[FEATURE] add quant algo Learned Step Size Quantization

README.md

@@ -187,6 +187,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
+- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark.
 - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
 - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.
 - [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.

README_zh-CN.md

@@ -160,6 +160,7 @@ MMRazor 是一款由来自不同高校和企业的研发人员共同参与贡献
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
+- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO 系列工具箱与测试基准
 - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱
 - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具箱
 - [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱

configs/distill/mmcls/deit/README.md

@@ -0,0 +1,45 @@
+# DeiT
+
+> [](https://arxiv.org/abs/2012.12877)
+> Training data-efficient image transformers & distillation through attention
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption.   In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data.   More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/143225703-c287c29e-82c9-4c85-a366-dfae30d198cd.png" width="40%"/>
+</div>
+
+## Results and models
+
+### Classification
+
+| Dataset  | Model     | Teacher     | Top-1 (%) | Top-5 (%) | Configs                                          | Download                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| -------- | --------- | ----------- | --------- | --------- | ------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ImageNet | Deit-base | RegNety-160 | 83.24     | 96.33     | [config](deit-base_regnety160_pt-16xb64_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v1/deit/deit-base/deit-base_regnety160_pt-16xb64_in1k_20221011_113403-a67bf475.pth?versionId=CAEQThiBgMCFteW0oBgiIDdmMWY2NGRiOGY1YzRmZWZiOTExMzQ2NjNlMjk2Nzcz) \| [log](https://openmmlab-share.oss-cn-hangzhou.aliyuncs.com/mmrazor/v1/deit/deit-base/deit-base_regnety160_pt-16xb64_in1k_20221011_113403-a67bf475.json?versionId=CAEQThiBgIDGos20oBgiIGVlNDgyM2M2ZTk5MzQyYjFhNTgwNGIzMjllZjg3YmZm) |
+
+```{warning}
+Before training, please first install `timm`.
+
+pip install timm
+or
+git clone https://github.com/rwightman/pytorch-image-models
+cd pytorch-image-models && pip install -e .
+```
+
+## Citation
+
+```
+@InProceedings{pmlr-v139-touvron21a,
+  title =     {Training data-efficient image transformers &amp; distillation through attention},
+  author =    {Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jegou, Herve},
+  booktitle = {International Conference on Machine Learning},
+  pages =     {10347--10357},
+  year =      {2021},
+  volume =    {139},
+  month =     {July}
+}
+```

configs/distill/mmcls/deit/deit-base_regnety160_pt-16xb64_in1k.py

@@ -0,0 +1,64 @@
+_base_ = ['mmcls::deit/deit-base_pt-16xb64_in1k.py']
+
+# student settings
+student = _base_.model
+student.backbone.type = 'DistilledVisionTransformer'
+student.head = dict(
+    type='mmrazor.DeiTClsHead',
+    num_classes=1000,
+    in_channels=768,
+    loss=dict(
+        type='mmcls.LabelSmoothLoss',
+        label_smooth_val=0.1,
+        mode='original',
+        loss_weight=0.5))
+
+data_preprocessor = dict(
+    type='mmcls.ClsDataPreprocessor', batch_augments=student.train_cfg)
+
+# teacher settings
+checkpoint_path = 'https://dl.fbaipublicfiles.com/deit/regnety_160-a5fe301d.pth'  # noqa: E501
+teacher = dict(
+    _scope_='mmcls',
+    type='ImageClassifier',
+    backbone=dict(
+        type='TIMMBackbone', model_name='regnety_160', pretrained=True),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=3024,
+        loss=dict(
+            type='LabelSmoothLoss',
+            label_smooth_val=0.1,
+            mode='original',
+            loss_weight=0.5),
+        topk=(1, 5),
+        init_cfg=dict(
+            type='Pretrained', checkpoint=checkpoint_path, prefix='head.')))
+
+model = dict(
+    _scope_='mmrazor',
+    _delete_=True,
+    type='SingleTeacherDistill',
+    architecture=student,
+    teacher=teacher,
+    distiller=dict(
+        type='ConfigurableDistiller',
+        student_recorders=dict(
+            fc=dict(type='ModuleOutputs', source='head.layers.head_dist')),
+        teacher_recorders=dict(
+            fc=dict(type='ModuleOutputs', source='head.fc')),
+        distill_losses=dict(
+            loss_distill=dict(
+                type='CrossEntropyLoss',
+                loss_weight=0.5,
+            )),
+        loss_forward_mappings=dict(
+            loss_distill=dict(
+                preds_S=dict(from_student=True, recorder='fc'),
+                preds_T=dict(from_student=False, recorder='fc')))))
+
+find_unused_parameters = True
+
+val_cfg = dict(_delete_=True, type='mmrazor.SingleTeacherDistillValLoop')

configs/distill/mmcls/deit/metafile.yml

@@ -0,0 +1,34 @@
+Collections:
+  - Name: DEIT
+    Metadata:
+      Training Data:
+        - ImageNet-1k
+    Paper:
+      URL: https://arxiv.org/abs/2012.12877
+      Title: Training data-efficient image transformers & distillation through attention
+    README: configs/distill/mmcls/deit/README.md
+
+Models:
+  - Name: deit-base_regnety160_pt-16xb64_in1k
+    In Collection: DEIT
+    Metadata:
+      Student:
+        Config: mmcls::deit/deit-base_pt-16xb64_in1k.py
+        Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base_pt-16xb64_in1k_20220216-db63c16c.pth
+        Metrics:
+          Top 1 Accuracy: 81.76
+          Top 5 Accuracy: 95.81
+      Teacher:
+        Config: mmrazor::distill/mmcls/deit/deit-base_regnety160_pt-16xb64_in1k.py
+        Weights: https://dl.fbaipublicfiles.com/deit/regnety_160-a5fe301d.pth
+        Metrics:
+          Top 1 Accuracy: 82.83
+          Top 5 Accuracy: 96.42
+    Results:
+      - Task: Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.24
+          Top 5 Accuracy: 96.33
+    Weights: https://download.openmmlab.com/mmrazor/v1/deit/deit-base/deit-base_regnety160_pt-16xb64_in1k_20221011_113403-a67bf475.pth?versionId=CAEQThiBgMCFteW0oBgiIDdmMWY2NGRiOGY1YzRmZWZiOTExMzQ2NjNlMjk2Nzcz
+    Config: configs/distill/mmcls/deit/deit-base_regnety160_pt-16xb64_in1k.py

configs/distill/mmcls/kd/README.md

@@ -14,9 +14,11 @@ A very simple way to improve the performance of almost any machine learning algo
 
 ### Classification
 
-| Location | Dataset  |                                                   Teacher                                                    |                                                   Student                                                    |  Acc  | Acc(T) | Acc(S) |                          Config                           | Download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| :------: | :------: | :----------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :---: | :----: | :----: | :-------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-|  logits  | ImageNet | [resnet34](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet34_8xb32_in1k.py) | [resnet18](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet18_8xb32_in1k.py) | 71.54 | 73.62  | 69.90  | [config](./wsld_cls_head_resnet34_resnet18_8xb32_in1k.py) | [teacher](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) \|[model](https://openmmlab-share.oss-cn-hangzhou.aliyuncs.com/mmrazor/v0.1/distill/wsld/wsld_cls_head_resnet34_resnet18_8xb32_in1k/wsld_cls_head_resnet34_resnet18_8xb32_in1k_acc-71.54_20211222-91f28cf6.pth?versionId=CAEQHxiBgMC6memK7xciIGMzMDFlYTA4YzhlYTRiMTNiZWU0YTVhY2I5NjVkMjY2) \| [log](https://openmmlab-share.oss-cn-hangzhou.aliyuncs.com/mmrazor/v0.1/distill/wsld/wsld_cls_head_resnet34_resnet18_8xb32_in1k/wsld_cls_head_resnet34_resnet18_8xb32_in1k_20211221_181516.log.json?versionId=CAEQHxiBgIDLmemK7xciIGNkM2FiN2Y4N2E5YjRhNDE4NDVlNmExNDczZDIxN2E5) |
+| Location | Dataset  |                                                    Teacher                                                    |                                                              Student                                                               |  Acc  | Acc(T) | Acc(S) |                             Config                             | Download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| :------: | :------: | :-----------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------: | :---: | :----: | :----: | :------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+|  logits  | ImageNet | [resnet34](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/resnet/resnet34_8xb32_in1k.py) |           [resnet18](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/resnet/resnet18_8xb32_in1k.py)            | 71.81 | 73.62  | 69.90  |     [config](./kd_logits_resnet34_resnet18_8xb32_in1k.py)      | [teacher](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth) \|[model](https://download.openmmlab.com/mmrazor/v1/kd/kl_r18_w3/kd_logits_resnet34_resnet18_8xb32_in1k_w3_20221011_181115-5c6a834d.pth?versionId=CAEQThiBgID1_Me0oBgiIDE3NTk3MDgxZmU2YjRlMjVhMzg1ZTQwMmRhNmYyNGU2) \| [log](https://download.openmmlab.com/mmrazor/v1/kd/kl_r18_w3/kd_logits_resnet34_resnet18_8xb32_in1k_w3_20221011_181115-5c6a834d.json?versionId=CAEQThiBgMDx_se0oBgiIDQxNTM2MWZjZGRhNjRhZDZiZTIzY2Y0NDU3NDA4ODBl) |
+|  logits  | ImageNet | [resnet50](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/resnet/resnet50_8xb32_in1k.py) |    [mobilenet-v2](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/mobilenet_v2/mobilenet-v2_8xb32_in1k.py)     | 73.56 | 76.55  | 71.86  |   [config](./kd_logits_resnet50_mobilenet-v2_8xb32_in1k.py)    | [teacher](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) \|[model](https://download.openmmlab.com/mmrazor/v1/kd/kl_mbv2_w3t1/kd_logits_resnet50_mobilenet-v2_8xb32_in1k_20221025_212407-6ea9e2a5.pth) \| [log](https://download.openmmlab.com/mmrazor/v1/kd/kl_mbv2_w3t1/kd_logits_resnet50_mobilenet-v2_8xb32_in1k_20221025_212407-6ea9e2a5.json)                                                                                                                                               |
+|  logits  | ImageNet | [resnet50](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/resnet/resnet50_8xb32_in1k.py) | [shufflenet-v2](https://github.com/open-mmlab/mmclassification/blob/dev-1.x/configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py) | 70.87 | 76.55  | 69.55  | [config](./kd_logits_resnet50_shufflenet-v2-1x_16xb64_in1k.py) | [teacher](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) \|[model](https://download.openmmlab.com/mmrazor/v1/kd/kl_shuffle_w3t1/kd_logits_resnet50_shufflenet-v2-1x_16xb64_in1k_20221025_224424-5d748c1b.pth) \| [log](https://download.openmmlab.com/mmrazor/v1/kd/kl_shuffle_w3t1/kd_logits_resnet50_shufflenet-v2-1x_16xb64_in1k_20221025_224424-5d748c1b.json)                                                                                                                               |
 
 ## Citation
 

configs/distill/mmcls/kd/kd_logits_resnet34_resnet18_8xb32_in1k.py

@@ -4,6 +4,8 @@
     'mmcls::_base_/default_runtime.py'
 ]
 
+teacher_ckpt = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth'  # noqa: E501
+
 model = dict(
     _scope_='mmrazor',
     type='SingleTeacherDistill',
@@ -17,16 +19,16 @@
     architecture=dict(
         cfg_path='mmcls::resnet/resnet18_8xb32_in1k.py', pretrained=False),
     teacher=dict(
-        cfg_path='mmcls::resnet/resnet34_8xb32_in1k.py', pretrained=True),
-    teacher_ckpt='resnet34_8xb32_in1k_20210831-f257d4e6.pth',
+        cfg_path='mmcls::resnet/resnet34_8xb32_in1k.py', pretrained=False),
+    teacher_ckpt=teacher_ckpt,
     distiller=dict(
         type='ConfigurableDistiller',
         student_recorders=dict(
             fc=dict(type='ModuleOutputs', source='head.fc')),
         teacher_recorders=dict(
             fc=dict(type='ModuleOutputs', source='head.fc')),
         distill_losses=dict(
-            loss_kl=dict(type='KLDivergence', tau=1, loss_weight=5)),
+            loss_kl=dict(type='KLDivergence', tau=1, loss_weight=3)),
         loss_forward_mappings=dict(
             loss_kl=dict(
                 preds_S=dict(from_student=True, recorder='fc'),

configs/distill/mmcls/kd/kd_logits_resnet50_mobilenet-v2_8xb32_in1k.py

@@ -0,0 +1,37 @@
+_base_ = ['mmcls::mobilenet_v2/mobilenet-v2_8xb32_in1k.py']
+
+student = _base_.model
+
+teacher_ckpt = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth'  # noqa: E501
+
+model = dict(
+    _scope_='mmrazor',
+    _delete_=True,
+    type='SingleTeacherDistill',
+    data_preprocessor=dict(
+        type='ImgDataPreprocessor',
+        # RGB format normalization parameters
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        # convert image from BGR to RGB
+        bgr_to_rgb=True),
+    architecture=student,
+    teacher=dict(
+        cfg_path='mmcls::resnet/resnet50_8xb32_in1k.py', pretrained=False),
+    teacher_ckpt=teacher_ckpt,
+    distiller=dict(
+        type='ConfigurableDistiller',
+        student_recorders=dict(
+            fc=dict(type='ModuleOutputs', source='head.fc')),
+        teacher_recorders=dict(
+            fc=dict(type='ModuleOutputs', source='head.fc')),
+        distill_losses=dict(
+            loss_kl=dict(type='KLDivergence', tau=1, loss_weight=3)),
+        loss_forward_mappings=dict(
+            loss_kl=dict(
+                preds_S=dict(from_student=True, recorder='fc'),
+                preds_T=dict(from_student=False, recorder='fc')))))
+
+find_unused_parameters = True
+
+val_cfg = dict(_delete_=True, type='mmrazor.SingleTeacherDistillValLoop')