EasyCV/easycv/models/loss/__init__.py

# Copyright (c) Alibaba, Inc. and its affiliates.
from .cross_entropy_loss import CrossEntropyLoss
from .focal_loss import FocalLoss, VarifocalLoss
from .iou_loss import GIoULoss, IoULoss, YOLOX_IOULoss
from .mse_loss import JointsMSELoss
from .pytorch_metric_learning import *
from .set_criterion import (CDNCriterion, DNCriterion, HungarianMatcher,
                            SetCriterion)
initial commit 2022-04-02 20:01:06 +08:00			`# Copyright (c) Alibaba, Inc. and its affiliates.`
[feature] add segmentation modules (#71) * add segmentation module & add ResNetV1c & ResNetV1d & add benchmark 2022-05-31 20:19:17 +08:00			`from .cross_entropy_loss import CrossEntropyLoss`
Yolox improve with REPConv/ASFF/TOOD (#154) * add attention layer and more loss function * add attention layer and various loss functions * add siou loss * add tah,various attention layers, and different loss functions * add asff sim, gsconv * blade utils fit faster * blade optimize for yolox static & fp16 * decode output for yolox control by cfg * add reparameterize_models for export * e2e trt_nms plugin export support and numeric test * split preprocess from end2end+blade, speedup from 17ms->7.2ms Co-authored-by: zouxinyi0625 <zouxinyi.zxy@alibaba-inc.com> 2022-08-24 18:11:15 +08:00			`from .focal_loss import FocalLoss, VarifocalLoss`
			`from .iou_loss import GIoULoss, IoULoss, YOLOX_IOULoss`
initial commit 2022-04-02 20:01:06 +08:00			`from .mse_loss import JointsMSELoss`
			`from .pytorch_metric_learning import *`
support DINO algo (#144) dino_4sc_r50_12e：48.71 dino_4sc_r50_24e：50.53 dino_4sc_r50_36e：50.69 dino_4sc_swinl_12e: 56.86 dino_4sc_swinl_36e: 58.04 dino_5sc_swinl_36e: 58.47 2022-08-31 15:18:11 +08:00			`from .set_criterion import (CDNCriterion, DNCriterion, HungarianMatcher,`
			`SetCriterion)`