mirrors
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
fast-reid/configs/Base-SBS.yml

63 lines
926 B
YAML
Raw Normal View History

update all config files
2020-07-06 16:48:14 +08:00
_BASE_: "Base-bagtricks.yml"
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
update all config files
2020-07-06 16:48:14 +08:00
MODEL:
FREEZE_LAYERS: ["backbone"]
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
BACKBONE:
chore(configs): update Market1501 training config
2020-04-29 21:06:57 +08:00
WITH_NL: True
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
HEADS:
chore(configs): update all training config
2020-05-01 09:04:51 +08:00
NECK_FEAT: "after"
change config file
2020-09-10 10:58:56 +08:00
POOL_LAYER: "gempoolP"
onnx/trt support Summary: change model pretrain mode and support onnx/TensorRT export
2020-07-29 17:43:39 +08:00
CLS_LAYER: "circleSoftmax"
chore(configs): update all training config
2020-05-01 09:04:51 +08:00
SCALE: 64
MARGIN: 0.35
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
LOSSES:
NAME: ("CrossEntropyLoss", "TripletLoss",)
CE:
EPSILON: 0.1
SCALE: 1.0
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
TRI:
MARGIN: 0.0
HARD_MINING: True
NORM_FEAT: False
SCALE: 1.0
INPUT:
SIZE_TRAIN: [384, 128]
SIZE_TEST: [384, 128]
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
DO_AUTOAUG: True
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
AUTOAUG_PROB: 0.1
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
DATALOADER:
NUM_INSTANCE: 16
SOLVER:
OPT: "Adam"
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
MAX_EPOCH: 60
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
BASE_LR: 0.00035
fix: change config of sbs change weight decay and bias_lr in config of SBS, which can boost performance slightly.
2020-05-18 20:16:38 +08:00
BIAS_LR_FACTOR: 1.
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
WEIGHT_DECAY: 0.0005
fix: change config of sbs change weight decay and bias_lr in config of SBS, which can boost performance slightly.
2020-05-18 20:16:38 +08:00
WEIGHT_DECAY_BIAS: 0.0005
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
IMS_PER_BATCH: 64
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
SCHED: "CosineAnnealingLR"
DELAY_EPOCHS: 30
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
ETA_MIN_LR: 0.00000077
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
WARMUP_FACTOR: 0.1
WARMUP_ITERS: 2000
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
FREEZE_ITERS: 2000
CHECKPOINT_PERIOD: 20
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
TEST:
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file
2020-12-07 14:19:20 +08:00
EVAL_PERIOD: 20
update all config files
2020-07-06 16:48:14 +08:00
IMS_PER_BATCH: 128
style(configs): put all config files together put all config files into one place for easily control, and add tools for put train_net.py which almost the same in different projects
2020-04-29 16:18:54 +08:00
CUDNN_BENCHMARK: True