a

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.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 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" 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/mySeg2.iml" filepath="$PROJECT_DIR$/.idea/mySeg2.iml" />
+    </modules>
+  </component>
+</project>

.idea/mySeg2.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="inheritedJdk" />
+    <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>

1212.md

@@ -1,75 +0,0 @@
----
-license: other
-tags:
-- vision
-- image-segmentation
-datasets:
-- cityscapes
-widget:
-- src: https://cdn-media.huggingface.co/Inference-API/Sample-results-on-the-Cityscapes-dataset-The-above-images-show-how-our-method-can-handle.png
-  example_title: road
----
-
-# SegFormer (b5-sized) model fine-tuned on CityScapes
-
-SegFormer model fine-tuned on CityScapes at resolution 640x1280. It was introduced in the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203) by Xie et al. and first released in [this repository](https://github.com/NVlabs/SegFormer). 
-
-Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team.
-
-## Model description
-
-SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a downstream dataset.
-
-## Intended uses & limitations
-
-You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?other=segformer) to look for fine-tuned versions on a task that interests you.
-
-### How to use
-
-Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
-
-```python
-from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
-from PIL import Image
-import requests
-
-feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
-model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
-
-url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
-
-inputs = feature_extractor(images=image, return_tensors="pt")
-outputs = model(**inputs)
-logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
-```
-
-For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/segformer.html#).
-
-### License
-
-The license for this model can be found [here](https://github.com/NVlabs/SegFormer/blob/master/LICENSE).
-
-### BibTeX entry and citation info
-
-```bibtex
-@article{DBLP:journals/corr/abs-2105-15203,
-  author    = {Enze Xie and
-               Wenhai Wang and
-               Zhiding Yu and
-               Anima Anandkumar and
-               Jose M. Alvarez and
-               Ping Luo},
-  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
-               Transformers},
-  journal   = {CoRR},
-  volume    = {abs/2105.15203},
-  year      = {2021},
-  url       = {https://arxiv.org/abs/2105.15203},
-  eprinttype = {arXiv},
-  eprint    = {2105.15203},
-  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
-  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
-  bibsource = {dblp computer science bibliography, https://dblp.org}
-}
-```

README.md

@@ -1,11 +1,12 @@
-
 ---
-title: MySeg2
-emoji: 📈
+title: MyImageSegmentation
+emoji: 🏢
 colorFrom: blue
-colorTo: yellow
+colorTo: gray
 sdk: gradio
-sdk_version: 4.2.0
+sdk_version: 3.44.4
 app_file: app.py
 pinned: false
----
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,15 +1,119 @@
-from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
+import gradio as gr
+
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
+import numpy as np
 from PIL import Image
-import requests
-import os
-os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
+import tensorflow as tf
+from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
+
+feature_extractor = SegformerFeatureExtractor.from_pretrained(
+    "mattmdjaga/segformer_b2_clothes"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    "mattmdjaga/segformer_b2_clothes"
+)
+
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [255, 0, 0],
+        [255, 94, 0],
+        [255, 187, 0],
+        [255, 228, 0],
+        [171, 242, 0],
+        [29, 219, 22],
+        [0, 216, 255],
+        [0, 84, 255],
+        [1, 0, 255],
+        [95, 0, 255],
+        [255, 0, 221],
+        [255, 0, 127],
+        [152, 0, 0],
+        [153, 112, 0],
+        [107, 153, 0],
+        [0, 51, 153],
+        [63, 0, 153],
+        [153, 0, 133]
+    ]
+
+
+labels_list = []
+
+with open(r"labels.txt", "r") as fp:
+    for line in fp:
+        labels_list.append(line[:-1])
+
+colormap = np.asarray(ade_palette())
+
+
+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 draw_plot(pred_img, seg):
+    fig = plt.figure(figsize=(20, 15))
+
+    grid_spec = gridspec.GridSpec(1, 2, width_ratios=[6, 1])
+
+    plt.subplot(grid_spec[0])
+    plt.imshow(pred_img)
+    plt.axis("off")
+    LABEL_NAMES = np.asarray(labels_list)
+    FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
+    FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)
+
+    unique_labels = np.unique(seg.numpy().astype("uint8"))
+    ax = plt.subplot(grid_spec[1])
+    plt.imshow(FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation="nearest")
+    ax.yaxis.tick_right()
+    plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
+    plt.xticks([], [])
+    ax.tick_params(width=0.0, labelsize=25)
+    return fig
+
+
+def sepia(input_img):
+    input_img = Image.fromarray(input_img)
+
+    inputs = feature_extractor(images=input_img, return_tensors="tf")
+    outputs = model(**inputs)
+    logits = outputs.logits
+
+    logits = tf.transpose(logits, [0, 2, 3, 1])
+    logits = tf.image.resize(
+        logits, input_img.size[::-1]
+    )  # We reverse the shape of `image` because `image.size` returns width and height.
+    seg = tf.math.argmax(logits, axis=-1)[0]
+
+    color_seg = np.zeros(
+        (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
+    )  # height, width, 3
+    for label, color in enumerate(colormap):
+        color_seg[seg.numpy() == label, :] = color
+
+    # Show image + mask
+    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
+    pred_img = pred_img.astype(np.uint8)
+
+    fig = draw_plot(pred_img, seg)
+    return fig
+
 
-feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
-model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
+demo = gr.Interface(
+    fn=sepia,
+    inputs=gr.Image(shape=(400, 600)),
+    outputs=["plot"],
+    examples=[
+        "person-1.jpg","person-2.jpg","person-3.jpg","person-4.jpg", "person-5.jpg",],
+    allow_flagging="never",
+)
 
-url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
 
-inputs = feature_extractor(images=image, return_tensors="pt")
-outputs = model(**inputs)
-logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
+demo.launch()

config.json

@@ -1,110 +0,0 @@
-{
-  "architectures": [
-    "SegformerForSemanticSegmentation"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "classifier_dropout_prob": 0.1,
-  "decoder_hidden_size": 256,
-  "depths": [
-    2,
-    2,
-    2,
-    2
-  ],
-  "downsampling_rates": [
-    1,
-    4,
-    8,
-    16
-  ],
-  "drop_path_rate": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_sizes": [
-    32,
-    64,
-    160,
-    256
-  ],
-  "id2label": {
-    "0": "road",
-    "1": "sidewalk",
-    "2": "building",
-    "3": "wall",
-    "4": "fence",
-    "5": "pole",
-    "6": "traffic light",
-    "7": "traffic sign",
-    "8": "vegetation",
-    "9": "terrain",
-    "10": "sky",
-    "11": "person",
-    "12": "rider",
-    "13": "car",
-    "14": "truck",
-    "15": "bus",
-    "16": "train",
-    "17": "motorcycle",
-    "18": "bicycle"
-  },
-  "image_size": 224,
-  "initializer_range": 0.02,
-  "label2id": {
-    "bicycle": 18,
-    "building": 2,
-    "bus": 15,
-    "car": 13,
-    "fence": 4,
-    "motorcycle": 17,
-    "person": 11,
-    "pole": 5,
-    "rider": 12,
-    "road": 0,
-    "sidewalk": 1,
-    "sky": 10,
-    "terrain": 9,
-    "traffic light": 6,
-    "traffic sign": 7,
-    "train": 16,
-    "truck": 14,
-    "vegetation": 8,
-    "wall": 3
-  },
-  "layer_norm_eps": 1e-06,
-  "mlp_ratios": [
-    4,
-    4,
-    4,
-    4
-  ],
-  "model_type": "segformer",
-  "num_attention_heads": [
-    1,
-    2,
-    5,
-    8
-  ],
-  "num_channels": 3,
-  "num_encoder_blocks": 4,
-  "patch_sizes": [
-    7,
-    3,
-    3,
-    3
-  ],
-  "reshape_last_stage": true,
-  "sr_ratios": [
-    8,
-    4,
-    2,
-    1
-  ],
-  "strides": [
-    4,
-    2,
-    2,
-    2
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.12.0.dev0"
-}

labels.txt

@@ -1,19 +1,18 @@
-road
-sidewalk
-building
-wall
-fence
-pole
-traffic light
-traffic sign
-vegetation
-terrain
-sky
-person
-rider
-car
-truck
-bus
-train
-motorcycle
-bicycle
+background
+hat
+hair
+sunglasses
+upper-clothes
+skirt
+pants
+dress
+belt
+left-shoe
+right-shoe
+face
+left-leg
+right-leg
+left-arm
+right-arm
+bag
+scarf

preprocessor_config.json

@@ -1,18 +0,0 @@
-{
-  "do_normalize": true,
-  "do_resize": true,
-  "feature_extractor_type": "SegformerFeatureExtractor",
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "reduce_labels": false,
-  "resample": 2,
-  "size": 512
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ffe3494e1339abf7af09a13c914e72c3d2745e2f315eba1fd2b1dee15b7a73ed
-size 14957601

tf_model.h5

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b07d5d1354b5e4bc6ad579e7350a240c170b0dea3c781bf917019932174569c
-size 15151028