From 00adae5ce05f0d83a593483643965f0310bc05b3 Mon Sep 17 00:00:00 2001 From: syafiq Date: Wed, 16 Sep 2026 08:05:55 +0800 Subject: [PATCH] Add catalog v1.2 benchmark datasets --- .gitea/workflows/validate.yml | 2 +- .../bloodmnist/2.0/archives/bloodmnist.npz | 3 ++ .../caltech101/1.0/archives/caltech-101.zip | 3 ++ .../dermamnist/2.0/archives/dermamnist.npz | 3 ++ datasets/eurosat/1.0/archives/EuroSAT_RGB.zip | 3 ++ .../1.0/archives/t10k-images-idx3-ubyte.gz | 3 ++ .../1.0/archives/t10k-labels-idx1-ubyte.gz | 3 ++ .../1.0/archives/train-images-idx3-ubyte.gz | 3 ++ .../1.0/archives/train-labels-idx1-ubyte.gz | 3 ++ .../organamnist/2.0/archives/organamnist.npz | 3 ++ datasets/pathmnist/2.0/archives/pathmnist.npz | 3 ++ .../stl10/1.0/archives/stl10_binary.tar.gz | 3 ++ manifests/bloodmnist/2.0.json | 15 ++++++++++ manifests/caltech101/1.0.json | 15 ++++++++++ manifests/dermamnist/2.0.json | 15 ++++++++++ manifests/eurosat/1.0.json | 15 ++++++++++ manifests/fashionmnist/1.0.json | 30 +++++++++++++++++++ manifests/organamnist/2.0.json | 15 ++++++++++ manifests/pathmnist/2.0.json | 15 ++++++++++ manifests/stl10/1.0.json | 15 ++++++++++ 20 files changed, 169 insertions(+), 1 deletion(-) create mode 100644 datasets/bloodmnist/2.0/archives/bloodmnist.npz create mode 100644 datasets/caltech101/1.0/archives/caltech-101.zip create mode 100644 datasets/dermamnist/2.0/archives/dermamnist.npz create mode 100644 datasets/eurosat/1.0/archives/EuroSAT_RGB.zip create mode 100644 datasets/fashionmnist/1.0/archives/t10k-images-idx3-ubyte.gz create mode 100644 datasets/fashionmnist/1.0/archives/t10k-labels-idx1-ubyte.gz create mode 100644 datasets/fashionmnist/1.0/archives/train-images-idx3-ubyte.gz create mode 100644 datasets/fashionmnist/1.0/archives/train-labels-idx1-ubyte.gz create mode 100644 datasets/organamnist/2.0/archives/organamnist.npz create mode 100644 datasets/pathmnist/2.0/archives/pathmnist.npz create mode 100644 datasets/stl10/1.0/archives/stl10_binary.tar.gz create mode 100644 manifests/bloodmnist/2.0.json create mode 100644 manifests/caltech101/1.0.json create mode 100644 manifests/dermamnist/2.0.json create mode 100644 manifests/eurosat/1.0.json create mode 100644 manifests/fashionmnist/1.0.json create mode 100644 manifests/organamnist/2.0.json create mode 100644 manifests/pathmnist/2.0.json create mode 100644 manifests/stl10/1.0.json diff --git a/.gitea/workflows/validate.yml b/.gitea/workflows/validate.yml index 50dd0d2..b9934bb 100644 --- a/.gitea/workflows/validate.yml +++ b/.gitea/workflows/validate.yml @@ -8,6 +8,6 @@ jobs: with: lfs: true - run: git lfs fsck - - run: git clone --depth 1 --branch source-v0.2.0 https://github.com/spozi/kd-repair.git /tmp/kd-repair + - run: git clone --depth 1 --branch source-v0.3.1 https://github.com/spozi/kd-repair.git /tmp/kd-repair - run: python -m pip install -e /tmp/kd-repair --no-deps - run: python -m kd dataset registry-verify --registry-root . diff --git a/datasets/bloodmnist/2.0/archives/bloodmnist.npz b/datasets/bloodmnist/2.0/archives/bloodmnist.npz new file mode 100644 index 0000000..ca7570c --- /dev/null +++ b/datasets/bloodmnist/2.0/archives/bloodmnist.npz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062023e186f537e26b3c21ea3b2614ddfc475e8a14825dfd20663bbb7e37bddc +size 35461855 diff --git a/datasets/caltech101/1.0/archives/caltech-101.zip b/datasets/caltech101/1.0/archives/caltech-101.zip new file mode 100644 index 0000000..beb2095 --- /dev/null +++ b/datasets/caltech101/1.0/archives/caltech-101.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331234750fc7f77520e50d9565e8b6907b03565e30320da1401130db08c61f91 +size 137414764 diff --git a/datasets/dermamnist/2.0/archives/dermamnist.npz b/datasets/dermamnist/2.0/archives/dermamnist.npz new file mode 100644 index 0000000..b77c18a --- /dev/null +++ b/datasets/dermamnist/2.0/archives/dermamnist.npz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a309fec2e33bb6aba88e7d078e5ccbb9736c84a0b415ac197eb3c8fa331e050 +size 19725078 diff --git a/datasets/eurosat/1.0/archives/EuroSAT_RGB.zip b/datasets/eurosat/1.0/archives/EuroSAT_RGB.zip new file mode 100644 index 0000000..29fb3e6 --- /dev/null +++ b/datasets/eurosat/1.0/archives/EuroSAT_RGB.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f5b234ecb7d7ff9c6cddb046543b4717c53fd6e9815be6c0e80cc614f51b90 +size 94658721 diff --git a/datasets/fashionmnist/1.0/archives/t10k-images-idx3-ubyte.gz b/datasets/fashionmnist/1.0/archives/t10k-images-idx3-ubyte.gz new file mode 100644 index 0000000..e07f380 --- /dev/null +++ b/datasets/fashionmnist/1.0/archives/t10k-images-idx3-ubyte.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346e55b948d973a97e58d2351dde16a484bd415d4595297633bb08f03db6a073 +size 4422102 diff --git a/datasets/fashionmnist/1.0/archives/t10k-labels-idx1-ubyte.gz b/datasets/fashionmnist/1.0/archives/t10k-labels-idx1-ubyte.gz new file mode 100644 index 0000000..b203da4 --- /dev/null +++ b/datasets/fashionmnist/1.0/archives/t10k-labels-idx1-ubyte.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67da17c76eaffca5446c3361aaab5c3cd6d1c2608764d35dfb1850b086bf8dd5 +size 5148 diff --git a/datasets/fashionmnist/1.0/archives/train-images-idx3-ubyte.gz b/datasets/fashionmnist/1.0/archives/train-images-idx3-ubyte.gz new file mode 100644 index 0000000..91fb354 --- /dev/null +++ b/datasets/fashionmnist/1.0/archives/train-images-idx3-ubyte.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aede38d61863908ad78613f6a32ed271626dd12800ba2636569512369268a84 +size 26421880 diff --git a/datasets/fashionmnist/1.0/archives/train-labels-idx1-ubyte.gz b/datasets/fashionmnist/1.0/archives/train-labels-idx1-ubyte.gz new file mode 100644 index 0000000..371f432 --- /dev/null +++ b/datasets/fashionmnist/1.0/archives/train-labels-idx1-ubyte.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04f17134ac03560a47e3764e11b92fc97de4d1bfaf8ba1a3aa29af54cc90845 +size 29515 diff --git a/datasets/organamnist/2.0/archives/organamnist.npz b/datasets/organamnist/2.0/archives/organamnist.npz new file mode 100644 index 0000000..c4e3e2e --- /dev/null +++ b/datasets/organamnist/2.0/archives/organamnist.npz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8c8b0753e2c0d7f70928817eac02be7cbb09f6beff4346e9d0ea79ecb598bd +size 38247708 diff --git a/datasets/pathmnist/2.0/archives/pathmnist.npz b/datasets/pathmnist/2.0/archives/pathmnist.npz new file mode 100644 index 0000000..27a9971 --- /dev/null +++ b/datasets/pathmnist/2.0/archives/pathmnist.npz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81823f52dc622e69db2db4c72f8e8e617938dd6864d3c1f23d4e49724a28ea72 +size 205615438 diff --git a/datasets/stl10/1.0/archives/stl10_binary.tar.gz b/datasets/stl10/1.0/archives/stl10_binary.tar.gz new file mode 100644 index 0000000..c051ab9 --- /dev/null +++ b/datasets/stl10/1.0/archives/stl10_binary.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31fd99273a1acb8609c8db427cebb1de3f71de77758cdc0e22956e1289b9866 +size 2640397119 diff --git a/manifests/bloodmnist/2.0.json b/manifests/bloodmnist/2.0.json new file mode 100644 index 0000000..d47299c --- /dev/null +++ b/manifests/bloodmnist/2.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "npz": { + "path": "datasets/bloodmnist/2.0/archives/bloodmnist.npz", + "sha256": "062023e186f537e26b3c21ea3b2614ddfc475e8a14825dfd20663bbb7e37bddc", + "size": 35461855 + } + }, + "dataset": "bloodmnist", + "recipe_sha256": "7274ded6a3d584404c87615137b2a88d58e82d4d79bde07ee5781f2f77012875", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 35461855, + "version": "2.0" +} diff --git a/manifests/caltech101/1.0.json b/manifests/caltech101/1.0.json new file mode 100644 index 0000000..4aee044 --- /dev/null +++ b/manifests/caltech101/1.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "archive": { + "path": "datasets/caltech101/1.0/archives/caltech-101.zip", + "sha256": "331234750fc7f77520e50d9565e8b6907b03565e30320da1401130db08c61f91", + "size": 137414764 + } + }, + "dataset": "caltech101", + "recipe_sha256": "e888ea4aef55dddd2b1c4cb05fe309de5f293841d08e9b015dbe6445d1b7d658", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 137414764, + "version": "1.0" +} diff --git a/manifests/dermamnist/2.0.json b/manifests/dermamnist/2.0.json new file mode 100644 index 0000000..699eb6c --- /dev/null +++ b/manifests/dermamnist/2.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "npz": { + "path": "datasets/dermamnist/2.0/archives/dermamnist.npz", + "sha256": "1a309fec2e33bb6aba88e7d078e5ccbb9736c84a0b415ac197eb3c8fa331e050", + "size": 19725078 + } + }, + "dataset": "dermamnist", + "recipe_sha256": "7cf9b32bfa6d95aea229b4b2ec2ee5ed196e216df8c2a9dd140fbbb834df091f", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 19725078, + "version": "2.0" +} diff --git a/manifests/eurosat/1.0.json b/manifests/eurosat/1.0.json new file mode 100644 index 0000000..1059e08 --- /dev/null +++ b/manifests/eurosat/1.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "rgb": { + "path": "datasets/eurosat/1.0/archives/EuroSAT_RGB.zip", + "sha256": "b4f5b234ecb7d7ff9c6cddb046543b4717c53fd6e9815be6c0e80cc614f51b90", + "size": 94658721 + } + }, + "dataset": "eurosat", + "recipe_sha256": "c1c1c38659fdcd9d1b6c6c0ccc3b48a24a7bda63b3f564d33ad3e2ef34a04821", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 94658721, + "version": "1.0" +} diff --git a/manifests/fashionmnist/1.0.json b/manifests/fashionmnist/1.0.json new file mode 100644 index 0000000..85b2e1f --- /dev/null +++ b/manifests/fashionmnist/1.0.json @@ -0,0 +1,30 @@ +{ + "artifacts": { + "test_images": { + "path": "datasets/fashionmnist/1.0/archives/t10k-images-idx3-ubyte.gz", + "sha256": "346e55b948d973a97e58d2351dde16a484bd415d4595297633bb08f03db6a073", + "size": 4422102 + }, + "test_labels": { + "path": "datasets/fashionmnist/1.0/archives/t10k-labels-idx1-ubyte.gz", + "sha256": "67da17c76eaffca5446c3361aaab5c3cd6d1c2608764d35dfb1850b086bf8dd5", + "size": 5148 + }, + "train_images": { + "path": "datasets/fashionmnist/1.0/archives/train-images-idx3-ubyte.gz", + "sha256": "3aede38d61863908ad78613f6a32ed271626dd12800ba2636569512369268a84", + "size": 26421880 + }, + "train_labels": { + "path": "datasets/fashionmnist/1.0/archives/train-labels-idx1-ubyte.gz", + "sha256": "a04f17134ac03560a47e3764e11b92fc97de4d1bfaf8ba1a3aa29af54cc90845", + "size": 29515 + } + }, + "dataset": "fashionmnist", + "recipe_sha256": "ca3a062012b45472c145e51e1912d4d5483aa501f74d2153f5a03c73725a65f1", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 30878645, + "version": "1.0" +} diff --git a/manifests/organamnist/2.0.json b/manifests/organamnist/2.0.json new file mode 100644 index 0000000..4f55313 --- /dev/null +++ b/manifests/organamnist/2.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "npz": { + "path": "datasets/organamnist/2.0/archives/organamnist.npz", + "sha256": "7c8c8b0753e2c0d7f70928817eac02be7cbb09f6beff4346e9d0ea79ecb598bd", + "size": 38247708 + } + }, + "dataset": "organamnist", + "recipe_sha256": "6124a42e5595638a28b0e53a61aa39321507ec8a13436911243df3b95693319f", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 38247708, + "version": "2.0" +} diff --git a/manifests/pathmnist/2.0.json b/manifests/pathmnist/2.0.json new file mode 100644 index 0000000..7117da7 --- /dev/null +++ b/manifests/pathmnist/2.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "npz": { + "path": "datasets/pathmnist/2.0/archives/pathmnist.npz", + "sha256": "81823f52dc622e69db2db4c72f8e8e617938dd6864d3c1f23d4e49724a28ea72", + "size": 205615438 + } + }, + "dataset": "pathmnist", + "recipe_sha256": "0b8da47c8978e4f6eddbd51e54955c3f948bc8134de0054faff36c33c1a3f3ab", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 205615438, + "version": "2.0" +} diff --git a/manifests/stl10/1.0.json b/manifests/stl10/1.0.json new file mode 100644 index 0000000..c64afd2 --- /dev/null +++ b/manifests/stl10/1.0.json @@ -0,0 +1,15 @@ +{ + "artifacts": { + "binary": { + "path": "datasets/stl10/1.0/archives/stl10_binary.tar.gz", + "sha256": "f31fd99273a1acb8609c8db427cebb1de3f71de77758cdc0e22956e1289b9866", + "size": 2640397119 + } + }, + "dataset": "stl10", + "recipe_sha256": "a73ff4cd5ac62fb191163f522b6b08a143f7b8da4ddaef4a711f0758e54e4418", + "schema_version": 1, + "terms_reviewed": true, + "total_bytes": 2640397119, + "version": "1.0" +}