Upload 13 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/description/demo_result.jpg filter=lfs diff=lfs merge=lfs -text
+AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/description/m2fp_arch.png filter=lfs diff=lfs merge=lfs -text
+AfsHumanParsing/ahp_ckpts/sapiens_1b_goliath_best_goliath_mIoU_7994_epoch_151_torchscript.pt2 filter=lfs diff=lfs merge=lfs -text

AfsHumanParsing/ahp_ckpts/RealESRGAN_x4plus.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1
+size 67040989

AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/.mv

@@ -0,0 +1 @@
+Revision:v1.0.1,CreatedAt:1676291246

AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/README.md

@@ -0,0 +1,131 @@
+---
+tasks:
+- image-segmentation
+widgets:
+  - task: image-segmentation
+    inputs:
+      - type: image
+    examples:
+      - name: 1
+        title: 示例1
+        inputs:
+          - data: git://description/demo.jpg
+      - name: 2
+        title: 示例2
+        inputs:
+          - data: git://description/demo2.jpg
+    inferencespec:
+      cpu: 4
+      memory: 8000
+      gpu: 1
+      gpu_memory: 16000
+model-type:
+- m2fp
+domain:
+- cv
+frameworks:
+- pytorch
+backbone:
+- ResNet-101
+metrics:
+- mIoU
+- APr
+customized-quickstart: True
+finetune-support: False
+license: Other
+tags:
+- Alibaba
+- multiple human parsing
+- M2FP
+datasets:
+  train:
+  - modelscope/CIHP
+  evaluation:
+  - modelscope/CIHP
+---
+
+# M2FP多人人体解析模型介绍
+
+## 模型描述
+
+M2FP（Mask2Former for Parsing，[官方代码](https://github.com/soeaver/M2FP)）基于 Mask2Former 架构，并进行了一些改进以适应人体解析。 M2FP 可以适应几乎所有人体解析任务并产生惊人的性能。
+
+模型整体架构图如下：
+
+![M2FP模型结构](description/m2fp_arch.png)
+
+## 期望模型使用方式以及适用范围
+
+本模型适用于包含多个人体的图像，对图片中的人体各组件进行解析、分割。
+
+### 如何使用
+
+在ModelScope框架上，提供输入图片，即可通过简单的Pipeline调用来使用。
+
+#### 代码范例
+```python
+from modelscope.outputs import OutputKeys
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+input_img = 'https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/mog_face_detection.jpg'
+segmentation_pipeline = pipeline(Tasks.image_segmentation, 'damo/cv_resnet101_image-multiple-human-parsing')
+result = segmentation_pipeline(input_img)
+print(result[OutputKeys.LABELS])
+```
+
+### 模型局限性以及可能的偏差
+
+- 部分非常规图片或人体占比太小或遮挡严重可能会影响分割结果
+- 本模型依赖mmcv-full，需用户在机器上正确安装[mmcv-full](https://mmcv.readthedocs.io/en/latest/get_started/installation.html)
+- 部分代码依赖CC BY-NC 4.0 license，不支持商用
+
+## 训练数据介绍
+
+- CIHP，大规模多人人体解析数据集，[官方地址](https://lip.sysuhcp.com/overview.php)。
+
+## 模型训练流程
+
+- 请参考原论文
+
+## 数据评估及结果
+
+模型在CIHP验证集上进行评估，结果如下:
+
+|  Backbone  |  Pretrain   | Epochs | mIoU  |  APr  | #params | FLOPs  | 
+|:----------:|:-----------:|:------:|:-----:|:-----:|:-------:|:------:|
+| ResNet-101 | ImageNet-1k |  150   | 69.15 | 60.47 |  63.0M  | 206.2G |
+
+注：测试时使用了 TTA（Test Time Augmentation）数据增强
+
+可视化结果：
+
+![source](description/demo.jpg)  ![result](description/demo_result.jpg)
+
+## 引用
+如果你觉得该模型对你有所帮助，请考虑引用下面的相关论文：
+
+```BibTeX
+@article{yang2023humanparsing,
+  title={Deep Learning Technique for Human Parsing: A Survey and Outlook},
+  author={Lu Yang and Wenhe Jia and Shan Li and Qing Song},
+  journal={arXiv preprint arXiv:2301.00394},
+  year={2023}
+}
+```
+```BibTeX
+@inproceedings{cheng2021mask2former,
+  title={Masked-attention Mask Transformer for Universal Image Segmentation},
+  author={Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar},
+  journal={CVPR},
+  year={2021}
+}
+```
+```BibTeX
+@inproceedings{cheng2021maskformer,
+  title={Per-Pixel Classification is Not All You Need for Semantic Segmentation},
+  author={Bowen Cheng and Alexander G. Schwing and Alexander Kirillov},
+  journal={NeurIPS},
+  year={2021}
+}
+```

AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/configuration.json

@@ -0,0 +1,97 @@
+{
+    "framework": "pytorch",
+
+    "task": "image-segmentation",
+
+     "pipeline": {
+       "type": "m2fp-image-human-parsing"
+    },
+
+    "model": {
+        "type": "m2fp",
+        "pretrained": true,
+        "parsing_ins_score_thr": 0.3,
+        "parsing_on": true,
+        "semantic_on": false,
+        "sem_seg_postprocess_before_inference": false,
+        "single_human": false,
+        "with_human_instance": true,
+        "num_parsing": 20,
+        "backbone": {
+            "depth": 101,
+            "norm": "BN",
+            "num_groups": 1,
+            "out_features": [
+                "res2",
+                "res3",
+                "res4",
+                "res5"
+            ],
+            "res2_out_channels": 256,
+            "res4_dilation": 1,
+            "res5_dilation": 1,
+            "res5_multi_grid": [
+                1,
+                1,
+                1
+            ],
+            "stem_out_channels": 128,
+            "stride_in_1x1": false,
+            "width_per_group": 64
+        },
+        "encoder": {
+            "common_stride": 4,
+            "conv_dim": 256,
+            "in_features": [
+                "res2",
+                "res3",
+                "res4",
+                "res5"
+            ],
+            "transformer_in_features": [
+                "res3",
+                "res4",
+                "res5"
+            ],
+            "transformer_dim_feedforward": 1024,
+            "mask_dim": 256,
+            "transformer_enc_layers": 6,
+            "transformer_nheads": 8,
+            "transformer_dropout": 0
+        },
+        "decoder": {
+            "num_classes": 21,
+            "hidden_dim": 256,
+            "num_queries": 100,
+            "nheads": 8,
+            "dim_feedforward": 2048,
+            "dec_layers": 9,
+            "pre_norm": false,
+            "enforce_input_project": false,
+            "mask_dim": 256
+        },
+        "classes": [
+            "Background",
+            "Hat",
+            "Hair",
+            "Gloves",
+            "Sunglasses",
+            "UpperClothes",
+            "Dress",
+            "Coat",
+            "Socks",
+            "Pants",
+            "Torso-skin",
+            "Scarf",
+            "Skirt",
+            "Face",
+            "Left-arm",
+            "Right-arm",
+            "Left-leg",
+            "Right-leg",
+            "Left-shoe",
+            "Right-shoe",
+            "Human"
+        ]
+    }
+}

AfsHumanParsing/ahp_ckpts/cv_resnet101_image-multiple-human-parsing/pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7451e822298c8dee3781444ebd490bc43f192ca135b66ada841f16245746bad1
+size 757764792

AfsHumanParsing/ahp_ckpts/sapiens_1b_goliath_best_goliath_mIoU_7994_epoch_151_torchscript.pt2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bba30f3de8d9cfd44e4eaa4817b1bfdd98c188edfc87fa7cc031ba0f4edc17
+size 4716314057

AfsHumanParsing/ahp_ckpts/yolov8x.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d5a3f000d771762f03fc8b57ebd0aae324aeaefdd6e68492a9c4470f2d1e8b
+size 136867539