init from [zkkli/RepQ-ViT]

Author: jiho264

.gitignore

@@ -0,0 +1,4 @@
+**/**.pth
+**/**.pt
+**/**.pyc
+data/

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,52 @@
+## RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
+
+Below are instructions for reproducing the classification results of RepQ-ViT.
+
+## Evaluation
+
+- You can quantize and evaluate a single model using the following command:
+
+```bash
+python test_quant.py [--model] [--dataset] [--w_bit] [--a_bit]
+
+optional arguments:
+--model: Model architecture, the choises can be: 
+    vit_small, vit_base, deit_tiny, deit_small, deit_base, swin_tiny, swin_small.
+--dataset: Path to ImageNet dataset.
+--w_bit: Bit-precision of weights, default=4.
+--a_bit: Bit-precision of activation, default=4.
+```
+
+- Example: Quantize *DeiT-S* at W4/A4 precision:
+
+```bash
+python test_quant.py --model deit_small --dataset <YOUR_DATA_DIR>
+```
+
+## Results
+
+Below are the experimental results of our proposed RepQ-ViT that you should get on ImageNet dataset.
+
+|     Model      | Prec. | Top-1(%) | Prec. | Top-1(%) |
+| :------------: | :---: | :------: | :---: | :------: |
+| ViT-S (81.39)  | W4/A4 |  65.05   | W6/A6 |  80.43   |
+| ViT-B (84.54)  | W4/A4 |  68.48   | W6/A6 |  83.62   |
+| DeiT-T (72.21) | W4/A4 |  57.43   | W6/A6 |  70.76   |
+| DeiT-S (79.85) | W4/A4 |  69.03   | W6/A6 |  78.90   |
+| DeiT-B (81.80) | W4/A4 |  75.61   | W6/A6 |  81.27   |
+| Swin-T (81.35) | W4/A4 |  72.31   | W6/A6 |  80.69   |
+| Swin-S (83.23) | W4/A4 |  79.45   | W6/A6 |  82.79   |
+
+## Citation
+
+We appreciate it if you would please cite the following paper if you found the implementation useful for your work:
+
+```bash
+@inproceedings{li2023repq,
+  title={Repq-vit: Scale reparameterization for post-training quantization of vision transformers},
+  author={Li, Zhikai and Xiao, Junrui and Yang, Lianwei and Gu, Qingyi},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={17227--17236},
+  year={2023}
+}
+```

classification/quant/__init__.py

@@ -0,0 +1,3 @@
+from .quant_model import *
+from .quant_modules import *
+from .quantizer import *

classification/quant/quant_model.py

@@ -0,0 +1,83 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from utils.build_model import MatMul
+from .quant_modules import QuantConv2d, QuantLinear, QuantMatMul
+from copy import deepcopy
+
+
+def quant_model(model, input_quant_params={}, weight_quant_params={}):
+    # post-softmax
+    input_quant_params_matmul2 = deepcopy(input_quant_params)
+    input_quant_params_matmul2["log_quant"] = True
+
+    # SimQuant
+    input_quant_params_channel = deepcopy(input_quant_params)
+    input_quant_params_channel["channel_wise"] = True
+
+    module_dict = {}
+    for name, m in model.named_modules():
+        module_dict[name] = m
+        idx = name.rfind(".")
+        if idx == -1:
+            idx = 0
+        father_name = name[:idx]
+        if father_name in module_dict:
+            father_module = module_dict[father_name]
+        else:
+            raise RuntimeError(f"father module {father_name} not found")
+
+        if isinstance(m, nn.Conv2d):
+            # Embedding Layer
+            idx = idx + 1 if idx != 0 else idx
+            new_m = QuantConv2d(
+                m.in_channels,
+                m.out_channels,
+                m.kernel_size,
+                m.stride,
+                m.padding,
+                m.dilation,
+                m.groups,
+                m.bias is not None,
+                input_quant_params,
+                weight_quant_params,
+            )
+            new_m.weight.data = m.weight.data
+            new_m.bias = m.bias
+            setattr(father_module, name[idx:], new_m)
+        elif isinstance(m, nn.Linear):
+            # Linear Layer
+            idx = idx + 1 if idx != 0 else idx
+            if "qkv" in name or "fc1" in name or "reduction" in name:
+                new_m = QuantLinear(
+                    m.in_features,
+                    m.out_features,
+                    input_quant_params_channel,
+                    weight_quant_params,
+                )
+            else:
+                new_m = QuantLinear(
+                    m.in_features,
+                    m.out_features,
+                    input_quant_params,
+                    weight_quant_params,
+                )
+            new_m.weight.data = m.weight.data
+            new_m.bias = m.bias
+            setattr(father_module, name[idx:], new_m)
+        elif isinstance(m, MatMul):
+            # Matmul Layer
+            idx = idx + 1 if idx != 0 else idx
+            if "matmul2" in name:
+                new_m = QuantMatMul(input_quant_params_matmul2)
+            else:
+                new_m = QuantMatMul(input_quant_params)
+            setattr(father_module, name[idx:], new_m)
+
+    return model
+
+
+def set_quant_state(model, input_quant=False, weight_quant=False):
+    for m in model.modules():
+        if isinstance(m, (QuantConv2d, QuantLinear, QuantMatMul)):
+            m.set_quant_state(input_quant, weight_quant)