autogluon.multimodal 1.1.2b20241031__py3-none-any.whl → 1.1.2b20241107__py3-none-any.whl

autogluon/multimodal/configs/model/default.yaml

@@ -115,6 +115,7 @@ model:
     max_img_num_per_col: 1
     output_bbox_format: "xyxy"  # now support xyxy or xywh, for bbox format details see https://keras.io/api/keras_cv/bounding_box/formats/
     frozen_layers: null
+    coco_root: null
 
   mmocr_text_detection:
     checkpoint_name: "TextSnake"

autogluon/multimodal/learners/object_detection.py

@@ -74,6 +74,8 @@ class ObjectDetectionLearner(BaseLearner):
         )
         check_if_packages_installed(problem_type=self._problem_type)
 
+        self._config = self.get_config_per_run(config=self._config, hyperparameters=hyperparameters)
+
         self._output_shape = num_classes
         self._classes = classes
         self._sample_data_path = sample_data_path
@@ -102,10 +104,18 @@ class ObjectDetectionLearner(BaseLearner):
     def setup_detection_train_tuning_data(self, max_num_tuning_data, seed, train_data, tuning_data):
         if isinstance(train_data, str):
             self._detection_anno_train = train_data
-            train_data = from_coco_or_voc(train_data, "train")  # TODO: Refactor to use convert_data_to_df
+            train_data = from_coco_or_voc(
+                train_data,
+                "train",
+                coco_root=self._config.model.mmdet_image.coco_root,
+            )  # TODO: Refactor to use convert_data_to_df
             if tuning_data is not None:
                 self.detection_anno_train = tuning_data
-                tuning_data = from_coco_or_voc(tuning_data, "val")  # TODO: Refactor to use convert_data_to_df
+                tuning_data = from_coco_or_voc(
+                    tuning_data,
+                    "val",
+                    coco_root=self._config.model.mmdet_image.coco_root,
+                )  # TODO: Refactor to use convert_data_to_df
                 if max_num_tuning_data is not None:
                     if len(tuning_data) > max_num_tuning_data:
                         tuning_data = tuning_data.sample(
@@ -114,10 +124,16 @@ class ObjectDetectionLearner(BaseLearner):
         elif isinstance(train_data, pd.DataFrame):
             self._detection_anno_train = None
             # sanity check dataframe columns
-            train_data = object_detection_data_to_df(train_data)
+            train_data = object_detection_data_to_df(
+                train_data,
+                coco_root=self._config.model.mmdet_image.coco_root,
+            )
             if tuning_data is not None:
                 self.detection_anno_train = tuning_data
-                tuning_data = object_detection_data_to_df(tuning_data)
+                tuning_data = object_detection_data_to_df(
+                    tuning_data,
+                    coco_root=self._config.model.mmdet_image.coco_root,
+                )
                 if max_num_tuning_data is not None:
                     if len(tuning_data) > max_num_tuning_data:
                         tuning_data = tuning_data.sample(
@@ -556,7 +572,9 @@ class ObjectDetectionLearner(BaseLearner):
         if isinstance(anno_file_or_df, str):
             anno_file = anno_file_or_df
             data = from_coco_or_voc(
-                anno_file, "test"
+                anno_file,
+                "test",
+                coco_root=self._config.model.mmdet_image.coco_root,
             )  # TODO: maybe remove default splits hardcoding (only used in VOC)
             if os.path.isdir(anno_file):
                 eval_tool = "torchmetrics"  # we can only use torchmetrics for VOC format evaluation.
@@ -636,7 +654,10 @@ class ObjectDetectionLearner(BaseLearner):
                 eval_tool=eval_tool,
             )
         else:
-            data = object_detection_data_to_df(data)
+            data = object_detection_data_to_df(
+                data,
+                coco_root=self._config.model.mmdet_image.coco_root,
+            )
             return self.evaluate_coco(
                 anno_file_or_df=data,
                 metrics=metrics,
@@ -676,7 +697,10 @@ class ObjectDetectionLearner(BaseLearner):
         self.ensure_predict_ready()
         ret_type = BBOX
         if self._problem_type == OBJECT_DETECTION:
-            data = object_detection_data_to_df(data)
+            data = object_detection_data_to_df(
+                data,
+                coco_root=self._config.model.mmdet_image.coco_root,
+            )
             if self._label_column not in data:
                 self._label_column = None
 

autogluon/multimodal/models/ft_transformer.py

@@ -41,7 +41,7 @@ class CategoricalFeatureTokenizer(nn.Module):
         References
         ----------
         1. Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, Artem Babenko,
-        "Revisiting Deep Learning Models for Tabular Data", 2021
+        "Revisiting Deep Learning Models for Tabular Data", NeurIPS 2021
         https://arxiv.org/pdf/2106.11959.pdf
         2. Code: https://github.com/Yura52/tabular-dl-revisiting-models
         """

autogluon/multimodal/utils/object_detection.py

@@ -145,7 +145,9 @@ def object_detection_df_to_coco(data: pd.DataFrame, save_path: Optional[str] = N
     return output_json_dict
 
 
-def object_detection_data_to_df(data: Union[pd.DataFrame, dict, list, str]) -> pd.DataFrame:
+def object_detection_data_to_df(
+    data: Union[pd.DataFrame, dict, list, str], coco_root: Optional[str] = None
+) -> pd.DataFrame:
     """
     Construct a dataframe from a data dictionary, json file path (for COCO), folder path (for VOC),
     image path (for single image), list of image paths (for multiple images)
@@ -163,7 +165,7 @@ def object_detection_data_to_df(data: Union[pd.DataFrame, dict, list, str]) -> p
         return from_list(data)
     if isinstance(data, str):
         if os.path.isdir(data) or data.endswith(".json"):
-            return from_coco_or_voc(data)
+            return from_coco_or_voc(data, coco_root=coco_root)
         return from_str(data)
     if isinstance(data, pd.DataFrame):
         sanity_check_dataframe(data)
@@ -700,7 +702,7 @@ def _check_load_coco_bbox(
 
 def from_coco(
     anno_file: Optional[str],
-    root: Optional[str] = None,
+    coco_root: Optional[str] = None,
     min_object_area: Optional[Union[int, float]] = 0,
     use_crowd: Optional[bool] = False,
 ):
@@ -718,7 +720,7 @@ def from_coco(
     ----------
     anno_file
         The path to the annotation file.
-    root
+    coco_root
         Root of the COCO folder. The default relative root folder (if set to `None`) is `anno_file/../`.
     min_object_area
         Minimum object area to consider.
@@ -740,16 +742,19 @@ def from_coco(
     coco = COCO(anno_file)
 
     # get data root
-    if isinstance(root, Path):
-        root = str(root.expanduser().resolve())
-    elif isinstance(root, str):
-        root = os.path.abspath(os.path.expanduser(root))
-    elif root is None:
+    if isinstance(coco_root, Path):
+        coco_root = str(coco_root.expanduser().resolve())
+    elif isinstance(coco_root, str):
+        coco_root = os.path.abspath(os.path.expanduser(coco_root))
+    elif coco_root is None:
         # try to use the default coco structure
-        root = os.path.join(os.path.dirname(anno_file), "..")
-        logger.info(f"Using default root folder: {root}. Specify `root=...` if you feel it is wrong...")
+        coco_root = os.path.join(os.path.dirname(anno_file), "..")
+        logger.info(
+            f"Using default root folder: {coco_root}. "
+            "Specify `model.mmdet_image.coco_root=...` in hyperparameters if you think it is wrong."
+        )
     else:
-        raise ValueError("Unable to parse root: {}".format(root))
+        raise ValueError("Unable to parse coco_root: {}".format(coco_root))
 
     # support prediction using data with no annotations
     # note that data with annotation can be used for prediction without any changes
@@ -764,9 +769,9 @@ def from_coco(
     for entry in coco.loadImgs(image_ids):
         if "coco_url" in entry:
             dirname, filename = entry["coco_url"].split("/")[-2:]
-            abs_path = os.path.join(root, dirname, filename)
+            abs_path = os.path.join(coco_root, dirname, filename)
         else:
-            abs_path = os.path.join(root, entry["file_name"])
+            abs_path = os.path.join(coco_root, entry["file_name"])
         if not os.path.exists(abs_path):
             logger.warning(f"File skipped since not exists: {abs_path}.")
             continue
@@ -1146,7 +1151,7 @@ def process_voc_annotations(
         f.writelines("\n".join(xml_file_names))
 
 
-def from_coco_or_voc(file_path: str, splits: Optional[Union[str]] = None):
+def from_coco_or_voc(file_path: str, splits: Optional[Union[str]] = None, coco_root: Optional[str] = None):
     """
     Convert the data from coco or voc format to pandas Dataframe.
 
@@ -1167,7 +1172,7 @@ def from_coco_or_voc(file_path: str, splits: Optional[Union[str]] = None):
         # VOC use dir as input
         return from_voc(root=file_path, splits=splits)
     else:
-        return from_coco(file_path)
+        return from_coco(file_path, coco_root=coco_root)
 
 
 def get_coco_format_classes(sample_data_path: str):
@@ -1539,11 +1544,13 @@ def save_result_df(
     return result_df
 
 
-def save_result_coco_format(detection_data_path, pred, result_path):
+def save_result_coco_format(detection_data_path, pred, result_path, coco_root: Optional[str] = None):
     coco_dataset = COCODataset(detection_data_path)
     result_name, _ = os.path.splitext(result_path)
     result_path = result_name + ".json"
-    coco_dataset.save_result(pred, from_coco_or_voc(detection_data_path, "test"), save_path=result_path)
+    coco_dataset.save_result(
+        pred, from_coco_or_voc(detection_data_path, "test", coco_root=coco_root), save_path=result_path
+    )
     logger.info(25, f"Saved detection result to {result_path}")
 
 

autogluon/multimodal/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.2b20241031'
+__version__ = '1.1.2b20241107'
 __lite__ = False

{autogluon.multimodal-1.1.2b20241031.dist-info → autogluon.multimodal-1.1.2b20241107.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.multimodal
-Version: 1.1.2b20241031
+Version: 1.1.2b20241107
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -41,27 +41,27 @@ Requires-Dist: scikit-learn<1.5.3,>=1.4.0
 Requires-Dist: Pillow<12,>=10.0.1
 Requires-Dist: tqdm<5,>=4.38
 Requires-Dist: boto3<2,>=1.10
-Requires-Dist: torch<2.5,>=2.2
-Requires-Dist: lightning<2.4,>=2.2
-Requires-Dist: transformers[sentencepiece]<4.41.0,>=4.38.0
-Requires-Dist: accelerate<0.22.0,>=0.21.0
+Requires-Dist: torch<2.6,>=2.2
+Requires-Dist: lightning<2.6,>=2.2
+Requires-Dist: transformers[sentencepiece]<5,>=4.38.0
+Requires-Dist: accelerate<1.0,>=0.32.0
 Requires-Dist: requests<3,>=2.30
 Requires-Dist: jsonschema<4.22,>=4.18
 Requires-Dist: seqeval<1.3.0,>=1.2.2
 Requires-Dist: evaluate<0.5.0,>=0.4.0
-Requires-Dist: timm<0.10.0,>=0.9.5
+Requires-Dist: timm<1.0.7,>=0.9.5
 Requires-Dist: torchvision<0.21.0,>=0.16.0
 Requires-Dist: scikit-image<0.25.0,>=0.19.1
 Requires-Dist: text-unidecode<1.4,>=1.3
 Requires-Dist: torchmetrics<1.3.0,>=1.2.0
 Requires-Dist: nptyping<2.5.0,>=1.4.4
 Requires-Dist: omegaconf<2.3.0,>=2.1.1
-Requires-Dist: autogluon.core[raytune]==1.1.2b20241031
-Requires-Dist: autogluon.features==1.1.2b20241031
-Requires-Dist: autogluon.common==1.1.2b20241031
+Requires-Dist: autogluon.core[raytune]==1.1.2b20241107
+Requires-Dist: autogluon.features==1.1.2b20241107
+Requires-Dist: autogluon.common==1.1.2b20241107
 Requires-Dist: pytorch-metric-learning<2.4,>=1.3.0
 Requires-Dist: nlpaug<1.2.0,>=1.1.10
-Requires-Dist: nltk<4.0.0,>=3.4.5
+Requires-Dist: nltk<3.9,>=3.4.5
 Requires-Dist: openmim<0.4.0,>=0.3.7
 Requires-Dist: defusedxml<0.7.2,>=0.7.1
 Requires-Dist: jinja2<3.2,>=3.0.3

{autogluon.multimodal-1.1.2b20241031.dist-info → autogluon.multimodal-1.1.2b20241107.dist-info}/RECORD

@@ -1,11 +1,11 @@
-autogluon.multimodal-1.1.2b20241031-py3.8-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.multimodal-1.1.2b20241107-py3.8-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
 autogluon/multimodal/__init__.py,sha256=EuWb-QmtFBKePJw4_4Kpp9dKrabv121haYw_Oiu2jfI,238
 autogluon/multimodal/constants.py,sha256=lFA03ZQeZlp8mwuXLuMOgeByljV5wPYBjN_hi6Xc8zg,8498
 autogluon/multimodal/predictor.py,sha256=VTJGcKH4Kktdm4Qq2x9oRThpfp6w_kFSjJOmQPsmB5g,40654
 autogluon/multimodal/presets.py,sha256=VR_arn7X4eiQcGcvJVmwxDopPJGvYP1W1cBZ2AOcdJM,25882
 autogluon/multimodal/problem_types.py,sha256=JPSoV3Fg-NGQansRlyT2bPZG3iIkgWo7eB8oDoAfg90,9201
 autogluon/multimodal/registry.py,sha256=vqvONWweZP44aBo1jCvlqLdL0Agn2kyTK8uXUwagZhs,3670
-autogluon/multimodal/version.py,sha256=tx6cpwmCPDMSmbDZ7J3YiTj8to4zDuAZYwlwmwUpHsI,90
+autogluon/multimodal/version.py,sha256=H_a15z27R7xk2LlVEqVCWjJ8Z2gZ7G-G5jZGl1qOVXM,90
 autogluon/multimodal/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/multimodal/cli/prepare_detection_dataset.py,sha256=9NCYmCUMPRWbxxbN_C7YQjMYlrAm8gbwJ3Qd-79JWH4,5218
 autogluon/multimodal/cli/voc2coco.py,sha256=LXVu9RIfOZs_1URrzO-_3Nrvb9uGEgPxCY4-B6m1coc,9605
@@ -14,7 +14,7 @@ autogluon/multimodal/configs/data/default.yaml,sha256=gsadTDJ3ZbppQ5rpA0sPhqd9Mw
 autogluon/multimodal/configs/distiller/default.yaml,sha256=DiCZYYJDEk5k03ZI-ewj9hWiKpMQbB8oqjWYavMK1wU,513
 autogluon/multimodal/configs/environment/default.yaml,sha256=Di1EohFWUoGi0bLuJfOr3bDD4ceD_ZrfDc_GJO55mpk,1235
 autogluon/multimodal/configs/matcher/default.yaml,sha256=K0ehM0uIFfKq1CeeaFcv14RBjo3khMgWKS2ymWI-V9I,218
-autogluon/multimodal/configs/model/default.yaml,sha256=7cLxvza8AEfWEyLfrXe89kn1pvaY5JsvgBBB38vi_xI,8731
+autogluon/multimodal/configs/model/default.yaml,sha256=NgCPV01hfcG21hvmtLaiTbahTYkRi3ZmHONzsRdwjOE,8751
 autogluon/multimodal/configs/optimization/default.yaml,sha256=w4xlVS1gUK8tDXyhfDtIKabTqr_gBWSduq1y8T9CBI8,2182
 autogluon/multimodal/configs/pretrain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/multimodal/configs/pretrain/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -71,7 +71,7 @@ autogluon/multimodal/learners/base.py,sha256=IUHRBzwrKqAwo9nDsqzg0rBQaFiVxfyeMnd
 autogluon/multimodal/learners/few_shot_svm.py,sha256=TXauhXr_2hWqaEwO8XhFxWRRPXDYxLpmmKYaCrxFWPM,23934
 autogluon/multimodal/learners/matching.py,sha256=gueWrqy0g9gVbyBvQOAj03JgBwbJsBXeLLtKsiTzrnU,89891
 autogluon/multimodal/learners/ner.py,sha256=0VZl_Z1O98A5mOSw8Ee8F9foaCT684DT0j1ALx-8RU4,19035
-autogluon/multimodal/learners/object_detection.py,sha256=JRxXaI33Um0BWGsRRKFfLy7tAfqJj2SsT_DqIL1igKo,29015
+autogluon/multimodal/learners/object_detection.py,sha256=tSRKdWEnFwqOCzHoqRAPvllY0T_vwXSdInGVX70-ZD4,29856
 autogluon/multimodal/learners/semantic_segmentation.py,sha256=cy2ALYTtqeSnPo75htgr5STZ_utgkzeGxp5j4J1mScc,20183
 autogluon/multimodal/models/__init__.py,sha256=wynO5U5zY_vElZPGL10Oqb7OVkj2iovqzml22MRL3iE,842
 autogluon/multimodal/models/adaptation_layers.py,sha256=NuzwU_ghk8D2axmDuD8UEZ_HamoMSCcKMV9DB1AYWAg,38425
@@ -79,7 +79,7 @@ autogluon/multimodal/models/categorical_mlp.py,sha256=R4qNo2eJ2B4FKIpTE5HXJezT0Q
 autogluon/multimodal/models/clip.py,sha256=hbIV1jsomCZXg6RF6R5jDpxESlBq46hInQ2S5Y4gJBM,8875
 autogluon/multimodal/models/custom_transformer.py,sha256=jOqe6dSMsvhqagUc5abB2Nu5VUwODn_frtFVTIA5WgY,27581
 autogluon/multimodal/models/document_transformer.py,sha256=_-hcnR0qRyzTgEmCRmnzLSChq3l7dIiXT60uDSXXT_M,7114
-autogluon/multimodal/models/ft_transformer.py,sha256=KfdMDVh9B740qeozXfPFll8ZeC8jAzsgz4LdGAgFkQc,26374
+autogluon/multimodal/models/ft_transformer.py,sha256=xjv4v5Rr8Iq4wJGoIMR4hmuWkN5BTRB5mU1ElC8mtQ0,26382
 autogluon/multimodal/models/huggingface_text.py,sha256=QPkxuU6d5V1XtjrSmPPPt89CW4_19QAMZHZC_lfAlQM,11871
 autogluon/multimodal/models/mlp.py,sha256=KZt10QjP_C9e6L0HUtGef8AqWFR2kxAXsZAH7_iK20Y,4456
 autogluon/multimodal/models/mmdet_image.py,sha256=gdgoyBXVyiXMDhnKwFPafpgxv4PhFXFt4PZ_TLsW22I,27112
@@ -131,15 +131,15 @@ autogluon/multimodal/utils/misc.py,sha256=WaDWN-6xCCL4tCkxMr4VMb5oiNmmBLrWo5FC3b
 autogluon/multimodal/utils/mmcv.py,sha256=Jjg5PiPqiRNJk6yWkQQlNiqT7qhStN94QjqQsZO3uVw,922
 autogluon/multimodal/utils/model.py,sha256=Z_9bev8nRk92cUZjPggVAM3R3CHFlecU-YzjkMGPUsE,21963
 autogluon/multimodal/utils/nlpaug.py,sha256=rWztiOZDbtEGBdyjkXZ0DoSEpXGKX9akpDpFnz4xIMw,2557
-autogluon/multimodal/utils/object_detection.py,sha256=EjLPzmq8Ge_HAtibiY5FNOChL_qAIls4PJF3PFd8kYA,50047
+autogluon/multimodal/utils/object_detection.py,sha256=br3QSa3h17ZMG9MjC0iWn9n42EGD28KvtGzoDQOUaGw,50382
 autogluon/multimodal/utils/onnx.py,sha256=rblWnphKTsfbosbieJu8PsH6SMDw4on9BS8bR1plL2U,5607
 autogluon/multimodal/utils/save.py,sha256=zYIO3mYMGBvHfZcmCUaLpsQa14nVq1LPv2F76uaz89w,3951
 autogluon/multimodal/utils/visualizer.py,sha256=qAc4_36r3MBDPq1R1jBeb_gcfzIrsylL1S31sRf3wuw,22562
-autogluon.multimodal-1.1.2b20241031.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.multimodal-1.1.2b20241031.dist-info/METADATA,sha256=LyeJWhLA0CjNSgQkC9QAd72niD1bkSF23N8zX4vA-Zs,12891
-autogluon.multimodal-1.1.2b20241031.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.multimodal-1.1.2b20241031.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-autogluon.multimodal-1.1.2b20241031.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.multimodal-1.1.2b20241031.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.multimodal-1.1.2b20241031.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.multimodal-1.1.2b20241031.dist-info/RECORD,,
+autogluon.multimodal-1.1.2b20241107.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.multimodal-1.1.2b20241107.dist-info/METADATA,sha256=UqJlg5KlO9dvhr6lf7SfaNUdBv2MCAaSv-5vcuDISps,12880
+autogluon.multimodal-1.1.2b20241107.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.multimodal-1.1.2b20241107.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+autogluon.multimodal-1.1.2b20241107.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.multimodal-1.1.2b20241107.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.multimodal-1.1.2b20241107.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.multimodal-1.1.2b20241107.dist-info/RECORD,,