Duplicate from ototadana/occlusion-aware-face-segmentation

Co-authored-by: Otota DANA <ototadana@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,35 @@
+---
+license: cc0-1.0
+pipeline_tag: image-segmentation
+tags:
+- mmsegmentation
+- face
+- occlusion
+---
+
+# Occlusion-aware face segmentation
+A model for occlusion-aware face segmentation.
+
+This model was created following the procedures in [mmsegmentation](https://mmsegmentation.readthedocs.io/en/latest/)'s PR [[Feature] Support Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets #2194](https://github.com/open-mmlab/mmsegmentation/pull/2194).
+
+For more information, see: 
+- https://github.com/open-mmlab/mmsegmentation/pull/2194/files
+- https://github.com/kennyvoo/face-occlusion-generation
+
+### How to use
+Use with [mmsegmentation](https://mmsegmentation.readthedocs.io/en/latest/get_started.html).
+
+Example:
+
+```python
+from mmseg.apis import inference_model, init_model, show_result_pyplot
+import mmcv
+
+config_file = 'deeplabv3plus_r101_512x512_face-occlusion.py'
+checkpoint_file = 'deeplabv3plus_r101_512x512_face-occlusion-93ec6695.pth'
+model = init_model(config_file, checkpoint_file, device='cuda:0')
+
+img = 'face-image.png'
+result = inference_model(model, img)
+show_result_pyplot(model, img, result, show=True, out_file='result.jpg', opacity=0.5)
+```

deeplabv3plus_r101_512x512_face-occlusion-93ec6695.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee938da54fe72f34916ec1456192c81efe40e846c03ad0a78cb460a3420f6a0
+size 251071621

deeplabv3plus_r101_512x512_face-occlusion.py

@@ -0,0 +1,84 @@
+norm_cfg = dict(type="SyncBN", requires_grad=True)
+
+data_preprocessor = dict(
+    bgr_to_rgb=True,
+    mean=[123.675, 116.28, 103.53],
+    pad_val=0,
+    seg_pad_val=255,
+    size=(512, 512),
+    std=[58.395, 57.12, 57.375],
+    type="SegDataPreProcessor",
+)
+
+test_pipeline = [
+    dict(type="LoadImageFromNDArray"),
+    dict(type="Resize", scale=(512, 512), keep_ratio=True),
+    dict(type="LoadAnnotations", reduce_zero_label=True),
+    dict(type="PackSegInputs"),
+]
+
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_model = dict(type="SegTTAModel")
+tta_pipeline = [
+    dict(type="LoadImageFromNDArray", backend_args=None),
+    dict(
+        type="TestTimeAug",
+        transforms=[
+            [dict(type="Resize", scale_factor=r, keep_ratio=True) for r in img_ratios],
+            [
+                dict(type="RandomFlip", prob=0.0, direction="horizontal"),
+                dict(type="RandomFlip", prob=1.0, direction="horizontal"),
+            ],
+            [dict(type="LoadAnnotations")],
+            [dict(type="PackSegInputs")],
+        ],
+    ),
+]
+
+model = dict(
+    type="EncoderDecoder",
+    data_preprocessor=data_preprocessor,
+    pretrained="open-mmlab://resnet101_v1c",
+    backbone=dict(
+        type="ResNetV1c",
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style="pytorch",
+        contract_dilation=True,
+    ),
+    decode_head=dict(
+        type="DepthwiseSeparableASPPHead",
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=256,
+        c1_channels=48,
+        dropout_ratio=0.1,
+        num_classes=2,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0),
+        sampler=dict(type="OHEMPixelSampler", thresh=0.7, min_kept=10000),
+    ),
+    auxiliary_head=dict(
+        type="FCNHead",
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=2,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(type="CrossEntropyLoss", use_sigmoid=False, loss_weight=0.4),
+    ),
+    train_cfg=dict(),
+    test_cfg=dict(mode="whole"),
+)