------------------------------------------------
sys.platform linux
Python 3.10.4 | packaged by conda-forge | (main, Mar 24 2022, 17:39:04) [GCC 10.3.0]
numpy 1.26.2
detectron2 0.6 @/home/mona/anaconda3/envs/gdrnpp/lib/python3.10/site-packages/detectron2
Compiler GCC 11.4
CUDA compiler CUDA 11.8
detectron2 arch flags 8.9
DETECTRON2_ENV_MODULE <not set>
PyTorch 2.1.2+cu118 @/home/mona/.local/lib/python3.10/site-packages/torch
PyTorch debug build False
torch._C._GLIBCXX_USE_CXX11_ABI False
GPU available Yes
GPU 0 NVIDIA RTX 6000 Ada Generation (arch=8.9)
Driver version 535.104.12
CUDA_HOME /usr/local/cuda-11.8
Pillow 9.0.0.post1
torchvision 0.16.2+cu118 @/home/mona/.local/lib/python3.10/site-packages/torchvision
torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
fvcore 0.1.5.post20221221
iopath 0.1.9
cv2 4.8.1
------------------------------- -----------------------------------------------------------------------------
PyTorch built with:
- GCC 9.3
- C++ Version: 201703
- Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.1.1 (Git Hash 64f6bcbcbab628e96f33a62c3e975f8535a7bde4)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 11.8
- NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_90,code=sm_90
- CuDNN 8.7
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-invalid-partial-specialization -Wno-unused-private-field -Wno-aligned-allocation-unavailable -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.1.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
20240102_103057|core.utils.default_args_setup@126: Command line arguments: Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resume=False, eval_only=True, launcher='none', local_rank=0, fp16_allreduce=False, use_adasum=False, num_gpus=1, num_machines=1, machine_rank=0, dist_url='tcp://127.0.0.1:50154', opts=None, strategy=None)
20240102_103057|core.utils.default_args_setup@128: Contents of args.config_file=configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py:
# about 3 days
_base_ = ["../../_base_/gdrn_base.py"]
OUTPUT_DIR = "output/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv"
INPUT = dict(
DZI_PAD_SCALE=1.5,
TRUNCATE_FG=True,
CHANGE_BG_PROB=0.5,
COLOR_AUG_PROB=0.8,
COLOR_AUG_TYPE="code",
COLOR_AUG_CODE=(
"Sequential(["
# Sometimes(0.5, PerspectiveTransform(0.05)),
# Sometimes(0.5, CropAndPad(percent=(-0.05, 0.1))),
# Sometimes(0.5, Affine(scale=(1.0, 1.2))),
"Sometimes(0.5, CoarseDropout( p=0.2, size_percent=0.05) ),"
"Sometimes(0.4, GaussianBlur((0., 3.))),"
"Sometimes(0.3, pillike.EnhanceSharpness(factor=(0., 50.))),"
"Sometimes(0.3, pillike.EnhanceContrast(factor=(0.2, 50.))),"
"Sometimes(0.5, pillike.EnhanceBrightness(factor=(0.1, 6.))),"
"Sometimes(0.3, pillike.EnhanceColor(factor=(0., 20.))),"
"Sometimes(0.5, Add((-25, 25), per_channel=0.3)),"
"Sometimes(0.3, Invert(0.2, per_channel=True)),"
"Sometimes(0.5, Multiply((0.6, 1.4), per_channel=0.5)),"
"Sometimes(0.5, Multiply((0.6, 1.4))),"
"Sometimes(0.1, AdditiveGaussianNoise(scale=10, per_channel=True)),"
"Sometimes(0.5, iaa.contrast.LinearContrast((0.5, 2.2), per_channel=0.3)),"
"Sometimes(0.5, Grayscale(alpha=(0.0, 1.0)))," # maybe remove for det
"], random_order=True)"
# cosy+aae
),
)
SOLVER = dict(
IMS_PER_BATCH=48,
TOTAL_EPOCHS=40, # 10
LR_SCHEDULER_NAME="flat_and_anneal",
ANNEAL_METHOD="cosine", # "cosine"
ANNEAL_POINT=0.72,
OPTIMIZER_CFG=dict(_delete_=True, type="Ranger", lr=8e-4, weight_decay=0.01),
WEIGHT_DECAY=0.0,
WARMUP_FACTOR=0.001,
WARMUP_ITERS=1000,
)
DATASETS = dict(
TRAIN=("ycbv_train_real", "ycbv_train_pbr"),
TEST=("ycbv_test",),
DET_FILES_TEST=("datasets/BOP_DATASETS/ycbv/test/test_bboxes/yolox_x_640_ycbv_real_pbr_ycbv_bop_test.json",),
SYM_OBJS=[
"024_bowl",
"036_wood_block",
"051_large_clamp",
"052_extra_large_clamp",
"061_foam_brick",
], # used for custom evalutor
)
DATALOADER = dict(
# Number of data loading threads
NUM_WORKERS=8,
FILTER_VISIB_THR=0.3,
)
MODEL = dict(
LOAD_DETS_TEST=True,
PIXEL_MEAN=[0.0, 0.0, 0.0],
PIXEL_STD=[255.0, 255.0, 255.0],
BBOX_TYPE="AMODAL_CLIP", # VISIB or AMODAL
POSE_NET=dict(
NAME="GDRN_double_mask",
XYZ_ONLINE=True,
NUM_CLASSES=21,
BACKBONE=dict(
FREEZE=False,
PRETRAINED="timm",
INIT_CFG=dict(
type="timm/convnext_base",
pretrained=True,
in_chans=3,
features_only=True,
out_indices=(3,),
),
),
## geo head: Mask, XYZ, Region
GEO_HEAD=dict(
FREEZE=False,
INIT_CFG=dict(
type="TopDownDoubleMaskXyzRegionHead",
in_dim=1024, # this is num out channels of backbone conv feature
),
NUM_REGIONS=64,
XYZ_CLASS_AWARE=True,
MASK_CLASS_AWARE=True,
REGION_CLASS_AWARE=True,
),
PNP_NET=dict(
INIT_CFG=dict(norm="GN", act="gelu"),
REGION_ATTENTION=True,
WITH_2D_COORD=True,
ROT_TYPE="allo_rot6d",
TRANS_TYPE="centroid_z",
),
LOSS_CFG=dict(
# xyz loss ----------------------------
XYZ_LOSS_TYPE="L1", # L1 | CE_coor
XYZ_LOSS_MASK_GT="visib", # trunc | visib | obj
XYZ_LW=1.0,
# mask loss ---------------------------
MASK_LOSS_TYPE="L1", # L1 | BCE | CE
MASK_LOSS_GT="trunc", # trunc | visib | gt
MASK_LW=1.0,
# full mask loss ---------------------------
FULL_MASK_LOSS_TYPE="L1", # L1 | BCE | CE
FULL_MASK_LW=1.0,
# region loss -------------------------
REGION_LOSS_TYPE="CE", # CE
REGION_LOSS_MASK_GT="visib", # trunc | visib | obj
REGION_LW=1.0,
# pm loss --------------
PM_LOSS_SYM=True, # NOTE: sym loss
PM_R_ONLY=True, # only do R loss in PM
PM_LW=1.0,
# centroid loss -------
CENTROID_LOSS_TYPE="L1",
CENTROID_LW=1.0,
# z loss -----------
Z_LOSS_TYPE="L1",
Z_LW=1.0,
),
),
)
VAL = dict(
DATASET_NAME="ycbv",
SPLIT_TYPE="",
SCRIPT_PATH="lib/pysixd/scripts/eval_pose_results_more.py",
TARGETS_FILENAME="test_targets_bop19.json",
ERROR_TYPES="vsd,mspd,mssd",
USE_BOP=True, # whether to use bop toolkit
)
TEST = dict(EVAL_PERIOD=0, VIS=False, TEST_BBOX_TYPE="est") # gt | est
20240102_103057|core.utils.default_args_setup@135: Running with full config:
Config (path: configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py): {'OUTPUT_ROOT': 'output', 'OUTPUT_DIR': 'output/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv', 'EXP_NAME': '', 'DEBUG': False, 'SEED': -1, 'CUDNN_BENCHMARK': True, 'IM_BACKEND': 'cv2', 'VIS_PERIOD': 0, 'INPUT': {'FORMAT': 'BGR', 'MIN_SIZE_TRAIN': 480, 'MAX_SIZE_TRAIN': 640, 'MIN_SIZE_TRAIN_SAMPLING': 'choice', 'MIN_SIZE_TEST': 480, 'MAX_SIZE_TEST': 640, 'WITH_DEPTH': False, 'BP_DEPTH': False, 'AUG_DEPTH': False, 'NORM_DEPTH': False, 'DROP_DEPTH_RATIO': 0.2, 'DROP_DEPTH_PROB': 0.5, 'ADD_NOISE_DEPTH_LEVEL': 0.01, 'ADD_NOISE_DEPTH_PROB': 0.9, 'COLOR_AUG_PROB': 0.8, 'COLOR_AUG_TYPE': 'code', 'COLOR_AUG_CODE': 'Sequential([Sometimes(0.5, CoarseDropout( p=0.2, size_percent=0.05) ),Sometimes(0.4, GaussianBlur((0., 3.))),Sometimes(0.3, pillike.EnhanceSharpness(factor=(0., 50.))),Sometimes(0.3, pillike.EnhanceContrast(factor=(0.2, 50.))),Sometimes(0.5, pillike.EnhanceBrightness(factor=(0.1, 6.))),Sometimes(0.3, pillike.EnhanceColor(factor=(0., 20.))),Sometimes(0.5, Add((-25, 25), per_channel=0.3)),Sometimes(0.3, Invert(0.2, per_channel=True)),Sometimes(0.5, Multiply((0.6, 1.4), per_channel=0.5)),Sometimes(0.5, Multiply((0.6, 1.4))),Sometimes(0.1, AdditiveGaussianNoise(scale=10, per_channel=True)),Sometimes(0.5, iaa.contrast.LinearContrast((0.5, 2.2), per_channel=0.3)),Sometimes(0.5, Grayscale(alpha=(0.0, 1.0))),], random_order=True)', 'COLOR_AUG_SYN_ONLY': False, 'RANDOM_FLIP': 'none', 'WITH_BG_DEPTH': False, 'BG_DEPTH_FACTOR': 10000.0, 'BG_TYPE': 'VOC_table', 'BG_IMGS_ROOT': 'datasets/VOCdevkit/VOC2012/', 'NUM_BG_IMGS': 10000, 'CHANGE_BG_PROB': 0.5, 'TRUNCATE_FG': True, 'BG_KEEP_ASPECT_RATIO': True, 'DZI_TYPE': 'uniform', 'DZI_PAD_SCALE': 1.5, 'DZI_SCALE_RATIO': 0.25, 'DZI_SHIFT_RATIO': 0.25, 'SMOOTH_XYZ': False}, 'DATASETS': {'TRAIN': ('ycbv_train_real', 'ycbv_train_pbr'), 'TRAIN2': (), 'TRAIN2_RATIO': 0.0, 'DATA_LEN_WITH_TRAIN2': True, 'PROPOSAL_FILES_TRAIN': (), 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, 'TEST': ('ycbv_test',), 'PROPOSAL_FILES_TEST': (), 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, 'DET_FILES_TRAIN': (), 'DET_TOPK_PER_OBJ_TRAIN': 1, 'DET_TOPK_PER_IM_TRAIN': 30, 'DET_THR_TRAIN': 0.0, 'DET_FILES_TEST': ('datasets/BOP_DATASETS/ycbv/test/test_bboxes/yolox_x_640_ycbv_real_pbr_ycbv_bop_test.json',), 'DET_TOPK_PER_OBJ': 1, 'DET_TOPK_PER_IM': 30, 'DET_THR': 0.0, 'INIT_POSE_FILES_TEST': (), 'INIT_POSE_TOPK_PER_OBJ': 1, 'INIT_POSE_TOPK_PER_IM': 30, 'INIT_POSE_THR': 0.0, 'SYM_OBJS': ['024_bowl', '036_wood_block', '051_large_clamp', '052_extra_large_clamp', '061_foam_brick'], 'EVAL_SCENE_IDS': None}, 'DATALOADER': {'NUM_WORKERS': 8, 'PERSISTENT_WORKERS': False, 'MAX_OBJS_TRAIN': 120, 'ASPECT_RATIO_GROUPING': False, 'SAMPLER_TRAIN': 'TrainingSampler', 'REPEAT_THRESHOLD': 0.0, 'FILTER_EMPTY_ANNOTATIONS': True, 'FILTER_EMPTY_DETS': True, 'FILTER_VISIB_THR': 0.3, 'REMOVE_ANNO_KEYS': []}, 'SOLVER': {'IMS_PER_BATCH': 48, 'REFERENCE_BS': 48, 'TOTAL_EPOCHS': 40, 'OPTIMIZER_CFG': {'type': 'Ranger', 'lr': 0.0008, 'weight_decay': 0.01}, 'GAMMA': 0.1, 'BIAS_LR_FACTOR': 1.0, 'LR_SCHEDULER_NAME': 'flat_and_anneal', 'WARMUP_METHOD': 'linear', 'WARMUP_FACTOR': 0.001, 'WARMUP_ITERS': 1000, 'ANNEAL_METHOD': 'cosine', 'ANNEAL_POINT': 0.72, 'POLY_POWER': 0.9, 'REL_STEPS': (0.5, 0.75), 'CHECKPOINT_PERIOD': 5, 'CHECKPOINT_BY_EPOCH': True, 'MAX_TO_KEEP': 5, 'CLIP_GRADIENTS': {'ENABLED': False, 'CLIP_TYPE': 'value', 'CLIP_VALUE': 1.0, 'NORM_TYPE': 2.0}, 'SET_NAN_GRAD_TO_ZERO': False, 'AMP': {'ENABLED': False}, 'WEIGHT_DECAY': 0.01, 'OPTIMIZER_NAME': 'Ranger', 'BASE_LR': 0.0008, 'MOMENTUM': 0.9}, 'TRAIN': {'PRINT_FREQ': 100, 'VERBOSE': False, 'VIS': False, 'VIS_IMG': False}, 'VAL': {'DATASET_NAME': 'ycbv', 'SCRIPT_PATH': 'lib/pysixd/scripts/eval_pose_results_more.py', 'RESULTS_PATH': '', 'TARGETS_FILENAME': 'test_targets_bop19.json', 'ERROR_TYPES': 'vsd,mspd,mssd', 'RENDERER_TYPE': 'cpp', 'SPLIT': 'test', 'SPLIT_TYPE': '', 'N_TOP': 1, 'EVAL_CACHED': False, 'SCORE_ONLY': False, 'EVAL_PRINT_ONLY': False, 'EVAL_PRECISION': False, 'USE_BOP': True, 'SAVE_BOP_CSV_ONLY': False}, 'TEST': {'EVAL_PERIOD': 0, 'VIS': False, 'TEST_BBOX_TYPE': 'est', 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}, 'AMP_TEST': False, 'COLOR_AUG': False, 'USE_PNP': False, 'SAVE_RESULTS_ONLY': False, 'PNP_TYPE': 'ransac_pnp', 'USE_DEPTH_REFINE': False, 'DEPTH_REFINE_ITER': 2, 'DEPTH_REFINE_THRESHOLD': 0.8, 'USE_COOR_Z_REFINE': False}, 'DIST_PARAMS': {'backend': 'nccl'}, 'MODEL': {'DEVICE': 'cuda', 'WEIGHTS': '', 'PIXEL_MEAN': [0.0, 0.0, 0.0], 'PIXEL_STD': [255.0, 255.0, 255.0], 'LOAD_DETS_TEST': True, 'BBOX_CROP_REAL': False, 'BBOX_CROP_SYN': False, 'BBOX_TYPE': 'AMODAL_CLIP', 'EMA': {'ENABLED': False, 'INIT_CFG': {'decay': 0.9999, 'updates': 0}}, 'POSE_NET': {'NAME': 'GDRN_double_mask', 'XYZ_ONLINE': True, 'XYZ_BP': True, 'NUM_CLASSES': 21, 'USE_MTL': False, 'INPUT_RES': 256, 'OUTPUT_RES': 64, 'BACKBONE': {'FREEZE': False, 'PRETRAINED': 'timm', 'INIT_CFG': {'type': 'timm/convnext_base', 'in_chans': 3, 'features_only': True, 'pretrained': True, 'out_indices': (3,)}}, 'DEPTH_BACKBONE': {'ENABLED': False, 'FREEZE': False, 'PRETRAINED': 'timm', 'INIT_CFG': {'type': 'timm/resnet18', 'in_chans': 1, 'features_only': True, 'pretrained': True, 'out_indices': (4,)}}, 'FUSE_RGBD_TYPE': 'cat', 'NECK': {'ENABLED': False, 'FREEZE': False, 'LR_MULT': 1.0, 'INIT_CFG': {'type': 'FPN', 'in_channels': [256, 512, 1024, 2048], 'out_channels': 256, 'num_outs': 4}}, 'GEO_HEAD': {'FREEZE': False, 'LR_MULT': 1.0, 'INIT_CFG': {'type': 'TopDownDoubleMaskXyzRegionHead', 'in_dim': 1024, 'up_types': ('deconv', 'bilinear', 'bilinear'), 'deconv_kernel_size': 3, 'num_conv_per_block': 2, 'feat_dim': 256, 'feat_kernel_size': 3, 'norm': 'GN', 'num_gn_groups': 32, 'act': 'GELU', 'out_kernel_size': 1, 'out_layer_shared': True}, 'XYZ_BIN': 64, 'XYZ_CLASS_AWARE': True, 'MASK_CLASS_AWARE': True, 'REGION_CLASS_AWARE': True, 'MASK_THR_TEST': 0.5, 'NUM_REGIONS': 64}, 'PNP_NET': {'FREEZE': False, 'LR_MULT': 1.0, 'INIT_CFG': {'type': 'ConvPnPNet', 'norm': 'GN', 'act': 'gelu', 'num_gn_groups': 32, 'drop_prob': 0.0, 'denormalize_by_extent': True}, 'WITH_2D_COORD': True, 'COORD_2D_TYPE': 'abs', 'REGION_ATTENTION': True, 'MASK_ATTENTION': 'none', 'ROT_TYPE': 'allo_rot6d', 'TRANS_TYPE': 'centroid_z', 'Z_TYPE': 'REL'}, 'LOSS_CFG': {'XYZ_LOSS_TYPE': 'L1', 'XYZ_LOSS_MASK_GT': 'visib', 'XYZ_LW': 1.0, 'FULL_MASK_LOSS_TYPE': 'L1', 'FULL_MASK_LW': 1.0, 'MASK_LOSS_TYPE': 'L1', 'MASK_LOSS_GT': 'trunc', 'MASK_LW': 1.0, 'REGION_LOSS_TYPE': 'CE', 'REGION_LOSS_MASK_GT': 'visib', 'REGION_LW': 1.0, 'NUM_PM_POINTS': 3000, 'PM_LOSS_TYPE': 'L1', 'PM_SMOOTH_L1_BETA': 1.0, 'PM_LOSS_SYM': True, 'PM_NORM_BY_EXTENT': False, 'PM_R_ONLY': True, 'PM_DISENTANGLE_T': False, 'PM_DISENTANGLE_Z': False, 'PM_T_USE_POINTS': True, 'PM_LW': 1.0, 'ROT_LOSS_TYPE': 'angular', 'ROT_LW': 0.0, 'CENTROID_LOSS_TYPE': 'L1', 'CENTROID_LW': 1.0, 'Z_LOSS_TYPE': 'L1', 'Z_LW': 1.0, 'TRANS_LOSS_TYPE': 'L1', 'TRANS_LOSS_DISENTANGLE': True, 'TRANS_LW': 0.0, 'BIND_LOSS_TYPE': 'L1', 'BIND_LW': 0.0}}, 'KEYPOINT_ON': False, 'LOAD_PROPOSALS': False}, 'EXP_ID': 'convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv_test', 'RESUME': False}
20240102_103057|core.utils.default_args_setup@144: Full config saved to output/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py
Global seed set to 57917688
20240102_103057|d2.utils.env@41: Using a generated random seed 57917688
20240102_103057|core.utils.default_args_setup@162: Used mmcv backend: cv2
20240102_103057|__main__@157: Used GDRN module name: GDRN_double_mask
20240102_103058|timm.models.helpers@244: Loading pretrained weights from url (https://dl.fbaipublicfiles.com/convnext/convnext_base_1k_224_ema.pth)
20240102_103059|core.gdrn_modeling.models.GDRN_double_mask@600: Check if the backbone has been initialized with its own method!
20240102_103059|__main__@159: Model:
GDRN_DoubleMask(
(backbone): FeatureListNet(
(stem_0): Conv2d(3, 128, kernel_size=(4, 4), stride=(4, 4))
(stem_1): LayerNorm2d((128,), eps=1e-06, elementwise_affine=True)
(stages_0): ConvNeXtStage(
(downsample): Identity()
(blocks): Sequential(
(0): ConvNeXtBlock(
(conv_dw): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=128)
(norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=128, out_features=512, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=512, out_features=128, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(1): ConvNeXtBlock(
(conv_dw): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=128)
(norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=128, out_features=512, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=512, out_features=128, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(2): ConvNeXtBlock(
(conv_dw): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=128)
(norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=128, out_features=512, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=512, out_features=128, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
)
)
(stages_1): ConvNeXtStage(
(downsample): Sequential(
(0): LayerNorm2d((128,), eps=1e-06, elementwise_affine=True)
(1): Conv2d(128, 256, kernel_size=(2, 2), stride=(2, 2))
)
(blocks): Sequential(
(0): ConvNeXtBlock(
(conv_dw): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256)
(norm): LayerNorm((256,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=256, out_features=1024, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=1024, out_features=256, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(1): ConvNeXtBlock(
(conv_dw): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256)
(norm): LayerNorm((256,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=256, out_features=1024, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=1024, out_features=256, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(2): ConvNeXtBlock(
(conv_dw): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256)
(norm): LayerNorm((256,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=256, out_features=1024, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=1024, out_features=256, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
)
)
(stages_2): ConvNeXtStage(
(downsample): Sequential(
(0): LayerNorm2d((256,), eps=1e-06, elementwise_affine=True)
(1): Conv2d(256, 512, kernel_size=(2, 2), stride=(2, 2))
)
(blocks): Sequential(
(0): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(1): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(2): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(3): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(4): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(5): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(6): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(7): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(8): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(9): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(10): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(11): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(12): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(13): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(14): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(15): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(16): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(17): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(18): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(19): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(20): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(21): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(22): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(23): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(24): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(25): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(26): ConvNeXtBlock(
(conv_dw): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=512)
(norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
)
)
(stages_3): ConvNeXtStage(
(downsample): Sequential(
(0): LayerNorm2d((512,), eps=1e-06, elementwise_affine=True)
(1): Conv2d(512, 1024, kernel_size=(2, 2), stride=(2, 2))
)
(blocks): Sequential(
(0): ConvNeXtBlock(
(conv_dw): Conv2d(1024, 1024, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=1024)
(norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(1): ConvNeXtBlock(
(conv_dw): Conv2d(1024, 1024, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=1024)
(norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
(2): ConvNeXtBlock(
(conv_dw): Conv2d(1024, 1024, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=1024)
(norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(drop_path): Identity()
)
)
)
)
(geo_head_net): TopDownDoubleMaskXyzRegionHead(
(features): ModuleList(
(0): ConvTranspose2d(1024, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1), bias=False)
(1): GroupNorm(32, 256, eps=1e-05, affine=True)
(2): GELU(approximate='none')
(3-4): 2 x ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(norm): GroupNorm(32, 256, eps=1e-05, affine=True)
(gn): GroupNorm(32, 256, eps=1e-05, affine=True)
(activate): GELU(approximate='none')
)
(5): UpsamplingBilinear2d(scale_factor=2.0, mode='bilinear')
(6-7): 2 x ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(norm): GroupNorm(32, 256, eps=1e-05, affine=True)
(gn): GroupNorm(32, 256, eps=1e-05, affine=True)
(activate): GELU(approximate='none')
)
(8): UpsamplingBilinear2d(scale_factor=2.0, mode='bilinear')
(9-10): 2 x ConvModule(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(norm): GroupNorm(32, 256, eps=1e-05, affine=True)
(gn): GroupNorm(32, 256, eps=1e-05, affine=True)
(activate): GELU(approximate='none')
)
)
(out_layer): Conv2d(256, 1470, kernel_size=(1, 1), stride=(1, 1))
)
(pnp_net): ConvPnPNet(
(act): GELU(approximate='none')
(dropblock): LinearScheduler(
(dropblock): DropBlock2D()
)
(features): ModuleList(
(0): Conv2d(69, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): GroupNorm(32, 128, eps=1e-05, affine=True)
(2): GELU(approximate='none')
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(4): GroupNorm(32, 128, eps=1e-05, affine=True)
(5): GELU(approximate='none')
(6): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(7): GroupNorm(32, 128, eps=1e-05, affine=True)
(8): GELU(approximate='none')
)
(fc1): Linear(in_features=8192, out_features=1024, bias=True)
(fc2): Linear(in_features=1024, out_features=256, bias=True)
(fc_r): Linear(in_features=256, out_features=6, bias=True)
(fc_t): Linear(in_features=256, out_features=3, bias=True)
)
)
20240102_103059|__main__@171: 102.873543M params
20240102_103059|d2.checkpoint.detection_checkpoint@38: [DetectionCheckpointer] Loading from ...
20240102_103059|fvcore.common.checkpoint@148: No checkpoint found. Initializing model from scratch
20240102_103100|core.gdrn_modeling.datasets.ycbv_d2@310: loading dataset dicts: ycbv_test
20240102_103100|ERR|__main__@233: An error has been caught in function '<module>', process 'MainProcess' (15333), thread 'MainThread' (140609077046144):
Traceback (most recent call last):
> File "/home/mona/gdrnpp_bop2022/./core/gdrn_modeling/main_gdrn.py", line 233, in <module>
main(args)
│ └ Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resume...
└ <function main at 0x7fe0db649bd0>
File "/home/mona/gdrnpp_bop2022/./core/gdrn_modeling/main_gdrn.py", line 205, in main
).run(args, cfg)
│ └ Config (path: configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py): {'OUTPUT_ROOT':...
└ Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resume...
File "/home/mona/.local/lib/python3.10/site-packages/pytorch_lightning/lite/lite.py", line 408, in _run_impl
return run_method(*args, **kwargs)
│ │ └ {}
│ └ (Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resum...
└ functools.partial(<bound method LightningLite._run_with_strategy_setup of <__main__.Lite object at 0x7fe218caccd0>>, <bound m...
File "/home/mona/.local/lib/python3.10/site-packages/pytorch_lightning/lite/lite.py", line 413, in _run_with_strategy_setup
return run_method(*args, **kwargs)
│ │ └ {}
│ └ (Namespace(config_file='configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py', resum...
└ <bound method Lite.run of <__main__.Lite object at 0x7fe218caccd0>>
File "/home/mona/gdrnpp_bop2022/./core/gdrn_modeling/main_gdrn.py", line 183, in run
return self.do_test(cfg, model)
│ │ │ └ _LiteModule(
│ │ │ (_module): GDRN_DoubleMask(
│ │ │ (backbone): FeatureListNet(
│ │ │ (stem_0): Conv2d(3, 128, kernel_size=(4, 4),...
│ │ └ Config (path: configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py): {'OUTPUT_ROOT':...
│ └ <function GDRN_Lite.do_test at 0x7fe0e2940670>
└ <__main__.Lite object at 0x7fe218caccd0>
File "/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../core/gdrn_modeling/engine/engine.py", line 157, in do_test
data_loader = build_gdrn_test_loader(cfg, dataset_name, train_objs=evaluator.train_objs)
│ │ │ │ └ ['002_master_chef_can', '003_cracker_box', '004_sugar_box', '005_tomato_soup_can', '006_mustard_bottle', '007_tuna_fish_can',...
│ │ │ └ <core.gdrn_modeling.engine.gdrn_evaluator.GDRN_Evaluator object at 0x7fe0db232290>
│ │ └ 'ycbv_test'
│ └ Config (path: configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py): {'OUTPUT_ROOT':...
└ <function build_gdrn_test_loader at 0x7fe0e2da1bd0>
File "/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../core/gdrn_modeling/datasets/data_loader.py", line 914, in build_gdrn_test_loader
dataset_dicts = get_detection_dataset_dicts(
└ <function get_detection_dataset_dicts at 0x7fe117c9f010>
File "/home/mona/anaconda3/envs/gdrnpp/lib/python3.10/site-packages/detectron2/data/build.py", line 253, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
│ │ └ ['ycbv_test']
│ └ <function _DatasetCatalog.get at 0x7fe117c83370>
└ DatasetCatalog(registered datasets: coco_2014_train, coco_2014_val, coco_2014_minival, coco_2014_valminusminival, coco_2017_t...
File "/home/mona/anaconda3/envs/gdrnpp/lib/python3.10/site-packages/detectron2/data/build.py", line 253, in <listcomp>
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names]
│ │ │ └ 'ycbv_test'
│ │ └ 'ycbv_test'
│ └ <function _DatasetCatalog.get at 0x7fe117c83370>
└ DatasetCatalog(registered datasets: coco_2014_train, coco_2014_val, coco_2014_minival, coco_2014_valminusminival, coco_2017_t...
File "/home/mona/anaconda3/envs/gdrnpp/lib/python3.10/site-packages/detectron2/data/catalog.py", line 58, in get
return f()
└ <core.gdrn_modeling.datasets.ycbv_d2.YCBV_Dataset object at 0x7fe0db67dc60>
File "/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../core/gdrn_modeling/datasets/ycbv_d2.py", line 316, in __call__
dataset_dicts.extend(self._load_from_idx_file(ann_file, image_root))
│ │ │ │ │ └ '/home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv/test'
│ │ │ │ └ '/home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv/image_sets/keyframe.txt'
│ │ │ └ <function YCBV_Dataset._load_from_idx_file at 0x7fe0e41ca950>
│ │ └ <core.gdrn_modeling.datasets.ycbv_d2.YCBV_Dataset object at 0x7fe0db67dc60>
│ └ <method 'extend' of 'list' objects>
└ []
File "/home/mona/gdrnpp_bop2022/core/gdrn_modeling/../../core/gdrn_modeling/datasets/ycbv_d2.py", line 100, in _load_from_idx_file
with open(idx_file, "r") as f:
└ '/home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv/image_sets/keyframe.txt'
FileNotFoundError: [Errno 2] No such file or directory: '/home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv/image_sets/keyframe.txt'
(gdrnpp) mona@ada:~/gdrnpp_bop2022$ ls /home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv
lrwxrwxrwx 1 mona mona 22 Jan 2 09:43 /home/mona/gdrnpp_bop2022/datasets/BOP_DATASETS/ycbv -> /data2/data/BOP/YCB-V/
(gdrnpp) mona@ada:~/gdrnpp_bop2022$ ls /data2/data/BOP/YCB-V/
total 126G
drwxr-xr-x 14 mona mona 4.0K Aug 6 2019 test
drwxr-xr-x 82 mona mona 4.0K Aug 6 2019 train_real
drwxr-xr-x 82 mona mona 4.0K Aug 12 2019 train_synt
drwxrwxr-x 2 mona mona 4.0K Sep 27 2019 ycbv
drwxrwx--- 52 mona mona 4.0K Jun 15 2020 train_pbr
drwxrwxr-x 2 mona mona 4.0K Oct 24 16:13 models
drwxrwxr-x 2 mona mona 4.0K Oct 24 16:13 models_eval
drwxrwxr-x 2 mona mona 4.0K Oct 24 16:13 models_fine
drwxrwxr-x 10 mona mona 4.0K Oct 30 08:16 .
drwxrwxr-x 9 mona mona 4.0K Dec 11 15:53 ..
-rw-rw-r-- 1 mona mona 501M Aug 15 2019 ycbv_models.zip
-rw-rw-r-- 1 mona mona 16K Sep 27 2019 ycbv_base.zip
-rw-rw-r-- 1 mona mona 71G Jun 10 2020 ycbv_train_real.zip
-rw-rw-r-- 1 mona mona 21G Jun 11 2020 ycbv_train_synt.zip
-rw-rw-r-- 1 mona mona 14G Jun 11 2020 ycbv_test_all.zip
-rw-rw-r-- 1 mona mona 630M Jun 11 2020 ycbv_test_bop19.zip
-rw-rw-r-- 1 mona mona 20G Jun 17 2020 ycbv_train_pbr.zip
jfitzg7
kevinDrawn
shanice-l
I ran into this error while running the command
./core/gdrn_modeling/train_gdrn.sh configs/gdrn/ycbv/convnext_a6_AugCosyAAEGray_BG05_mlL1_DMask_amodalClipBox_classAware_ycbv.py 0,1 --strategy ddp --eval-onlywhich seems to be related to imageio:The line of code
return tuple(int(x) for x in pil_version.split("."))grabs the pillow version which is 9.0.0.post1 and doesn't parse the post1 part correctly.I've downgraded to imageio==2.23.0 which works, but I just arbitrarily chose that. It may be worth explicitly setting the imageio version to one that works in the requirements.txt, since the latest version (2.33.1) will throw this error.