Duplicate from zenes/SemanticImageSegmentation

Co-authored-by: Ilya Dudnikov <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,14 @@
+---
+title: SemanticImageSegmentation
+emoji: 🐨
+colorFrom: red
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.15.2
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: zenes/SemanticImageSegmentation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,5 @@
+import streamlit_config as st
+
+if __name__ == "__main__":
+    st.init()
+    st.run()

requirements.txt

@@ -0,0 +1,7 @@
+numpy==1.21.5
+Pillow==9.3.0
+requests==2.28.1
+seaborn==0.11.2
+streamlit==1.15.2
+torch==1.13.0
+transformers==4.25.1

segmentation.py

@@ -0,0 +1,44 @@
+from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
+from transformers.modeling_outputs import SemanticSegmenterOutput
+from transformers.feature_extraction_utils import BatchFeature
+from PIL import Image
+import torch
+import torch.nn.functional as F
+import numpy as np
+import seaborn as sns
+import itertools
+
+
+def create_model():
+    return SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
+
+
+def create_feature_extractor():
+    return SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
+
+
+def postprocess(masks, height, width):
+    masks = F.interpolate(masks, (height, width))
+
+    label_per_pixel = torch.argmax(
+        masks.squeeze(), dim=0).detach().numpy()
+    color_mask = np.zeros(label_per_pixel.shape + (3,))
+    palette = itertools.cycle(sns.color_palette())
+
+    for lbl in np.unique(label_per_pixel):
+        color_mask[label_per_pixel == lbl, :] = np.asarray(next(palette)) * 255
+
+    return color_mask
+
+
+def segment(image: Image, model, feature_extractor) -> torch.Tensor:
+    inputs = feature_extractor(
+        images=image, return_tensors="pt")
+    outputs = model(**inputs)
+    masks = outputs.logits
+
+    color_mask = postprocess(masks, image.height, image.width)
+    pred_img = np.array(image.convert('RGB')) * 0.25 + color_mask * 0.75
+    pred_img = pred_img.astype(np.uint8)
+
+    return pred_img

streamlit_config.py

@@ -0,0 +1,66 @@
+import streamlit as st
+from PIL import Image
+import re
+from io import BytesIO
+
+import segmentation
+
+
+def init():
+    st.set_page_config(page_title="Semantic image segmentation")
+    st.session_state["model"] = segmentation.create_model()
+    st.session_state["feature_extractor"] = segmentation.create_feature_extractor()
+
+
+@st.experimental_memo(show_spinner=False)
+def process_file(file):
+    return segmentation.segment(
+        Image.open(file),
+        st.session_state["model"],
+        st.session_state["feature_extractor"]
+    )
+
+
+def get_uploaded_file():
+    return st.file_uploader(
+        label="Choose a file",
+        type=["png", "jpg", "jpeg"],
+    )
+
+
+def download_button(file, name, format):
+    st.download_button(
+        label="Download processed image",
+        data=file,
+        file_name=name,
+        mime="image/" + format
+    )
+
+
+def run():
+    st.title("Semantic image segmentation")
+    st.subheader("Upload your image and get an image with segmentation")
+
+    file = get_uploaded_file()
+    if not file:
+        return
+
+    placeholder = st.empty()
+    placeholder.info(
+        "Processing..."
+    )
+
+    image = process_file(file)
+    placeholder.empty()
+    placeholder.image(image)
+
+    filename = file.name
+    format = re.findall("\..*$", filename)[0][1:]
+
+    image = Image.fromarray(image)
+
+    buf = BytesIO()
+    image.save(buf, format="JPEG")
+    byte_image = buf.getvalue()
+
+    download_button(byte_image, filename, format)