sps44 commited on
Commit
92e6506
0 Parent(s):

Duplicate from renumics/cifar100-sliceguard-demo

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.whl filter=lfs diff=lfs merge=lfs -text
2
+ *.7z filter=lfs diff=lfs merge=lfs -text
3
+ *.arrow filter=lfs diff=lfs merge=lfs -text
4
+ *.bin filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
7
+ *.ftz filter=lfs diff=lfs merge=lfs -text
8
+ *.gz filter=lfs diff=lfs merge=lfs -text
9
+ *.h5 filter=lfs diff=lfs merge=lfs -text
10
+ *.joblib filter=lfs diff=lfs merge=lfs -text
11
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
12
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
13
+ *.model filter=lfs diff=lfs merge=lfs -text
14
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
15
+ *.npy filter=lfs diff=lfs merge=lfs -text
16
+ *.npz filter=lfs diff=lfs merge=lfs -text
17
+ *.onnx filter=lfs diff=lfs merge=lfs -text
18
+ *.ot filter=lfs diff=lfs merge=lfs -text
19
+ *.parquet filter=lfs diff=lfs merge=lfs -text
20
+ *.pb filter=lfs diff=lfs merge=lfs -text
21
+ *.pickle filter=lfs diff=lfs merge=lfs -text
22
+ *.pkl filter=lfs diff=lfs merge=lfs -text
23
+ *.pt filter=lfs diff=lfs merge=lfs -text
24
+ *.pth filter=lfs diff=lfs merge=lfs -text
25
+ *.rar filter=lfs diff=lfs merge=lfs -text
26
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
27
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+
2
+ .venv/
Dockerfile ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.9
2
+
3
+ WORKDIR /code
4
+ ENV HOME=/code
5
+ COPY ./renumics_spotlight-1.3.0.post9+b32d1a8-py3-none-any.whl /code/renumics_spotlight-1.3.0.post9+b32d1a8-py3-none-any.whl
6
+ # RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
7
+
8
+ RUN apt install curl
9
+ RUN pip install pip -U
10
+
11
+ RUN pip install renumics_spotlight-1.3.0.post9+b32d1a8-py3-none-any.whl
12
+
13
+
14
+ RUN pip install pyarrow datasets cleanvision
15
+
16
+ COPY . .
17
+ RUN mkdir -p /code/.cache
18
+ RUN chmod -R 777 /code
19
+ RUN python prepare.py
20
+ CMD ["python", "run.py"]
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Explore data slices in the CIFAR-100 benchmark
3
+ emoji: 📊
4
+ colorFrom: gray
5
+ colorTo: blue
6
+ sdk: docker
7
+ pinned: false
8
+ license: mit
9
+ app_file: run.py
10
+ datasets:
11
+ - renumics/cifar100-enriched
12
+ - cifar100
13
+ tags:
14
+ - renumics
15
+ - spotlight
16
+ - sliceline
17
+ - data-centric-ai
18
+ duplicated_from: renumics/cifar100-sliceguard-demo
19
+ ---
20
+
21
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
cifar100-enrichment-cv.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc7e67b598b765cce75309f7c414a13ca9fcc8004f436a0490822c899bfa66c
3
+ size 544628
prepare.py ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ import datasets
3
+ import os
4
+ import pandas as pd
5
+
6
+ if __name__ == "__main__":
7
+ cache_file = "dataset_cache.parquet"
8
+ if os.path.exists(cache_file):
9
+ # Load dataset from cache
10
+ df = pd.read_parquet(cache_file)
11
+ print("Dataset loaded from cache.")
12
+ else:
13
+ # Load dataset using datasets.load_dataset()
14
+ dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
15
+ print("Dataset loaded using datasets.load_dataset().")
16
+
17
+ df = dataset.to_pandas()
18
+
19
+ # Save dataset to cache
20
+ df.to_parquet(cache_file)
21
+
22
+ print("Dataset saved to cache.")
23
+
renumics_spotlight-1.3.0.post9+b32d1a8-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f23ad15279cfeebb210ccd9ca29dc30075d5f9b61934cb23b55d07207317a5
3
+ size 2494250
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ renumics-spotlight
2
+ datasets
3
+ fastparquet
run.py ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ import datasets
3
+ from renumics import spotlight
4
+ import os
5
+ import pandas as pd
6
+
7
+ if __name__ == "__main__":
8
+ cache_file = "dataset_cache.parquet"
9
+ cache_file_enrichment="cifar100-enrichment-cv.parquet"
10
+ cache_file_issues="sliceguard-issues.pkl"
11
+
12
+ if os.path.exists(cache_file):
13
+ # Load dataset from cache
14
+ df = pd.read_parquet(cache_file)
15
+ print("Dataset loaded from cache.")
16
+ else:
17
+ # Load dataset using datasets.load_dataset()
18
+ dataset = datasets.load_dataset("renumics/cifar100-enriched", split="test")
19
+ print("Dataset loaded using datasets.load_dataset().")
20
+
21
+ df = dataset.to_pandas()
22
+
23
+ # Save dataset to cache
24
+ df.to_parquet(cache_file)
25
+
26
+ print("Dataset saved to cache.")
27
+
28
+ df_cv=pd.read_parquet(cache_file_enrichment)
29
+
30
+ df = pd.concat([df, df_cv], axis=1)
31
+
32
+ with open(cache_file_issues, "rb") as issue_file:
33
+ issues = pickle.load(issue_file)
34
+
35
+ #df = dataset.to_pandas()
36
+ df_show = df.drop(columns=['embedding', 'probabilities'])
37
+ while True:
38
+ view = spotlight.show(df_show, issues=issues, port=7860, host="0.0.0.0", layout="sliceguard-layout.json",
39
+ dtype={"image": spotlight.Image, "embedding_reduced": spotlight.Embedding}, allow_filebrowsing=False)
40
+ view.close()
sliceguard-issues.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2c652c7600f011f0225e9e6fc9c133781409f7d1a1b4ce3a1c5871809cda25
3
+ size 22835
sliceguard-layout.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"orientation":"vertical","children":[{"kind":"split","weight":55.98243688254665,"orientation":"horizontal","children":[{"kind":"tab","weight":30.029340660631746,"children":[{"kind":"widget","name":"Table","type":"table","config":{"tableView":"full","visibleColumns":null,"sorting":null,"orderByRelevance":false}}]},{"kind":"tab","weight":27.735432693500154,"children":[{"kind":"widget","name":"Similarity Map","type":"similaritymap","config":{"placeBy":null,"reductionMethod":null,"colorBy":"fine_label_prediction_error","sizeBy":null,"filter":false,"umapNNeighbors":20,"umapMetric":null,"umapMinDist":0.15,"pcaNormalization":null,"umapMenuLocalGlobalBalance":null,"umapMenuIsAdvanced":false}}]},{"kind":"tab","weight":42.235226645868096,"children":[{"kind":"widget","name":"Issues","type":"IssuesWidget","config":null},{"kind":"widget","name":"Scatter Plot","type":"scatterplot","config":{"xAxisColumn":null,"yAxisColumn":null,"colorBy":null,"sizeBy":null,"filter":false}},{"kind":"widget","name":"Histogram","type":"histogram","config":{"columnKey":"dark_score","stackByColumnKey":"fine_label_prediction_error","filter":false}}]}]},{"kind":"tab","weight":44.01756311745335,"children":[{"kind":"widget","name":"Inspector","type":"inspector","config":{"views":[{"view":"ImageView","columns":["full_image"],"name":"full_image","key":"8GcjVfK27yKRQzznAqWMRG"},{"view":"TextLens","columns":["fine_label_prediction_str"],"name":"view","key":"797cd1ce-e56a-42de-87ac-f82d09a4f519"},{"view":"TextLens","columns":["fine_label_str"],"name":"view","key":"37df2c98-2676-4479-9984-8b30516fcf40"}],"visibleColumns":4}}]}]}