Add catalog v1.2 benchmark datasets

.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 .

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"
+}

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"
+}

manifests/cifar100/1.0.json

@@ -0,0 +1,15 @@
+{
+  "artifacts": {
+    "python": {
+      "path": "datasets/cifar100/1.0/archives/cifar-100-python.tar.gz",
+      "sha256": "85cd44d02ba6437773c5bbd22e183051d648de2e7d6b014e1ef29b855ba677a7",
+      "size": 169001437
+    }
+  },
+  "dataset": "cifar100",
+  "recipe_sha256": "e8c903a8782dc41445f6f87173c3adaad881c106302bf357bc24bc1cecb6b64a",
+  "schema_version": 1,
+  "terms_reviewed": true,
+  "total_bytes": 169001437,
+  "version": "1.0"
+}

manifests/cinic10/1.0.json

@@ -0,0 +1,15 @@
+{
+  "artifacts": {
+    "archive": {
+      "path": "datasets/cinic10/1.0/archives/CINIC-10.tar.gz",
+      "sha256": "31b095acf6d75e25a9e028bae82a07a0f94ff6b00671be2802d34ac4efa81a9e",
+      "size": 687544992
+    }
+  },
+  "dataset": "cinic10",
+  "recipe_sha256": "24ac99f24f73d19581f44f67cb5551677daa21594ea97a5311d8b5198b48aff5",
+  "schema_version": 1,
+  "terms_reviewed": true,
+  "total_bytes": 687544992,
+  "version": "1.0"
+}

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"
+}

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"
+}

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"
+}

manifests/gtsrb/1.0.json

@@ -0,0 +1,25 @@
+{
+  "artifacts": {
+    "test_images": {
+      "path": "datasets/gtsrb/1.0/archives/GTSRB_Final_Test_Images.zip",
+      "sha256": "48ba6fab7e877eb64eaf8de99035b0aaecfbc279bee23e35deca4ac1d0a837fa",
+      "size": 88978620
+    },
+    "test_labels": {
+      "path": "datasets/gtsrb/1.0/archives/GTSRB_Final_Test_GT.zip",
+      "sha256": "f94e5a7614d75845c74c04ddb26b8796b9e483f43541dd95dd5b726504e16d6d",
+      "size": 99620
+    },
+    "train": {
+      "path": "datasets/gtsrb/1.0/archives/GTSRB-Training_fixed.zip",
+      "sha256": "df4144942083645bd60b594de348aa6930126c3e0e5de09e39611630abf8455a",
+      "size": 187490228
+    }
+  },
+  "dataset": "gtsrb",
+  "recipe_sha256": "441252cf42c35ae9a55d6a5a9cf569b03cbbf7f79b9c94aec4e18ee0d43f1977",
+  "schema_version": 1,
+  "terms_reviewed": true,
+  "total_bytes": 276568468,
+  "version": "1.0"
+}

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"
+}

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"
+}

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"
+}

manifests/svhn/1.0.json

@@ -0,0 +1,20 @@
+{
+  "artifacts": {
+    "test": {
+      "path": "datasets/svhn/1.0/archives/test_32x32.mat",
+      "sha256": "cdce80dfb2a2c4c6160906d0bd7c68ec5a99d7ca4831afa54f09182025b6a75b",
+      "size": 64275384
+    },
+    "train": {
+      "path": "datasets/svhn/1.0/archives/train_32x32.mat",
+      "sha256": "435e94d69a87fde4fd4d7f3dd208dfc32cb6ae8af2240d066de1df7508d083b8",
+      "size": 182040794
+    }
+  },
+  "dataset": "svhn",
+  "recipe_sha256": "08acaebe2a45ab5cc43122fb3a2449fe96895131051cc5219f826dd311e30eac",
+  "schema_version": 1,
+  "terms_reviewed": true,
+  "total_bytes": 246316178,
+  "version": "1.0"
+}