[fbsync] fix caltech dataset downloads (#5789)

Summary: (Note: this ignores all push blocking failures!)

Reviewed By: jdsgomes, NicolasHug

Differential Revision: D36095643

fbshipit-source-id: 3165f1891c2760a99ace01fdcee28792028cf20e

Author: YosuaMichael

torchvision/datasets/caltech.py

@@ -129,13 +129,15 @@ def download(self) -> None:
             return
 
         download_and_extract_archive(
-            "http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz",
+            "https://drive.google.com/file/d/137RyRjvTBkBiIfeYBNZBtViDHQ6_Ewsp",
             self.root,
+            filename="101_ObjectCategories.tar.gz",
             md5="b224c7392d521a49829488ab0f1120d9",
         )
         download_and_extract_archive(
-            "http://www.vision.caltech.edu/Image_Datasets/Caltech101/Annotations.tar",
+            "https://drive.google.com/file/d/175kQy3UsZ0wUEHZjqkUDdNVssr7bgh_m",
             self.root,
+            filename="Annotations.tar",
             md5="6f83eeb1f24d99cab4eb377263132c91",
         )
 
@@ -228,7 +230,7 @@ def download(self) -> None:
             return
 
         download_and_extract_archive(
-            "http://www.vision.caltech.edu/Image_Datasets/Caltech256/256_ObjectCategories.tar",
+            "https://drive.google.com/file/d/1r6o0pSROcV1_VwT4oSjA2FBUSCWGuxLK",
             self.root,
             filename="256_ObjectCategories.tar",
             md5="67b4f42ca05d46448c6bb8ecd2220f6d",

torchvision/prototype/datasets/_builtin/caltech.py

@@ -9,7 +9,7 @@
     Filter,
     IterKeyZipper,
 )
-from torchvision.prototype.datasets.utils import Dataset, HttpResource, OnlineResource
+from torchvision.prototype.datasets.utils import Dataset, GDriveResource, OnlineResource
 from torchvision.prototype.datasets.utils._internal import (
     INFINITE_BUFFER_SIZE,
     read_mat,
@@ -49,13 +49,15 @@ def __init__(
         )
 
     def _resources(self) -> List[OnlineResource]:
-        images = HttpResource(
-            "http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz",
+        images = GDriveResource(
+            "137RyRjvTBkBiIfeYBNZBtViDHQ6_Ewsp",
+            file_name="101_ObjectCategories.tar.gz",
             sha256="af6ece2f339791ca20f855943d8b55dd60892c0a25105fcd631ee3d6430f9926",
             preprocess="decompress",
         )
-        anns = HttpResource(
-            "http://www.vision.caltech.edu/Image_Datasets/Caltech101/Annotations.tar",
+        anns = GDriveResource(
+            "175kQy3UsZ0wUEHZjqkUDdNVssr7bgh_m",
+            file_name="Annotations.tar",
             sha256="1717f4e10aa837b05956e3f4c94456527b143eec0d95e935028b30aff40663d8",
         )
         return [images, anns]
@@ -171,8 +173,9 @@ def __init__(
 
     def _resources(self) -> List[OnlineResource]:
         return [
-            HttpResource(
-                "http://www.vision.caltech.edu/Image_Datasets/Caltech256/256_ObjectCategories.tar",
+            GDriveResource(
+                "1r6o0pSROcV1_VwT4oSjA2FBUSCWGuxLK",
+                file_name="256_ObjectCategories.tar",
                 sha256="08ff01b03c65566014ae88eb0490dbe4419fc7ac4de726ee1163e39fd809543e",
             )
         ]

torchvision/prototype/datasets/_builtin/cub200.py

@@ -13,11 +13,7 @@
     CSVParser,
     CSVDictParser,
 )
-from torchvision.prototype.datasets.utils import (
-    Dataset,
-    HttpResource,
-    OnlineResource,
-)
+from torchvision.prototype.datasets.utils import Dataset, GDriveResource, OnlineResource
 from torchvision.prototype.datasets.utils._internal import (
     INFINITE_BUFFER_SIZE,
     read_mat,
@@ -71,30 +67,35 @@ def __init__(
 
     def _resources(self) -> List[OnlineResource]:
         if self._year == "2011":
-            archive = HttpResource(
-                "http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz",
+            archive = GDriveResource(
+                "1hbzc_P1FuxMkcabkgn9ZKinBwW683j45",
+                file_name="CUB_200_2011.tgz",
                 sha256="0c685df5597a8b24909f6a7c9db6d11e008733779a671760afef78feb49bf081",
                 preprocess="decompress",
             )
-            segmentations = HttpResource(
-                "http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/segmentations.tgz",
+            segmentations = GDriveResource(
+                "1EamOKGLoTuZdtcVYbHMWNpkn3iAVj8TP",
+                file_name="segmentations.tgz",
                 sha256="dc77f6cffea0cbe2e41d4201115c8f29a6320ecb04fffd2444f51b8066e4b84f",
                 preprocess="decompress",
             )
             return [archive, segmentations]
         else:  # self._year == "2010"
-            split = HttpResource(
-                "http://www.vision.caltech.edu/visipedia-data/CUB-200/lists.tgz",
+            split = GDriveResource(
+                "1vZuZPqha0JjmwkdaS_XtYryE3Jf5Q1AC",
+                file_name="lists.tgz",
                 sha256="aeacbd5e3539ae84ea726e8a266a9a119c18f055cd80f3836d5eb4500b005428",
                 preprocess="decompress",
             )
-            images = HttpResource(
-                "http://www.vision.caltech.edu/visipedia-data/CUB-200/images.tgz",
+            images = GDriveResource(
+                "1GDr1OkoXdhaXWGA8S3MAq3a522Tak-nx",
+                file_name="images.tgz",
                 sha256="2a6d2246bbb9778ca03aa94e2e683ccb4f8821a36b7f235c0822e659d60a803e",
                 preprocess="decompress",
             )
-            anns = HttpResource(
-                "http://www.vision.caltech.edu/visipedia-data/CUB-200/annotations.tgz",
+            anns = GDriveResource(
+                "16NsbTpMs5L6hT4hUJAmpW2u7wH326WTR",
+                file_name="annotations.tgz",
                 sha256="c17b7841c21a66aa44ba8fe92369cc95dfc998946081828b1d7b8a4b716805c1",
                 preprocess="decompress",
             )