A comprehensive list [SAMRS@NeurIPS'23, RVSA@TGRS'22, RSP@TGRS'22] of our research works related to remote sensing, including papers, codes, and citations. Note: The repo for [TGRS'22] "An Empirical Study of Remote Sensing Pretraining" has been moved to: https://github.com/ViTAE-Transformer/RSP
438
stars
53
forks
source link
reproduce problem about swin-t in scene classification. #24
Hi, I try to follow your hyperparameters to reproduce the classification results in misclassification, but I train aid (2:8) using max_epochs=200, base_lr=5e-4, and other settings following:
base = [
@Leiyi-Hu We use MAE, not SimMIM. In addition, our classification experiments does not use mmclassification. We have provided corresponding codes. You should reproduce with our codes.
Hi, I try to follow your hyperparameters to reproduce the classification results in misclassification, but I train aid (2:8) using max_epochs=200, base_lr=5e-4, and other settings following: base = [
'../base/models/swin_transformer/base_224.py',
]
refer to SimMIM paper
ADJUST_FACTOR = 1.0 BATCH_SIZE = 64 BASE_LR = 5e-4 ADJUST_FACTOR # todo: adjust. WARMUP_LR = 5e-7 ADJUST_FACTOR MIN_LR = 5e-6 * ADJUST_FACTOR NUM_GPUS = 1 DROP_PATH_RATE = 0.2 SCALE_FACTOR = 512.0 MAX_EPOCHS = 200
model settings
model = dict( type="ImageClassifier", backbone=dict( type="SwinTransformer",
arch="base",
)
optimizer
paramwise_cfg = dict( norm_decay_mult=0.0, bias_decay_mult=0.0, custom_keys={ ".absolute_pos_embed": dict(decay_mult=0.0), ".relative_position_bias_table": dict(decay_mult=0.0), }, )
optimizer = dict( type="AdamW",
lr=1e-3 64 / 256, # 5e-4 64 / 512, # 1e-3 * 64 / 256,
) optimizer_config = dict(grad_clip=dict(max_norm=5.0))
learning policy
lr_config = dict( policy="CosineAnnealing",
min_lr=2.5e-7,
)
checkpoint_config = dict(interval=MAX_EPOCHS // 10) evaluation = dict( interval=MAX_EPOCHS // 10, metric="accuracy", save_best="auto" ) # save the checkpoint with highest accuracy runner = dict(type="EpochBasedRunner", max_epochs=MAX_EPOCHS)
data = dict(samples_per_gpu=96, workers_per_gpu=8,)
data = dict(samples_per_gpu=BATCH_SIZE, workers_per_gpu=8,)
fp16 settings
fp16 = dict(loss_scale="dynamic")
so could you help me with this? or provide your training log? Thanks!