Duplicate from tti-bias/identities-colorfulness-knn

.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: Identities Colorfulness k-nn
+emoji: ⚡
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: tti-bias/identities-colorfulness-knn
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from datasets import load_from_disk
+import numpy as np
+
+
+gender_labels = ['man', 'non-binary', 'woman', 'no_gender_specified', ]
+
+ethnicity_labels = ['African-American', 'American_Indian', 'Black', 'Caucasian', 'East_Asian',
+                    'First_Nations', 'Hispanic', 'Indigenous_American', 'Latino', 'Latinx',
+                    'Multiracial', 'Native_American', 'Pacific_Islander', 'South_Asian',
+                    'Southeast_Asian', 'White', 'no_ethnicity_specified']
+models = ['DallE', 'SD_14', 'SD_2']
+nos = [1,2,3,4,5,6,7,8,9,10]
+
+ds = load_from_disk("color-sorted")
+
+def get_nearest(gender, ethnicity, model, no):
+    df = ds.remove_columns(["image","image_path"]).to_pandas()
+    ix = df.loc[(df['ethnicity'] == ethnicity)  & (df['gender'] == gender) & (df['no'] == no) & (df['model'] == model)].index[0]
+    image = ds.select([ix])["image"][0]
+    neighbors =  ds.select(range(max(ix-10, 0), min(ix+10, len(ds)-1)))
+    neighbor_images = neighbors["image"]
+    neighbor_captions = [caption.split("/")[-1] for caption in neighbors["image_path"]]
+    neighbor_captions = [' '.join(caption.split("_")[4:-3]) for caption in neighbor_captions]
+    neighbor_models = neighbors["model"]
+    neighbor_captions = [f"{a} {b}" for a,b in zip(neighbor_captions,neighbor_models)]
+    return image, list(zip(neighbor_images, neighbor_captions))
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Colorfulness Nearest Neighbors Explorer")
+    gr.Markdown("### Colorfulness 1-D index of the _identities_ dataset of images generated by 3 models")
+    gr.Markdown("#### Choose one of the generated identity images to see its nearest neighbors according to colorfulness")
+    with gr.Row():
+        with gr.Column():
+            model = gr.Radio(models, label="Model")
+            gender = gr.Radio(gender_labels, label="Gender label")
+            no = gr.Radio(nos, label="Image number")
+        with gr.Column():
+            ethnicity = gr.Radio(ethnicity_labels, label="Ethnicity label")
+    button = gr.Button(value="Get nearest neighbors")
+    with gr.Row():
+        image = gr.Image()
+        gallery = gr.Gallery().style(grid=4)
+    button.click(get_nearest, inputs=[gender, ethnicity, model, no], outputs=[image, gallery])
+demo.launch()

color-sorted/dataset.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df800c69b324f3dce9602c00b279cfbd06903b9105c34945dae3f12d2ba59f70
+size 310798712

color-sorted/dataset_info.json

@@ -0,0 +1,56 @@
+{
+  "citation": "",
+  "dataset_size": 585345345,
+  "description": "",
+  "download_checksums": {
+    "https://huggingface.co/datasets/SDbiaseval/identities/resolve/538395897d14a7d8249a14eadb97ff262ee865e6/data/train-00000-of-00002-a20c3927bf1ab875.parquet": {
+      "num_bytes": 38449237,
+      "checksum": "ee977442c445508ae065e6b50eb0be0142b238e8289a827dc4fd5bf3454832ae"
+    },
+    "https://huggingface.co/datasets/SDbiaseval/identities/resolve/538395897d14a7d8249a14eadb97ff262ee865e6/data/train-00001-of-00002-b6de4065e8668eee.parquet": {
+      "num_bytes": 427536805,
+      "checksum": "01cd7c1933a747c877ce4953db32aca02ca076d36f5edc272eb1f76b480eed96"
+    }
+  },
+  "download_size": 465986042,
+  "features": {
+    "ethnicity": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "gender": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "no": {
+      "dtype": "int32",
+      "_type": "Value"
+    },
+    "image_path": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "image": {
+      "_type": "Image"
+    },
+    "model": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "colorfulness": {
+      "dtype": "float64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 1051331387,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 585345345,
+      "num_examples": 2040,
+      "dataset_name": "parquet"
+    }
+  }
+}

color-sorted/state.json

@@ -0,0 +1,14 @@
+{
+  "_data_files": [
+    {
+      "filename": "dataset.arrow"
+    }
+  ],
+  "_fingerprint": "d5cb759a141f776e",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_indexes": {},
+  "_output_all_columns": false,
+  "_split": "train"
+}

requirements.txt

@@ -0,0 +1,2 @@
+datasets[vision]
+numpy