adding cloth and fashion models

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,129 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="101">
+            <item index="0" class="java.lang.String" itemvalue="human-pose-estimator" />
+            <item index="1" class="java.lang.String" itemvalue="torch" />
+            <item index="2" class="java.lang.String" itemvalue="numpy" />
+            <item index="3" class="java.lang.String" itemvalue="gradio" />
+            <item index="4" class="java.lang.String" itemvalue="opencv-python-headless" />
+            <item index="5" class="java.lang.String" itemvalue="pymatting" />
+            <item index="6" class="java.lang.String" itemvalue="scipy" />
+            <item index="7" class="java.lang.String" itemvalue="pillow" />
+            <item index="8" class="java.lang.String" itemvalue="rembg" />
+            <item index="9" class="java.lang.String" itemvalue="carvekit" />
+            <item index="10" class="java.lang.String" itemvalue="scikit-image" />
+            <item index="11" class="java.lang.String" itemvalue="paddlepaddle" />
+            <item index="12" class="java.lang.String" itemvalue="paddlehub" />
+            <item index="13" class="java.lang.String" itemvalue="bisnet" />
+            <item index="14" class="java.lang.String" itemvalue="torchvision" />
+            <item index="15" class="java.lang.String" itemvalue="realesrgan" />
+            <item index="16" class="java.lang.String" itemvalue="huggingface-hub" />
+            <item index="17" class="java.lang.String" itemvalue="opencv-python" />
+            <item index="18" class="java.lang.String" itemvalue="yapf" />
+            <item index="19" class="java.lang.String" itemvalue="gfpgan" />
+            <item index="20" class="java.lang.String" itemvalue="lmdb" />
+            <item index="21" class="java.lang.String" itemvalue="tqdm" />
+            <item index="22" class="java.lang.String" itemvalue="filetype" />
+            <item index="23" class="java.lang.String" itemvalue="onnxruntime" />
+            <item index="24" class="java.lang.String" itemvalue="basicsr" />
+            <item index="25" class="java.lang.String" itemvalue="onnx" />
+            <item index="26" class="java.lang.String" itemvalue="psutil" />
+            <item index="27" class="java.lang.String" itemvalue="torchaudio" />
+            <item index="28" class="java.lang.String" itemvalue="timm" />
+            <item index="29" class="java.lang.String" itemvalue="gradio_imageslider" />
+            <item index="30" class="java.lang.String" itemvalue="transformers" />
+            <item index="31" class="java.lang.String" itemvalue="pydantic" />
+            <item index="32" class="java.lang.String" itemvalue="huggingface_hub" />
+            <item index="33" class="java.lang.String" itemvalue="monotonic-align" />
+            <item index="34" class="java.lang.String" itemvalue="einops-exts" />
+            <item index="35" class="java.lang.String" itemvalue="phonemizer" />
+            <item index="36" class="java.lang.String" itemvalue="txtsplit" />
+            <item index="37" class="java.lang.String" itemvalue="nltk" />
+            <item index="38" class="java.lang.String" itemvalue="SoundFile" />
+            <item index="39" class="java.lang.String" itemvalue="librosa" />
+            <item index="40" class="java.lang.String" itemvalue="gruut" />
+            <item index="41" class="java.lang.String" itemvalue="munch" />
+            <item index="42" class="java.lang.String" itemvalue="cached-path" />
+            <item index="43" class="java.lang.String" itemvalue="gdown" />
+            <item index="44" class="java.lang.String" itemvalue="diffusers" />
+            <item index="45" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="46" class="java.lang.String" itemvalue="skimage" />
+            <item index="47" class="java.lang.String" itemvalue="ultralytics" />
+            <item index="48" class="java.lang.String" itemvalue="Pillow" />
+            <item index="49" class="java.lang.String" itemvalue="dis_bg_remover" />
+            <item index="50" class="java.lang.String" itemvalue="kiui" />
+            <item index="51" class="java.lang.String" itemvalue="xatlas" />
+            <item index="52" class="java.lang.String" itemvalue="open-clip-torch" />
+            <item index="53" class="java.lang.String" itemvalue="nvdiffrast" />
+            <item index="54" class="java.lang.String" itemvalue="pymeshlab" />
+            <item index="55" class="java.lang.String" itemvalue="opencv-contrib-python-headless" />
+            <item index="56" class="java.lang.String" itemvalue="xformers" />
+            <item index="57" class="java.lang.String" itemvalue="pygltflib" />
+            <item index="58" class="java.lang.String" itemvalue="einops" />
+            <item index="59" class="java.lang.String" itemvalue="trimesh" />
+            <item index="60" class="java.lang.String" itemvalue="deepface" />
+            <item index="61" class="java.lang.String" itemvalue="pyside6" />
+            <item index="62" class="java.lang.String" itemvalue="dlib" />
+            <item index="63" class="java.lang.String" itemvalue="qtawesome" />
+            <item index="64" class="java.lang.String" itemvalue="tensorflow" />
+            <item index="65" class="java.lang.String" itemvalue="tensorboard" />
+            <item index="66" class="java.lang.String" itemvalue="tensorboardX" />
+            <item index="67" class="java.lang.String" itemvalue="imgaug" />
+            <item index="68" class="java.lang.String" itemvalue="torchsde" />
+            <item index="69" class="java.lang.String" itemvalue="onnxruntime-gpu" />
+            <item index="70" class="java.lang.String" itemvalue="alembic" />
+            <item index="71" class="java.lang.String" itemvalue="comfyui-embedded-docs" />
+            <item index="72" class="java.lang.String" itemvalue="comfyui-frontend-package" />
+            <item index="73" class="java.lang.String" itemvalue="av" />
+            <item index="74" class="java.lang.String" itemvalue="SQLAlchemy" />
+            <item index="75" class="java.lang.String" itemvalue="spandrel" />
+            <item index="76" class="java.lang.String" itemvalue="segment_anything" />
+            <item index="77" class="java.lang.String" itemvalue="comfyui-workflow-templates" />
+            <item index="78" class="java.lang.String" itemvalue="dotenv" />
+            <item index="79" class="java.lang.String" itemvalue="hydra-core" />
+            <item index="80" class="java.lang.String" itemvalue="fvcore" />
+            <item index="81" class="java.lang.String" itemvalue="cloudpickle" />
+            <item index="82" class="java.lang.String" itemvalue="pycocotools" />
+            <item index="83" class="java.lang.String" itemvalue="omegaconf" />
+            <item index="84" class="java.lang.String" itemvalue="accelerate" />
+            <item index="85" class="java.lang.String" itemvalue="ftfy" />
+            <item index="86" class="java.lang.String" itemvalue="pytorch-lightning" />
+            <item index="87" class="java.lang.String" itemvalue="torch-fidelity" />
+            <item index="88" class="java.lang.String" itemvalue="torchmetrics" />
+            <item index="89" class="java.lang.String" itemvalue="taming-transformers" />
+            <item index="90" class="java.lang.String" itemvalue="deepspeed" />
+            <item index="91" class="java.lang.String" itemvalue="open_clip_torch" />
+            <item index="92" class="java.lang.String" itemvalue="autokeras" />
+            <item index="93" class="java.lang.String" itemvalue="pyyaml" />
+            <item index="94" class="java.lang.String" itemvalue="albumentations" />
+            <item index="95" class="java.lang.String" itemvalue="kornia" />
+            <item index="96" class="java.lang.String" itemvalue="protobuf" />
+            <item index="97" class="java.lang.String" itemvalue="typing" />
+            <item index="98" class="java.lang.String" itemvalue="packaging" />
+            <item index="99" class="java.lang.String" itemvalue="setuptools" />
+            <item index="100" class="java.lang.String" itemvalue="spaces" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8Inspection" enabled="true" level="INFORMATION" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="E301" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N802" />
+          <option value="N803" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Torcho" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Torcho" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/segformer-tf-transformers.iml" filepath="$PROJECT_DIR$/.idea/segformer-tf-transformers.iml" />
+    </modules>
+  </component>
+</project>

.idea/segformer-tf-transformers.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Torcho" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

README.md

@@ -1,5 +1,5 @@
 ---
-title: SegFormer (ADE20k) in ONNX
+title: SegFormer ONNX
 emoji: 🏃
 colorFrom: indigo
 colorTo: gray
@@ -8,25 +8,31 @@ sdk_version: 5.49.0
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: Image segmentation fine-tuned on the ADE20k dataset
+short_description: SegFormer image segmentation ADE20k, Cloths & Fashion
 ---
 
-## SegFormer (ADE20k) in ONNX
+# [SegFormer image segmentation ADE20k, Cloths & Fashion](https://huggingface.co/spaces/leonelhs/segformer-tf-transformers )
 
-This is demo TensorFlow SegFormer from 🤗 `transformers` official package. The pre-trained model was trained to segment scene specific images. We are **currently using ONNX model converted from the TensorFlow based SegFormer to improve the latency**. The average latency of an inference is **21** and **8** seconds for TensorFlow and ONNX converted models respectively (in [Colab](https://github.com/deep-diver/segformer-tf-transformers/blob/main/notebooks/TFSegFormer_ONNX.ipynb)). Check out the [repository](https://github.com/deep-diver/segformer-tf-transformers) to find out how to make inference, finetune the model with custom dataset, and further information.
+This is demo collects SegFormer implementations from several spaces  
 
+## Model ADE20k 
+This model is fine-tuned for images belonging to scene categories.
 
-This space hosts the [SegFormer model](https://arxiv.org/abs/2105.15203) in TensorFlow. This model was fine-tuned on the [ADE20k dataset](http://groups.csail.mit.edu/vision/datasets/ADE20K/). To know more about the checkpoint used in this space, refer to the model card
-[here](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640).
+## Model Cloths 
+This model is fine-tuned for human cloth images.
+Expected classes: Face, Hat, Hair, Upper_clothes, Skirt, Pants, Dress, Belt, shoe, leg, arm, Bag, Scarf
 
-Please note that since the model was fine-tuned on the ADE20k dataset, the model is expected to provide best results for images
-belonging to scene categories. For an overview of the dataset, refer to its [homepage](http://groups.csail.mit.edu/vision/datasets/ADE20K/).
+## Model Fashion 
+This model extends and complements human cloth model.
+Expected classes: shirt, top, sweater, cardigan, jacket, vest, pants, shorts, skirt, coat, dress, jumpsuit, cape, glasses, hat, hairaccessory, tie, glove, watch, belt, legwarmer, tights, sock, shoe, bagwallet, scarf, umbrella, hood, collar, lapel, epaulette, sleeve, pocket, neckline, buckle, zipper, applique, bead, bow, flower, fringe, ribbon, rivet, ruffle, sequin, tassel
 
 ## Acknowledgments
 This work integrates code and concepts from several repositories.  
 For proper attribution, please refer to the following sources (or notify us if any are missing):
-- [Original space](https://huggingface.co/spaces/chansung/segformer-tf-transformers)
-- 
+- [github](https://github.com/deep-diver/segformer-tf-transformers)
+- [huggingface](https://huggingface.co/spaces/chansung/segformer-tf-transformers)
+- [ADE20k dataset](http://groups.csail.mit.edu/vision/datasets/ADE20K/)
+- [nvidia](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640)
 ## Contact
 For questions, comments, or feedback, please contact:  
 📧 **leonelhs@gmail.com**

ade_palette.txt

@@ -1,150 +0,0 @@
-[120, 120, 120]
-[180, 120, 120]
-[6, 230, 230]
-[80, 50, 50]
-[4, 200, 3]
-[120, 120, 80]
-[140, 140, 140]
-[204, 5, 255]
-[230, 230, 230]
-[4, 250, 7]
-[224, 5, 255]
-[235, 255, 7]
-[150, 5, 61]
-[120, 120, 70]
-[8, 255, 51]
-[255, 6, 82]
-[143, 255, 140]
-[204, 255, 4]
-[255, 51, 7]
-[204, 70, 3]
-[0, 102, 200]
-[61, 230, 250]
-[255, 6, 51]
-[11, 102, 255]
-[255, 7, 71]
-[255, 9, 224]
-[9, 7, 230]
-[220, 220, 220]
-[255, 9, 92]
-[112, 9, 255]
-[8, 255, 214]
-[7, 255, 224]
-[255, 184, 6]
-[10, 255, 71]
-[255, 41, 10]
-[7, 255, 255]
-[224, 255, 8]
-[102, 8, 255]
-[255, 61, 6]
-[255, 194, 7]
-[255, 122, 8]
-[0, 255, 20]
-[255, 8, 41]
-[255, 5, 153]
-[6, 51, 255]
-[235, 12, 255]
-[160, 150, 20]
-[0, 163, 255]
-[140, 140, 140]
-[250, 10, 15]
-[20, 255, 0]
-[31, 255, 0]
-[255, 31, 0]
-[255, 224, 0]
-[153, 255, 0]
-[0, 0, 255]
-[255, 71, 0]
-[0, 235, 255]
-[0, 173, 255]
-[31, 0, 255]
-[11, 200, 200]
-[255, 82, 0]
-[0, 255, 245]
-[0, 61, 255]
-[0, 255, 112]
-[0, 255, 133]
-[255, 0, 0]
-[255, 163, 0]
-[255, 102, 0]
-[194, 255, 0]
-[0, 143, 255]
-[51, 255, 0]
-[0, 82, 255]
-[0, 255, 41]
-[0, 255, 173]
-[10, 0, 255]
-[173, 255, 0]
-[0, 255, 153]
-[255, 92, 0]
-[255, 0, 255]
-[255, 0, 245]
-[255, 0, 102]
-[255, 173, 0]
-[255, 0, 20]
-[255, 184, 184]
-[0, 31, 255]
-[0, 255, 61]
-[0, 71, 255]
-[255, 0, 204]
-[0, 255, 194]
-[0, 255, 82]
-[0, 10, 255]
-[0, 112, 255]
-[51, 0, 255]
-[0, 194, 255]
-[0, 122, 255]
-[0, 255, 163]
-[255, 153, 0]
-[0, 255, 10]
-[255, 112, 0]
-[143, 255, 0]
-[82, 0, 255]
-[163, 255, 0]
-[255, 235, 0]
-[8, 184, 170]
-[133, 0, 255]
-[0, 255, 92]
-[184, 0, 255]
-[255, 0, 31]
-[0, 184, 255]
-[0, 214, 255]
-[255, 0, 112]
-[92, 255, 0]
-[0, 224, 255]
-[112, 224, 255]
-[70, 184, 160]
-[163, 0, 255]
-[153, 0, 255]
-[71, 255, 0]
-[255, 0, 163]
-[255, 204, 0]
-[255, 0, 143]
-[0, 255, 235]
-[133, 255, 0]
-[255, 0, 235]
-[245, 0, 255]
-[255, 0, 122]
-[255, 245, 0]
-[10, 190, 212]
-[214, 255, 0]
-[0, 204, 255]
-[20, 0, 255]
-[255, 255, 0]
-[0, 153, 255]
-[0, 41, 255]
-[0, 255, 204]
-[41, 0, 255]
-[41, 255, 0]
-[173, 0, 255]
-[0, 245, 255]
-[71, 0, 255]
-[122, 0, 255]
-[0, 255, 184]
-[0, 92, 255]
-[184, 255, 0]
-[0, 133, 255]
-[255, 214, 0]
-[25, 194, 194]
-[102, 255, 0]
-[92, 0, 255]

app-ade20k.py

@@ -0,0 +1,127 @@
+#######################################################################################
+#
+# MIT License
+#
+# Copyright (c) [2025] [leonelhs@gmail.com]
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+#
+#######################################################################################
+#
+# This project is one of several repositories exploring image segmentation techniques.
+# All related projects and interactive demos can be found at:
+# https://huggingface.co/spaces/leonelhs/removators
+# huggingface: https://huggingface.co/spaces/leonelhs/segformer-tf-transformers
+#
+
+import csv
+import os
+import sys
+from itertools import islice
+
+import cv2
+import numpy as np
+import onnxruntime as ort
+import gradio as gr
+from PIL import Image
+from huggingface_hub import hf_hub_download
+
+ade_palette = []
+labels_list = []
+
+csv.field_size_limit(sys.maxsize)
+
+with open(r"labels.txt", "r") as fp:
+    for line in fp:
+        labels_list.append(line[:-1])
+
+with open(r"ade_palette.txt", "r") as fp:
+    for line in fp:
+        tmp_list = list(map(int, line[:-1].strip("][").split(", ")))
+        ade_palette.append(tmp_list)
+
+    colormap = np.asarray(ade_palette)
+
+
+REPO_ID = "leonelhs/segmentators"
+model_path = hf_hub_download(repo_id=REPO_ID, filename="segformer/segformer-b5-finetuned-ade-640-640.onnx")
+
+
+sess_options = ort.SessionOptions()
+sess_options.intra_op_num_threads = os.cpu_count()
+sess = ort.InferenceSession(model_path, sess_options, providers=["CPUExecutionProvider"])
+
+
+def label_to_color_image(label):
+    if label.ndim != 2:
+        raise ValueError("Expect 2-D input label")
+
+    if np.max(label) >= len(colormap):
+        raise ValueError("label value too large.")
+
+    return colormap[label]
+
+def predict(input_img):
+
+    img = cv2.imread(input_img)
+    img = cv2.resize(img, (640, 640)).astype(np.float32)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    img_batch = np.expand_dims(img, axis=0)
+    img_batch = np.transpose(img_batch, (0, 3, 1, 2))
+
+    logits = sess.run(None, {"pixel_values": img_batch})[0]
+
+    logits = np.transpose(logits, (0, 2, 3, 1))
+    segmented_mask = np.argmax(logits, axis=-1)[0].astype("float32")
+    segmented_mask = cv2.resize(segmented_mask, (640, 640)).astype("uint8")
+
+
+    parts = []
+    unique_labels = np.unique(segmented_mask)
+    label_names = np.asarray(labels_list)
+
+    for label in unique_labels:
+        part = np.where(segmented_mask == label)
+        color_seg = np.full((640, 640, 3), 0, dtype=np.uint8)
+        color_seg[part[0], part[1], :] = colormap[label]
+        color_seg = cv2.cvtColor(color_seg, cv2.COLOR_BGR2GRAY)
+        parts.append((color_seg, label_names[label]))
+
+    return Image.fromarray(img.astype("uint8")), parts
+
+with gr.Blocks(title="SegFormer") as app:
+    navbar = gr.Navbar(visible=True, main_page_name="Workspace")
+    gr.Markdown("## SegFormer(ADE20k) ONNX")
+    with gr.Row():
+        with gr.Column(scale=1):
+            inp = gr.Image(type="filepath", label="Upload Image")
+            btn_predict = gr.Button("Parse")
+        with gr.Column(scale=2):
+            out = gr.AnnotatedImage(label="Image parsed annotated")
+
+    btn_predict.click(predict, inputs=[inp], outputs=[out])
+
+
+with app.route("About this", "/about"):
+    with open("README.md") as f:
+        for line in islice(f, 12, None):
+            gr.Markdown(line.strip())
+
+app.launch(share=False, debug=True, show_error=True, mcp_server=True, pwa=True)
+app.queue()

app.py

@@ -30,9 +30,7 @@
 # huggingface: https://huggingface.co/spaces/leonelhs/segformer-tf-transformers
 #
 
-import csv
 import os
-import sys
 from itertools import islice
 
 import cv2
@@ -42,42 +40,35 @@ import gradio as gr
 from PIL import Image
 from huggingface_hub import hf_hub_download
 
-ade_palette = []
-labels_list = []
-
-csv.field_size_limit(sys.maxsize)
-
-with open(r"labels.txt", "r") as fp:
-    for line in fp:
-        labels_list.append(line[:-1])
-
-with open(r"ade_palette.txt", "r") as fp:
-    for line in fp:
-        tmp_list = list(map(int, line[:-1].strip("][").split(", ")))
-        ade_palette.append(tmp_list)
-
-    colormap = np.asarray(ade_palette)
-
+from pallete import colormap
+from labels import cloth_labels, fashion_labels, ADE20k_labels
 
 REPO_ID = "leonelhs/segmentators"
-model_path = hf_hub_download(repo_id=REPO_ID, filename="segformer/segformer-b5-finetuned-ade-640-640.onnx")
 
+ADE20k_path = hf_hub_download(repo_id=REPO_ID, filename="segformer/segformer-b5-finetuned-ade-640-640.onnx")
+fashion_path = hf_hub_download(repo_id=REPO_ID, filename="segformer/segformer-b3-fashion.onnx")
+clothes_path = hf_hub_download(repo_id=REPO_ID, filename="segformer/segformer_b2_clothes.onnx")
 
 sess_options = ort.SessionOptions()
 sess_options.intra_op_num_threads = os.cpu_count()
-sess = ort.InferenceSession(model_path, sess_options, providers=["CPUExecutionProvider"])
+
+session_ade20k = ort.InferenceSession(fashion_path, sess_options, providers=["CPUExecutionProvider"])
+session_cloth = ort.InferenceSession(clothes_path, sess_options, providers=["CPUExecutionProvider"])
+session_fashion = ort.InferenceSession(fashion_path, sess_options, providers=["CPUExecutionProvider"])
 
 
-def label_to_color_image(label):
-    if label.ndim != 2:
-        raise ValueError("Expect 2-D input label")
+def predict(input_img, model="ADE20k"):
 
-    if np.max(label) >= len(colormap):
-        raise ValueError("label value too large.")
+    session = session_ade20k
+    labels = ADE20k_labels
 
-    return colormap[label]
+    if model == "Cloth":
+        session = session_cloth
+        labels = cloth_labels
+    elif model == "Fashion":
+        session = session_fashion
+        labels = fashion_labels
 
-def predict(input_img):
 
     img = cv2.imread(input_img)
     img = cv2.resize(img, (640, 640)).astype(np.float32)
@@ -85,37 +76,38 @@ def predict(input_img):
     img_batch = np.expand_dims(img, axis=0)
     img_batch = np.transpose(img_batch, (0, 3, 1, 2))
 
-    logits = sess.run(None, {"pixel_values": img_batch})[0]
+    inputs = {'input': img_batch}
+
+    logits = session.run(None, inputs)[0]
 
     logits = np.transpose(logits, (0, 2, 3, 1))
     segmented_mask = np.argmax(logits, axis=-1)[0].astype("float32")
     segmented_mask = cv2.resize(segmented_mask, (640, 640)).astype("uint8")
 
-
     parts = []
     unique_labels = np.unique(segmented_mask)
-    label_names = np.asarray(labels_list)
 
     for label in unique_labels:
         part = np.where(segmented_mask == label)
         color_seg = np.full((640, 640, 3), 0, dtype=np.uint8)
         color_seg[part[0], part[1], :] = colormap[label]
         color_seg = cv2.cvtColor(color_seg, cv2.COLOR_BGR2GRAY)
-        parts.append((color_seg, label_names[label]))
+        parts.append((color_seg, labels[label]))
 
     return Image.fromarray(img.astype("uint8")), parts
 
 with gr.Blocks(title="SegFormer") as app:
     navbar = gr.Navbar(visible=True, main_page_name="Workspace")
-    gr.Markdown("## SegFormer(ADE20k) ONNX")
+    gr.Markdown("## SegFormer ONNX")
     with gr.Row():
         with gr.Column(scale=1):
             inp = gr.Image(type="filepath", label="Upload Image")
+            mod = gr.Dropdown(choices=["ADE20k","Cloth","Fashion"], label="Model generator", value="ADE20k")
             btn_predict = gr.Button("Parse")
         with gr.Column(scale=2):
             out = gr.AnnotatedImage(label="Image parsed annotated")
 
-    btn_predict.click(predict, inputs=[inp], outputs=[out])
+    btn_predict.click(predict, inputs=[inp, mod], outputs=[out])
 
 
 with app.route("About this", "/about"):

labels.py

@@ -0,0 +1,223 @@
+cloth_labels = {
+    0: "background",
+    1: "Hat",
+    2: "Hair",
+    3: "Sunglasses",
+    4: "Upper-clothes",
+    5: "Skirt",
+    6: "Pants",
+    7: "Dress",
+    8: "Belt",
+    9: "Left-shoe",
+    10: "Right-shoe",
+    11: "Face",
+    12: "Left-leg",
+    13: "Right-leg",
+    14: "Left-arm",
+    15: "Right-arm",
+    16: "Bag",
+    17: "Scarf"
+}
+
+fashion_labels = {
+    0: "background",
+    1: "shirt",
+    2: "top",
+    3: "sweater",
+    4: "cardigan",
+    5: "jacket",
+    6: "vest",
+    7: "pants",
+    8: "shorts",
+    9: "skirt",
+    10: "coat",
+    11: "dress",
+    12: "jumpsuit",
+    13: "cape",
+    14: "glasses",
+    15: "hat",
+    16: "hairaccessory",
+    17: "tie",
+    18: "glove",
+    19: "watch",
+    20: "belt",
+    21: "legwarmer",
+    22: "tights",
+    23: "sock",
+    24: "shoe",
+    25: "bagwallet",
+    26: "scarf",
+    27: "umbrella",
+    28: "hood",
+    29: "collar",
+    30: "lapel",
+    31: "epaulette",
+    32: "sleeve",
+    33: "pocket",
+    34: "neckline",
+    35: "buckle",
+    36: "zipper",
+    37: "applique",
+    38: "bead",
+    39: "bow",
+    40: "flower",
+    41: "fringe",
+    42: "ribbon",
+    43: "rivet",
+    44: "ruffle",
+    45: "sequin",
+    46: "tassel"
+}
+
+ADE20k_labels = {
+    0: "wall",
+    1: "building;edifice",
+    2: "sky",
+    3: "floor;flooring",
+    4: "tree",
+    5: "ceiling",
+    6: "road;route",
+    7: "bed",
+    8: "windowpane;window",
+    9: "grass",
+    10: "cabinet",
+    11: "sidewalk;pavement",
+    12: "person;individual;someone;somebody;mortal;soul",
+    13: "earth;ground",
+    14: "door;double;door",
+    15: "table",
+    16: "mountain;mount",
+    17: "plant;flora;plant;life",
+    18: "curtain;drape;drapery;mantle;pall",
+    19: "chair",
+    20: "car;auto;automobile;machine;motorcar",
+    21: "water",
+    22: "painting;picture",
+    23: "sofa;couch;lounge",
+    24: "shelf",
+    25: "house",
+    26: "sea",
+    27: "mirror",
+    28: "rug;carpet;carpeting",
+    29: "field",
+    30: "armchair",
+    31: "seat",
+    32: "fence;fencing",
+    33: "desk",
+    34: "rock;stone",
+    35: "wardrobe;closet;press",
+    36: "lamp",
+    37: "bathtub;bathing;tub;bath;tub",
+    38: "railing;rail",
+    39: "cushion",
+    40: "base;pedestal;stand",
+    41: "box",
+    42: "column;pillar",
+    43: "signboard;sign",
+    44: "chest;of;drawers;chest;bureau;dresser",
+    45: "counter",
+    46: "sand",
+    47: "sink",
+    48: "skyscraper",
+    49: "fireplace;hearth;open;fireplace",
+    50: "refrigerator;icebox",
+    51: "grandstand;covered;stand",
+    52: "path",
+    53: "stairs;steps",
+    54: "runway",
+    55: "case;display;case;showcase;vitrine",
+    56: "pool;table;billiard;table;snooker;table",
+    57: "pillow",
+    58: "screen;door;screen",
+    59: "stairway;staircase",
+    60: "river",
+    61: "bridge;span",
+    62: "bookcase",
+    63: "blind;screen",
+    64: "coffee;table;cocktail;table",
+    65: "toilet;can;commode;crapper;pot;potty;stool;throne",
+    66: "flower",
+    67: "book",
+    68: "hill",
+    69: "bench",
+    70: "countertop",
+    71: "stove;kitchen;stove;range;kitchen;range;cooking;stove",
+    72: "palm;palm;tree",
+    73: "kitchen;island",
+    74: "computer;computing;machine;computing;device;data;processor;electronic;computer;information;processing;system",
+    75: "swivel;chair",
+    76: "boat",
+    77: "bar",
+    78: "arcade;machine",
+    79: "hovel;hut;hutch;shack;shanty",
+    80: "bus;autobus;coach;charabanc;double-decker;jitney;motorbus;motorcoach;omnibus;passenger;vehicle",
+    81: "towel",
+    82: "light;light;source",
+    83: "truck;motortruck",
+    84: "tower",
+    85: "chandelier;pendant;pendent",
+    86: "awning;sunshade;sunblind",
+    87: "streetlight;street;lamp",
+    88: "booth;cubicle;stall;kiosk",
+    89: "television;television;receiver;television;set;tv;tv;set;idiot;box;boob;tube;telly;goggle;box",
+    90: "airplane;aeroplane;plane",
+    91: "dirt;track",
+    92: "apparel;wearing;apparel;dress;clothes",
+    93: "pole",
+    94: "land;ground;soil",
+    95: "bannister;banister;balustrade;balusters;handrail",
+    96: "escalator;moving;staircase;moving;stairway",
+    97: "ottoman;pouf;pouffe;puff;hassock",
+    98: "bottle",
+    99: "buffet;counter;sideboard",
+    100: "poster;posting;placard;notice;bill;card",
+    101: "stage",
+    102: "van",
+    103: "ship",
+    104: "fountain",
+    105: "conveyer;belt;conveyor;belt;conveyer;conveyor;transporter",
+    106: "canopy",
+    107: "washer;automatic;washer;washing;machine",
+    108: "plaything;toy",
+    109: "swimming;pool;swimming;bath;natatorium",
+    110: "stool",
+    111: "barrel;cask",
+    112: "basket;handbasket",
+    113: "waterfall;falls",
+    114: "tent;collapsible;shelter",
+    115: "bag",
+    116: "minibike;motorbike",
+    117: "cradle",
+    118: "oven",
+    119: "ball",
+    120: "food;solid;food",
+    121: "step;stair",
+    122: "tank;storage;tank",
+    123: "trade;name;brand;name;brand;marque",
+    124: "microwave;microwave;oven",
+    125: "pot;flowerpot",
+    126: "animal;animate;being;beast;brute;creature;fauna",
+    127: "bicycle;bike;wheel;cycle",
+    128: "lake",
+    129: "dishwasher;dish;washer;dishwashing;machine",
+    130: "screen;silver;screen;projection;screen",
+    131: "blanket;cover",
+    132: "sculpture",
+    133: "hood;exhaust;hood",
+    134: "sconce",
+    135: "vase",
+    136: "traffic;light;traffic;signal;stoplight",
+    137: "tray",
+    138: "ashcan;trash;can;garbage;can;wastebin;ash;bin;ash-bin;ashbin;dustbin;trash;barrel;trash;bin",
+    139: "fan",
+    140: "pier;wharf;wharfage;dock",
+    141: "crt;screen",
+    142: "plate",
+    143: "monitor;monitoring;device",
+    144: "bulletin;board;notice;board",
+    145: "shower",
+    146: "radiator",
+    147: "glass;drinking;glass",
+    148: "clock",
+    149: "flag",
+}

labels.txt

@@ -1,150 +0,0 @@
-wall
-building;edifice
-sky
-floor;flooring
-tree
-ceiling
-road;route
-bed
-windowpane;window
-grass
-cabinet
-sidewalk;pavement
-person;individual;someone;somebody;mortal;soul
-earth;ground
-door;double;door
-table
-mountain;mount
-plant;flora;plant;life
-curtain;drape;drapery;mantle;pall
-chair
-car;auto;automobile;machine;motorcar
-water
-painting;picture
-sofa;couch;lounge
-shelf
-house
-sea
-mirror
-rug;carpet;carpeting
-field
-armchair
-seat
-fence;fencing
-desk
-rock;stone
-wardrobe;closet;press
-lamp
-bathtub;bathing;tub;bath;tub
-railing;rail
-cushion
-base;pedestal;stand
-box
-column;pillar
-signboard;sign
-chest;of;drawers;chest;bureau;dresser
-counter
-sand
-sink
-skyscraper
-fireplace;hearth;open;fireplace
-refrigerator;icebox
-grandstand;covered;stand
-path
-stairs;steps
-runway
-case;display;case;showcase;vitrine
-pool;table;billiard;table;snooker;table
-pillow
-screen;door;screen
-stairway;staircase
-river
-bridge;span
-bookcase
-blind;screen
-coffee;table;cocktail;table
-toilet;can;commode;crapper;pot;potty;stool;throne
-flower
-book
-hill
-bench
-countertop
-stove;kitchen;stove;range;kitchen;range;cooking;stove
-palm;palm;tree
-kitchen;island
-computer;computing;machine;computing;device;data;processor;electronic;computer;information;processing;system
-swivel;chair
-boat
-bar
-arcade;machine
-hovel;hut;hutch;shack;shanty
-bus;autobus;coach;charabanc;double-decker;jitney;motorbus;motorcoach;omnibus;passenger;vehicle
-towel
-light;light;source
-truck;motortruck
-tower
-chandelier;pendant;pendent
-awning;sunshade;sunblind
-streetlight;street;lamp
-booth;cubicle;stall;kiosk
-television;television;receiver;television;set;tv;tv;set;idiot;box;boob;tube;telly;goggle;box
-airplane;aeroplane;plane
-dirt;track
-apparel;wearing;apparel;dress;clothes
-pole
-land;ground;soil
-bannister;banister;balustrade;balusters;handrail
-escalator;moving;staircase;moving;stairway
-ottoman;pouf;pouffe;puff;hassock
-bottle
-buffet;counter;sideboard
-poster;posting;placard;notice;bill;card
-stage
-van
-ship
-fountain
-conveyer;belt;conveyor;belt;conveyer;conveyor;transporter
-canopy
-washer;automatic;washer;washing;machine
-plaything;toy
-swimming;pool;swimming;bath;natatorium
-stool
-barrel;cask
-basket;handbasket
-waterfall;falls
-tent;collapsible;shelter
-bag
-minibike;motorbike
-cradle
-oven
-ball
-food;solid;food
-step;stair
-tank;storage;tank
-trade;name;brand;name;brand;marque
-microwave;microwave;oven
-pot;flowerpot
-animal;animate;being;beast;brute;creature;fauna
-bicycle;bike;wheel;cycle
-lake
-dishwasher;dish;washer;dishwashing;machine
-screen;silver;screen;projection;screen
-blanket;cover
-sculpture
-hood;exhaust;hood
-sconce
-vase
-traffic;light;traffic;signal;stoplight
-tray
-ashcan;trash;can;garbage;can;wastebin;ash;bin;ash-bin;ashbin;dustbin;trash;barrel;trash;bin
-fan
-pier;wharf;wharfage;dock
-crt;screen
-plate
-monitor;monitoring;device
-bulletin;board;notice;board
-shower
-radiator
-glass;drinking;glass
-clock
-flag

pallete.py

@@ -0,0 +1,152 @@
+colormap = {
+    0: [120, 120, 120],
+    1: [180, 120, 120],
+    2: [6, 230, 230],
+    3: [80, 50, 50],
+    4: [4, 200, 3],
+    5: [120, 120, 80],
+    6: [140, 140, 140],
+    7: [204, 5, 255],
+    8: [230, 230, 230],
+    9: [4, 250, 7],
+    10: [224, 5, 255],
+    11: [235, 255, 7],
+    12: [150, 5, 61],
+    13: [120, 120, 70],
+    14: [8, 255, 51],
+    15: [255, 6, 82],
+    16: [143, 255, 140],
+    17: [204, 255, 4],
+    18: [255, 51, 7],
+    19: [204, 70, 3],
+    20: [0, 102, 200],
+    21: [61, 230, 250],
+    22: [255, 6, 51],
+    23: [11, 102, 255],
+    24: [255, 7, 71],
+    25: [255, 9, 224],
+    26: [9, 7, 230],
+    27: [220, 220, 220],
+    28: [255, 9, 92],
+    29: [112, 9, 255],
+    30: [8, 255, 214],
+    31: [7, 255, 224],
+    32: [255, 184, 6],
+    33: [10, 255, 71],
+    34: [255, 41, 10],
+    35: [7, 255, 255],
+    36: [224, 255, 8],
+    37: [102, 8, 255],
+    38: [255, 61, 6],
+    39: [255, 194, 7],
+    40: [255, 122, 8],
+    41: [0, 255, 20],
+    42: [255, 8, 41],
+    43: [255, 5, 153],
+    44: [6, 51, 255],
+    45: [235, 12, 255],
+    46: [160, 150, 20],
+    47: [0, 163, 255],
+    48: [140, 140, 140],
+    49: [250, 10, 15],
+    50: [20, 255, 0],
+    51: [31, 255, 0],
+    52: [255, 31, 0],
+    53: [255, 224, 0],
+    54: [153, 255, 0],
+    55: [0, 0, 255],
+    56: [255, 71, 0],
+    57: [0, 235, 255],
+    58: [0, 173, 255],
+    59: [31, 0, 255],
+    60: [11, 200, 200],
+    61: [255, 82, 0],
+    62: [0, 255, 245],
+    63: [0, 61, 255],
+    64: [0, 255, 112],
+    65: [0, 255, 133],
+    66: [255, 0, 0],
+    67: [255, 163, 0],
+    68: [255, 102, 0],
+    69: [194, 255, 0],
+    70: [0, 143, 255],
+    71: [51, 255, 0],
+    72: [0, 82, 255],
+    73: [0, 255, 41],
+    74: [0, 255, 173],
+    75: [10, 0, 255],
+    76: [173, 255, 0],
+    77: [0, 255, 153],
+    78: [255, 92, 0],
+    79: [255, 0, 255],
+    80: [255, 0, 245],
+    81: [255, 0, 102],
+    82: [255, 173, 0],
+    83: [255, 0, 20],
+    84: [255, 184, 184],
+    85: [0, 31, 255],
+    86: [0, 255, 61],
+    87: [0, 71, 255],
+    88: [255, 0, 204],
+    89: [0, 255, 194],
+    90: [0, 255, 82],
+    91: [0, 10, 255],
+    92: [0, 112, 255],
+    93: [51, 0, 255],
+    94: [0, 194, 255],
+    95: [0, 122, 255],
+    96: [0, 255, 163],
+    97: [255, 153, 0],
+    98: [0, 255, 10],
+    99: [255, 112, 0],
+    100: [143, 255, 0],
+    101: [82, 0, 255],
+    102: [163, 255, 0],
+    103: [255, 235, 0],
+    104: [8, 184, 170],
+    105: [133, 0, 255],
+    106: [0, 255, 92],
+    107: [184, 0, 255],
+    108: [255, 0, 31],
+    109: [0, 184, 255],
+    110: [0, 214, 255],
+    111: [255, 0, 112],
+    112: [92, 255, 0],
+    113: [0, 224, 255],
+    114: [112, 224, 255],
+    115: [70, 184, 160],
+    116: [163, 0, 255],
+    117: [153, 0, 255],
+    118: [71, 255, 0],
+    119: [255, 0, 163],
+    120: [255, 204, 0],
+    121: [255, 0, 143],
+    122: [0, 255, 235],
+    123: [133, 255, 0],
+    124: [255, 0, 235],
+    125: [245, 0, 255],
+    126: [255, 0, 122],
+    127: [255, 245, 0],
+    128: [10, 190, 212],
+    129: [214, 255, 0],
+    130: [0, 204, 255],
+    131: [20, 0, 255],
+    132: [255, 255, 0],
+    133: [0, 153, 255],
+    134: [0, 41, 255],
+    135: [0, 255, 204],
+    136: [41, 0, 255],
+    137: [41, 255, 0],
+    138: [173, 0, 255],
+    139: [0, 245, 255],
+    140: [71, 0, 255],
+    141: [122, 0, 255],
+    142: [0, 255, 184],
+    143: [0, 92, 255],
+    144: [184, 255, 0],
+    145: [0, 133, 255],
+    146: [255, 214, 0],
+    147: [25, 194, 194],
+    148: [102, 255, 0],
+    149: [92, 0, 255]
+}

requirements.txt

@@ -1,4 +1,3 @@
 onnxruntime==1.22.1
 numpy==2.2.6
-opencv-python
-matplotlib== 3.10.6
+opencv-python