Update (base update)

[ghstack-poisoned]

Author: NicolasHug

torchvision/datasets/_stereo_matching.py

@@ -588,7 +588,6 @@ def _download_dataset(self, root: Union[str, Path]) -> None:
                 for calibration in ["perfect", "imperfect"]:
                     scene_name = f"{split_scene}-{calibration}"
                     scene_url = f"{base_url}/{scene_name}.zip"
-                    print(f"Downloading {scene_url}")
                     # download the scene only if it doesn't exist
                     if not (split_root / scene_name).exists():
                         download_and_extract_archive(

torchvision/datasets/inaturalist.py

@@ -239,4 +239,3 @@ def download(self) -> None:
         if not os.path.exists(orig_dir_name):
             raise RuntimeError(f"Unable to find downloaded files at {orig_dir_name}")
         os.rename(orig_dir_name, self.root)
-        print(f"Dataset version '{self.version}' has been downloaded and prepared for use")

torchvision/datasets/kinetics.py

@@ -1,6 +1,5 @@
 import csv
 import os
-import time
 import urllib
 from functools import partial
 from multiprocessing import Pool
@@ -121,7 +120,6 @@ def __init__(
         self._legacy = _legacy
 
         if _legacy:
-            print("Using legacy structure")
             self.split_folder = root
             self.split = "unknown"
             output_format = "THWC"
@@ -157,14 +155,8 @@ def __init__(
 
     def download_and_process_videos(self) -> None:
         """Downloads all the videos to the _root_ folder in the expected format."""
-        tic = time.time()
         self._download_videos()
-        toc = time.time()
-        print("Elapsed time for downloading in mins ", (toc - tic) / 60)
         self._make_ds_structure()
-        toc2 = time.time()
-        print("Elapsed time for processing in mins ", (toc2 - toc) / 60)
-        print("Elapsed time overall in mins ", (toc2 - tic) / 60)
 
     def _download_videos(self) -> None:
         """download tarballs containing the video to "tars" folder and extract them into the _split_ folder where

torchvision/datasets/mnist.py

@@ -181,19 +181,20 @@ def download(self) -> None:
 
         # download files
         for filename, md5 in self.resources:
+            errors = []
             for mirror in self.mirrors:
                 url = f"{mirror}{filename}"
                 try:
-                    print(f"Downloading {url}")
                     download_and_extract_archive(url, download_root=self.raw_folder, filename=filename, md5=md5)
-                except URLError as error:
-                    print(f"Failed to download (trying next):\n{error}")
+                except URLError as e:
+                    errors.append(e)
                     continue
-                finally:
-                    print()
                 break
             else:
-                raise RuntimeError(f"Error downloading {filename}")
+                s = f"Error downloading {filename}:\n"
+                for mirror, e in zip(self.mirrors, errors):
+                    s += f"Tried {mirror}, got:\n{str(e)}\n"
+                raise RuntimeError(s)
 
     def extra_repr(self) -> str:
         split = "Train" if self.train is True else "Test"

torchvision/datasets/phototour.py

@@ -145,7 +145,6 @@ def _check_downloaded(self) -> bool:
 
     def download(self) -> None:
         if self._check_datafile_exists():
-            print(f"# Found cached data {self.data_file}")
             return
 
         if not self._check_downloaded():
@@ -157,8 +156,6 @@ def download(self) -> None:
 
             download_url(url, self.root, filename, md5)
 
-            print(f"# Extracting data {self.data_down}\n")
-
             import zipfile
 
             with zipfile.ZipFile(fpath, "r") as z:
@@ -168,7 +165,6 @@ def download(self) -> None:
 
     def cache(self) -> None:
         # process and save as torch files
-        print(f"# Caching data {self.data_file}")
 
         dataset = (
             read_image_file(self.data_dir, self.image_ext, self.lens[self.name]),

torchvision/datasets/utils.py

@@ -112,7 +112,6 @@ def download_url(
 
     # check if file is already present locally
     if check_integrity(fpath, md5):
-        print("Using downloaded and verified file: " + fpath)
         return
 
     if _is_remote_location_available():
@@ -128,12 +127,10 @@ def download_url(
 
         # download the file
         try:
-            print("Downloading " + url + " to " + fpath)
             _urlretrieve(url, fpath)
         except (urllib.error.URLError, OSError) as e:  # type: ignore[attr-defined]
             if url[:5] == "https":
                 url = url.replace("https:", "http:")
-                print("Failed download. Trying https -> http instead. Downloading " + url + " to " + fpath)
                 _urlretrieve(url, fpath)
             else:
                 raise e
@@ -204,7 +201,6 @@ def download_file_from_google_drive(
     os.makedirs(root, exist_ok=True)
 
     if check_integrity(fpath, md5):
-        print(f"Using downloaded {'and verified ' if md5 else ''}file: {fpath}")
         return
 
     gdown.download(id=file_id, output=fpath, quiet=False, user_agent=USER_AGENT)
@@ -395,7 +391,6 @@ def download_and_extract_archive(
     download_url(url, download_root, filename, md5)
 
     archive = os.path.join(download_root, filename)
-    print(f"Extracting {archive} to {extract_root}")
     extract_archive(archive, extract_root, remove_finished)