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/fastreid/layers/__init__.py

20 lines
517 B
Python
Raw Normal View History

Update sampler code
2020-02-10 07:38:56 +08:00
# encoding: utf-8
"""
@author: liaoxingyu
@contact: sherlockliao01@gmail.com
"""
update fast global avgpool Summary: update fast pool according to https://arxiv.org/pdf/2003.13630.pdf
2020-06-12 16:34:03 +08:00
from .activation import *
support regnet backbone
2020-07-17 19:13:45 +08:00
from .arc_softmax import ArcSoftmax
onnx/trt support Summary: change model pretrain mode and support onnx/TensorRT export
2020-07-29 17:43:39 +08:00
from .circle_softmax import CircleSoftmax
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
from .cos_softmax import CosSoftmax
Update sampler code
2020-02-10 07:38:56 +08:00
from .batch_drop import BatchDrop
feat: add SyncBN and GroupNorm suppor
2020-05-14 11:36:28 +08:00
from .batch_norm import *
update version0.2 code
2020-03-25 10:58:26 +08:00
from .context_block import ContextBlock
update fast global avgpool Summary: update fast pool according to https://arxiv.org/pdf/2003.13630.pdf
2020-06-12 16:34:03 +08:00
from .frn import FRN, TLU
refactor(fastreid) refactor architecture
2020-04-20 10:59:29 +08:00
from .non_local import Non_local
update fast global avgpool Summary: update fast pool according to https://arxiv.org/pdf/2003.13630.pdf
2020-06-12 16:34:03 +08:00
from .pooling import *
refactor(fastreid) refactor architecture
2020-04-20 10:59:29 +08:00
from .se_layer import SELayer
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
from .splat import SplAtConv2d, DropBlock2D
fix triplet loss backward propagation on multi-gpu training (#82) Summary: fix torch.distributed.all_gather has no gradient when performing all_gather operation on the provided tensors, instead using `GatherLayer`.
2020-09-28 17:16:51 +08:00
from .gather_layer import GatherLayer