pswena
commented
2 years ago 这是我的配置情况： [05/24 00:48:29] fastreid INFO: Rank of current process: 0. World size: 4 [05/24 00:48:31] fastreid INFO: Environment info:
sys.platform linux
Python 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]
numpy 1.21.2
fastreid 1.3 @./fastreid
FASTREID_ENV_MODULE
PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.3
- 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_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
- CuDNN 8.2
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -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-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -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 -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON,
[05/24 00:48:31] fastreid INFO: Command line arguments: Namespace(config_file='./configs/VehicleID/bagtricks_R50-ibn.yml', dist_url='tcp://127.0.0.1:49152', eval_only=False, machine_rank=0, num_gpus=4, num_machines=1, opts=[], resume=False) [05/24 00:48:31] fastreid INFO: Contents of args.config_file=./configs/VehicleID/bagtricks_R50-ibn.yml: BASE: ../Base-bagtricks.yml
INPUT: SIZE_TRAIN: [256, 256] SIZE_TEST: [256, 256]
MODEL: BACKBONE: WITH_IBN: True HEADS: POOL_LAYER: GeneralizedMeanPooling
LOSSES: TRI: HARD_MINING: False MARGIN: 0.0
DATASETS: NAMES: ("VehicleID",) TESTS: ("SmallVehicleID", "MediumVehicleID", "LargeVehicleID",)
SOLVER: BIAS_LR_FACTOR: 1.
IMS_PER_BATCH: 512 MAX_EPOCH: 60 STEPS: [30, 50] WARMUP_ITERS: 2000
CHECKPOINT_PERIOD: 20
TEST: EVAL_PERIOD: 20 IMS_PER_BATCH: 128
OUTPUT_DIR: logs/vehicleid/bagtricks_R50-ibn_4gpu-lr35-openai523
[05/24 00:48:31] fastreid INFO: Running with full config: CUDNN_BENCHMARK: True DATALOADER: NUM_INSTANCE: 4 NUM_WORKERS: 8 SAMPLER_TRAIN: NaiveIdentitySampler SET_WEIGHT: [] DATASETS: COMBINEALL: False NAMES: ('VehicleID',) TESTS: ('SmallVehicleID', 'MediumVehicleID', 'LargeVehicleID') INPUT: AFFINE: ENABLED: False AUGMIX: ENABLED: False PROB: 0.0 AUTOAUG: ENABLED: False PROB: 0.0 CJ: BRIGHTNESS: 0.15 CONTRAST: 0.15 ENABLED: False HUE: 0.1 PROB: 0.5 SATURATION: 0.1 CROP: ENABLED: False RATIO: [0.75, 1.3333333333333333] SCALE: [0.16, 1] SIZE: [224, 224] FLIP: ENABLED: True PROB: 0.5 PADDING: ENABLED: True MODE: constant SIZE: 10 REA: ENABLED: True PROB: 0.5 VALUE: [123.675, 116.28, 103.53] RPT: ENABLED: False PROB: 0.5 SIZE_TEST: [256, 256] SIZE_TRAIN: [256, 256] KD: EMA: ENABLED: False MOMENTUM: 0.999 MODEL_CONFIG: [] MODEL_WEIGHTS: [] MODEL: BACKBONE: ATT_DROP_RATE: 0.0 DEPTH: 50x DROP_PATH_RATIO: 0.1 DROP_RATIO: 0.0 FEAT_DIM: 2048 LAST_STRIDE: 1 NAME: build_resnet_backbone NORM: BN PRETRAIN: True PRETRAIN_PATH: ./resnet50_ibn_a-d9d0bb7b.pth SIE_COE: 3.0 STRIDE_SIZE: (16, 16) WITH_IBN: True WITH_NL: False WITH_SE: False DEVICE: cuda FREEZE_LAYERS: [] HEADS: CLS_LAYER: Linear EMBEDDING_DIM: 0 MARGIN: 0.0 NAME: EmbeddingHead NECK_FEAT: before NORM: BN NUM_CLASSES: 0 POOL_LAYER: GeneralizedMeanPooling SCALE: 1 WITH_BNNECK: True LOSSES: CE: ALPHA: 0.2 EPSILON: 0.1 SCALE: 1.0 CIRCLE: GAMMA: 128 MARGIN: 0.25 SCALE: 1.0 COSFACE: GAMMA: 128 MARGIN: 0.25 SCALE: 1.0 FL: ALPHA: 0.25 GAMMA: 2 SCALE: 1.0 NAME: ('CrossEntropyLoss', 'TripletLoss') TRI: HARD_MINING: False MARGIN: 0.0 NORM_FEAT: False SCALE: 1.0 META_ARCHITECTURE: Baseline PIXEL_MEAN: [123.675, 116.28, 103.53] PIXEL_STD: [58.395, 57.120000000000005, 57.375] QUEUE_SIZE: 8192 WEIGHTS: OUTPUT_DIR: logs/vehicleid/bagtricks_R50-ibn_4gpu-lr35-openai523 SOLVER: AMP: ENABLED: True BASE_LR: 0.00035 BIAS_LR_FACTOR: 1.0 CHECKPOINT_PERIOD: 20 CLIP_GRADIENTS: CLIP_TYPE: norm CLIP_VALUE: 5.0 ENABLED: False NORM_TYPE: 2.0 DELAY_EPOCHS: 0 ETA_MIN_LR: 1e-07 FREEZE_ITERS: 0 GAMMA: 0.1 HEADS_LR_FACTOR: 1.0 IMS_PER_BATCH: 512 MAX_EPOCH: 60 MOMENTUM: 0.9 NESTEROV: False OPT: Adam SCHED: MultiStepLR STEPS: [30, 50] WARMUP_FACTOR: 0.1 WARMUP_ITERS: 2000 WARMUP_METHOD: linear WEIGHT_DECAY: 0.0005 WEIGHT_DECAY_BIAS: 0.0005 WEIGHT_DECAY_NORM: 0.0005 TEST: AQE: ALPHA: 3.0 ENABLED: False QE_K: 5 QE_TIME: 1 EVAL_PERIOD: 20 FLIP: ENABLED: False IMS_PER_BATCH: 128 METRIC: cosine PRECISE_BN: DATASET: Market1501 ENABLED: False NUM_ITER: 300 RERANK: ENABLED: False K1: 20 K2: 6 LAMBDA: 0.3 ROC: ENABLED: False
这是bagtricks_R50-ibn.yml的配置文件：
github-actions[bot]
我是用4张A4000去跑的VehicleID数据集，配置和你中的一样。但是最终结果差距挺大：