Upload 2 files

datasets/animelover/genshin-impact-images/genshin-impact-images.py

@@ -0,0 +1,52 @@
+import os
+import datasets
+from huggingface_hub import HfApi
+from datasets import DownloadManager, DatasetInfo
+from datasets.data_files import DataFilesDict
+
+_EXTENSION = [".png", ".jpg", ".jpeg"]
+_DESCRIPTION = ""
+_NAME = "animelover/genshin-impact-images"
+_REVISION = "main"
+
+
+class DanbooruDataset(datasets.GeneratorBasedBuilder):
+
+    def _info(self) -> DatasetInfo:
+        return datasets.DatasetInfo(
+            description=_DESCRIPTION,
+            features=datasets.Features(
+                {
+                    "image": datasets.Image(),
+                    "tags": datasets.Value("string")
+                }
+            ),
+            supervised_keys=None,
+            citation="",
+        )
+
+    def _split_generators(self, dl_manager: DownloadManager):
+        hfh_dataset_info = HfApi().dataset_info(_NAME, revision=_REVISION, timeout=100.0)
+        data_files = DataFilesDict.from_hf_repo(
+            {datasets.Split.TRAIN: ["**"]},
+            dataset_info=hfh_dataset_info,
+            allowed_extensions=["zip"],
+        )
+        gs = []
+        for split, files in data_files.items():
+            downloaded_files = dl_manager.download_and_extract(files)
+            gs.append(datasets.SplitGenerator(name=split, gen_kwargs={"filepath": downloaded_files}))
+        return gs
+
+    def _generate_examples(self, filepath):
+        for path in filepath:
+            all_fnames = {os.path.relpath(os.path.join(root, fname), start=path)
+                          for root, _dirs, files in os.walk(path) for fname in files}
+            image_fnames = sorted(fname for fname in all_fnames
+                                  if os.path.splitext(fname)[1].lower() in _EXTENSION)
+            for image_fname in image_fnames:
+                image_path = os.path.join(path, image_fname)
+                tags_path = os.path.join(path, os.path.splitext(image_fname)[0] + ".txt") 
+                with open(tags_path, "r", encoding="utf-8") as f:
+                    tags = f.read()
+                yield image_fname, {"image": image_path, "tags": tags}

datasets/animelover/genshin-impact-images/gitattributes.txt

@@ -0,0 +1,54 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text