Duplicate from tti-bias/identities-bovw-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 BOVW k-nn
+emoji: 📉
+colorFrom: green
+colorTo: red
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: tti-bias/identities-bovw-knn
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+from datasets import load_dataset
+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]
+indexes = [768, 1536, 10752]
+ds = load_dataset("tti-bias/identities", split="train")
+
+def get_nearest_64(gender, ethnicity, model, no, index):
+    df = ds.remove_columns(["image","image_path"]).to_pandas()
+    index = np.load(f"indexes/knn_{index}_65.npy")
+    ix = df.loc[(df['ethnicity'] == ethnicity)  & (df['gender'] == gender) & (df['no'] == no) & (df['model'] == model)].index[0]
+    image = ds.select([index[ix][0]])["image"][0]
+    neighbors =  ds.select(index[ix][1:25])
+    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("# BoVW Nearest Neighbors Explorer")
+    gr.Markdown("### TF-IDF index of the _identities_ dataset of images generated by 3 models using a visual vocabulary of 10,752 words.")
+    gr.Markdown("#### Choose one of the generated identity images to see its nearest neighbors according to a bag-of-visual-words model.")
+    with gr.Row():
+        with gr.Column():
+            model = gr.Radio(models, label="Model")
+            index = gr.Radio(indexes, label="Visual vocabulary size")
+            gender = gr.Radio(gender_labels, label="Gender label")
+        with gr.Column():
+            ethnicity = gr.Radio(ethnicity_labels, label="Ethnicity label")
+            no = gr.Radio(nos, label="Image number")
+    button = gr.Button(value="Get nearest neighbors")
+    with gr.Row():
+        image = gr.Image()
+        gallery = gr.Gallery().style(grid=4)
+    button.click(get_nearest_64, inputs=[gender, ethnicity, model, no, index], outputs=[image, gallery])
+demo.launch()

indexes/knn_10752_65.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47eb9dbb1b403c0533e09336bd592125a0db83f2c122ca267bbc05fc877d05c1
+size 530528

indexes/knn_1536_65.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2929f63867d439eb36f73bf4ad6056a036def14a7176149afddb884f4b9703
+size 530528

indexes/knn_768_65.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06c06fd8388b6013446468832b1a2087144b651e7c5f065eb9ee6a381c86a8e
+size 530528

requirements.txt

@@ -0,0 +1,3 @@
+datasets[vision]
+numpy
+imutils