careamics 0.0.11__py3-none-any.whl → 0.0.12__py3-none-any.whl

careamics/transforms/normalize.py

@@ -129,16 +129,27 @@ class Normalize(Transform):
         norm_patch = self._apply(patch, means, stds)
 
         # same for the target patch
-        if (
-            target is not None
-            and self.target_means is not None
-            and self.target_stds is not None
-        ):
+        if target is None:
+            norm_target = None
+        else:
+            if not self.target_means or not self.target_stds:
+                raise ValueError(
+                    "Target means and standard deviations must be provided "
+                    "if target is not None."
+                )
+            if len(self.target_means) == 0 and len(self.target_stds) == 0:
+                raise ValueError(
+                    "Target means and standard deviations must be provided "
+                    "if target is not None."
+                )
+            if len(self.target_means) != target.shape[0]:
+                raise ValueError(
+                    "Target means and standard deviations must have the same length "
+                    "as the target."
+                )
             target_means = _reshape_stats(self.target_means, target.ndim)
             target_stds = _reshape_stats(self.target_stds, target.ndim)
             norm_target = self._apply(target, target_means, target_stds)
-        else:
-            norm_target = None
 
         return norm_patch, norm_target, additional_arrays
 

careamics/utils/lightning_utils.py

@@ -28,26 +28,40 @@ def read_csv_logger(experiment_name: str, log_folder: Union[str, Path]) -> dict:
 
     path_log = path / f"version_{version}" / "metrics.csv"
 
-    epochs = []
-    train_losses_tmp = []
-    val_losses_tmp = []
     with open(path_log) as f:
         lines = f.readlines()
 
+        header = lines[0].strip().split(",")
+        metrics = {value: [] for value in header}
+        print(metrics)
+
         for single_line in lines[1:]:
-            epoch, _, train_loss, _, val_loss = single_line.strip().split(",")
+            values = single_line.strip().split(",")
 
-            epochs.append(epoch)
-            train_losses_tmp.append(train_loss)
-            val_losses_tmp.append(val_loss)
+            for k, v in zip(header, values):
+                metrics[k].append(v)
 
     # train and val are not logged on the same row and can have different lengths
     train_epoch = [
-        int(epochs[i]) for i in range(len(epochs)) if train_losses_tmp[i] != ""
+        int(metrics["epoch"][i])
+        for i in range(len(metrics["epoch"]))
+        if metrics["train_loss_epoch"][i] != ""
+    ]
+    val_epoch = [
+        int(metrics["epoch"][i])
+        for i in range(len(metrics["epoch"]))
+        if metrics["val_loss"][i] != ""
+    ]
+    train_losses = [
+        float(metrics["train_loss_epoch"][i])
+        for i in range(len(metrics["train_loss_epoch"]))
+        if metrics["train_loss_epoch"][i] != ""
+    ]
+    val_losses = [
+        float(metrics["val_loss"][i])
+        for i in range(len(metrics["val_loss"]))
+        if metrics["val_loss"][i] != ""
     ]
-    val_epoch = [int(epochs[i]) for i in range(len(epochs)) if val_losses_tmp[i] != ""]
-    train_losses = [float(loss) for loss in train_losses_tmp if loss != ""]
-    val_losses = [float(loss) for loss in val_losses_tmp if loss != ""]
 
     return {
         "train_epoch": train_epoch,

{careamics-0.0.11.dist-info → careamics-0.0.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: careamics
-Version: 0.0.11
+Version: 0.0.12
 Summary: Toolbox for running N2V and friends.
 Project-URL: homepage, https://careamics.github.io/
 Project-URL: repository, https://github.com/CAREamics/careamics
@@ -19,9 +19,9 @@ Requires-Python: >=3.9
 Requires-Dist: bioimageio-core==0.7
 Requires-Dist: matplotlib<=3.10.1
 Requires-Dist: numpy<2.0.0
-Requires-Dist: pillow<=11.1.0
+Requires-Dist: pillow<=11.2.1
 Requires-Dist: psutil<=7.0.0
-Requires-Dist: pydantic<2.11,>=2.5
+Requires-Dist: pydantic<=2.12,>=2.11
 Requires-Dist: pytorch-lightning<=2.5.0.post0,>=2.2
 Requires-Dist: pyyaml!=6.0.0,<=6.0.2
 Requires-Dist: scikit-image<=0.25.2

{careamics-0.0.11.dist-info → careamics-0.0.12.dist-info}/RECORD

@@ -1,5 +1,5 @@
 careamics/__init__.py,sha256=eHsl7oE8HTKmi7yLMj8Yyp0RbdtN3QDmQQb-4Sn9d8M,475
-careamics/careamist.py,sha256=OhBkchHIVIvLyk57R5UXt2Euy4e_EDSbNp5NXJ53hS8,37588
+careamics/careamist.py,sha256=4iLyet4XLk2GWsWB3v0HzEaS97GQECXn3PnhdJEWklQ,38301
 careamics/conftest.py,sha256=Od4WcaaP0UP-XUMrFr_oo4e6c2hi_RvNbuaRTopwlmI,911
 careamics/py.typed,sha256=esB4cHc6c07uVkGtqf8at7ttEnprwRxwk8obY8Qumq4,187
 careamics/cli/__init__.py,sha256=LbM9bVtU1dy-khmdiIDXwvKy2v8wPBCEUuWqV_8rosA,106
@@ -8,16 +8,16 @@ careamics/cli/main.py,sha256=S4B3c1ZN-OQK0l2_W42CaW0KmF_Pe_y4pKgn_UOuyDg,6564
 careamics/cli/utils.py,sha256=q_dmG7lxg_FT62qX9fPilIWL1M8ibhLnnhUKqa4knPI,660
 careamics/config/__init__.py,sha256=K0N1GIqFCYhpPjalZG-Ygap6Ew_dDAC0uw5Npzhg9Lk,1524
 careamics/config/callback_model.py,sha256=EeYHqpMIPQwyNxLRzzX32Uncl5mZuB1bJO76RHpNymg,4555
-careamics/config/configuration.py,sha256=D7i_g48P7d4H4_YSFyvDh9tRM7vLhM1mnU_XMeCC1HU,11193
+careamics/config/configuration.py,sha256=cZ8u0Lqs0Zrz9DbWJYZWLRhhfZEuSiVhgDjNEQdS8yk,11471
 careamics/config/configuration_factories.py,sha256=NhheOPkVhIF1cwz0FGNLQrxOByRQGrw-aZ_vGNIE8UE,34599
 careamics/config/configuration_io.py,sha256=P-bP1kzkXxJWOEFP02dEZFNmpuLAPJfJtYhX4bFeaKk,2324
 careamics/config/inference_model.py,sha256=UE_-ZmCX6LFCbDBOwyGnvuAboF_JNX2m2LcF0WiwgCI,6961
 careamics/config/likelihood_model.py,sha256=VorUtc0_-xIWNxwVrd1kBba-003ICdVMtxpcDCxH4Io,2259
 careamics/config/loss_model.py,sha256=yYcUBS90Qyon1MxeaHiVP3dJHPJFC0GUvWKGcAb3IHk,2036
 careamics/config/nm_model.py,sha256=5dAhDBLa4WPfKaNEK6ATNsSUwtlH8u8gYweEA4gZP6g,4758
-careamics/config/optimizer_models.py,sha256=OWpTydRBBR8wt_af1mZHNNwvL_RtnRFopAOdgjzLo30,5750
+careamics/config/optimizer_models.py,sha256=9qxcLjtDp5LjYX52u21Rom4F3_GZUV2GJimrK3un574,5717
 careamics/config/tile_information.py,sha256=c-_xrVPOgcnjiEzQ-9A_GhNPamObkMANbeHaRP29R-4,2059
-careamics/config/training_model.py,sha256=67_ipo_-LxhT4-WqAs40Sg8PjU--my43Qn3BhjvlXxM,3212
+careamics/config/training_model.py,sha256=VfK2bk_1FHaamKZw5S8UDPVxasyUqz1rY1ahcaxYZ7s,3114
 careamics/config/algorithms/__init__.py,sha256=on5D6zBO9Lu-Tf5To8xpF6owIFqdN7RSmZdpyXDOaNw,404
 careamics/config/algorithms/care_algorithm_model.py,sha256=ncf89BC2aFPFSquJ65-Y7NpwVbvgPE0BKH6Up1OHa1s,3238
 careamics/config/algorithms/n2n_algorithm_model.py,sha256=OZbRis9jhRKWNK1-Z_aw2tfJRuGdlJiYEYlH4Hr1FRs,3066
@@ -29,7 +29,7 @@ careamics/config/architectures/architecture_model.py,sha256=gXn4gdLrQP3bmTQxIhzk
 careamics/config/architectures/lvae_model.py,sha256=lwOiJYNUqPrZFl9SpPLYon77EiRbe2eI7pmpx45rO78,7606
 careamics/config/architectures/unet_model.py,sha256=HJJWf-wuYTv8KXMwikdjeB8htg1QOt0IyQbMuBt1LUI,3556
 careamics/config/data/__init__.py,sha256=ijNcvrKQtKljmBuZ6DDxh86PMzpRob2l2JMqbPQLqPk,111
-careamics/config/data/data_model.py,sha256=0YFN_NXL10f8h_Wr7ce6xsfOy86iZOPIkgLK-KIpeEU,12181
+careamics/config/data/data_model.py,sha256=Cz-ELguEdLwDFtRSZSiTEbS3gTdG1Q9GZrZaU6hKtkA,13431
 careamics/config/support/__init__.py,sha256=ktWvxbTkRXnQPS_N84l9E2B5kTZVdd64SIjsJIQKB-k,1041
 careamics/config/support/supported_activations.py,sha256=CqOWoziIK5jZZXJO7G7cGg3TTid1POqv8FXqxjXxyME,535
 careamics/config/support/supported_algorithms.py,sha256=w6YzcIqGZ_bS85Tw1s7TEltBDXLt4SzgN3Tc6s19dGU,946
@@ -73,24 +73,32 @@ careamics/dataset/tiling/__init__.py,sha256=aW_AMB9rzm0VmooUpjcyqv6sQP69RlPQMEdP
 careamics/dataset/tiling/collate_tiles.py,sha256=XK0BsDQE7XwIwmOoCHJIpVC3kqjSN6nDhrJ4POVeHS8,965
 careamics/dataset/tiling/lvae_tiled_patching.py,sha256=LYEEdjKuKaxIGFtOkhfpsE7hruBnIsD5HcW9aVH6WHI,13019
 careamics/dataset/tiling/tiled_patching.py,sha256=6vxsqlccUqIl4Ys92JWIPs0Kn95VzaHoAYMSGcp2dh8,5956
-careamics/dataset_ng/demo_dataset.ipynb,sha256=gAWQnodNga5I6TrjsJspjeAGWCHiy23SFE5dPvKnETE,7130
-careamics/dataset_ng/demo_patch_extractor.py,sha256=8iCAdvmfGdTJSR59yu0WOb_4r3HshRDDMrSiOpxoh5o,1510
-careamics/dataset_ng/demo_patch_extractor_factory.py,sha256=4NRtb9hOL0bXz2f8PHOmjoltbMhoMl8UkFXIJTf8f5Y,981
-careamics/dataset_ng/dataset/__init__.py,sha256=V8fSRAnabpo706OVLn6l9UtQCyp5Kc5CDwD1hMOjRAA,70
-careamics/dataset_ng/dataset/dataset.py,sha256=g0-uBKxLHVUEuRtIQnKseiExhc_yb0-pfS4icTdOFkE,6406
-careamics/dataset_ng/patch_extractor/__init__.py,sha256=X_UBCKi_5py0HfBAGiRMcTaqEu3EdJNVRI7eSG2wmlo,298
-careamics/dataset_ng/patch_extractor/demo_custom_image_stack_loader.py,sha256=fv-izzYW5QyMQ2Oki2sDGzXLAt51uzxxphu-NdrQMOA,2884
-careamics/dataset_ng/patch_extractor/image_stack_loader.py,sha256=0jSF-uM05kv-nqY3tB_bcbpC0Cb7qB1CBDDqkfTvjNs,4690
-careamics/dataset_ng/patch_extractor/patch_extractor.py,sha256=CLexpuFQ_GiNWhzRSa3HoepbBj3lvCHu9ZU5PVfYWas,748
-careamics/dataset_ng/patch_extractor/patch_extractor_factory.py,sha256=rIEuCMUhqslzd-7DHueOAQ13y8rgxjtvjlVX3dql0zk,6017
-careamics/dataset_ng/patch_extractor/image_stack/__init__.py,sha256=xTGRg2W_CpxsTgyiG-cHSFuXh7hwA0fGrEPm61GrsBI,225
-careamics/dataset_ng/patch_extractor/image_stack/image_stack_protocol.py,sha256=8QLpKEVqw3Edz-hL7lmKW_06x6DcbQo20feN8XkTnsY,1543
+careamics/dataset_ng/README.md,sha256=489sMnra-cVotBBWNL-jhb9H4eLO1FFa3b5zhfkK34g,9856
+careamics/dataset_ng/dataset.py,sha256=ds7Sow3QtvtrfCDDqEL5SQDZ5OCuL54H-pdYzqZScaY,9025
+careamics/dataset_ng/factory.py,sha256=XDVfqcQFNcd7waurP8aA14uuN4Kr4-0Wk8mWAg3hdk0,13640
+careamics/dataset_ng/legacy_interoperability.py,sha256=ROD7fSvbpxl3wEJpkwT8uCU9KwEtEiyK6yWgwiUqcZQ,5531
+careamics/dataset_ng/demos/bsd68_demo.ipynb,sha256=LQfDCv97SV7Me66tXiDWk8Olx8q7_vGhVLxKpsZdic8,10310
+careamics/dataset_ng/demos/care_U2OS_demo.ipynb,sha256=hYoUj6Ak0DvoFJIk5KifrWl_fek70ShUqUUwCsHO8BU,9487
+careamics/dataset_ng/demos/demo_custom_image_stack.ipynb,sha256=ktkhAZZ2QnaaNe8o3fuA8CiQqcr1-JTB9WbnZMN0qtw,25184
+careamics/dataset_ng/demos/demo_datamodule.ipynb,sha256=dkIca5vPawZ1QmF1-mTy4R_83SML6OMuYj1ah0ygmZY,12619
+careamics/dataset_ng/demos/demo_dataset.ipynb,sha256=LQXGk8MCi2AWhi7WhZk_4uIiNwCJtGdk1qfz9cDRyvg,7629
+careamics/dataset_ng/demos/demo_patch_extractor.py,sha256=2guz1iRqBzue4GLAVh9-K8sXCgsygtsJS-wzeHctY34,1419
+careamics/dataset_ng/demos/mouse_nuclei_demo.ipynb,sha256=Afd-_T848z3ZCDAL8vMfP6CJR8CbUg0xLAurBxg-fuc,8278
+careamics/dataset_ng/patch_extractor/__init__.py,sha256=U27Gxp6dk6DUc-MiDMPvdh2aoWlM7jU-bjueqa7elPg,207
+careamics/dataset_ng/patch_extractor/demo_custom_image_stack_loader.py,sha256=v6p4JNr8dqhaclsYd59SLDqlYPM-NG0SroxRDzn3Pb8,2973
+careamics/dataset_ng/patch_extractor/image_stack_loader.py,sha256=Gq1KbqZWCX8fR4ZCcFysXPK6LoJJJvb4Cig_KYeGyqs,2490
+careamics/dataset_ng/patch_extractor/patch_extractor.py,sha256=nGN5TrmmSo5KeQoXJ-wrVQtQlYadaR8onH7TOWXhVy4,824
+careamics/dataset_ng/patch_extractor/patch_extractor_factory.py,sha256=kTXaE4pcpubJX_69P9i-HQidBENJvcnQW1GLqmDEPU4,4658
+careamics/dataset_ng/patch_extractor/image_stack/__init__.py,sha256=Mgl-qv0WUmL0A8W_1FyqiEKEveqNhVqbI3zq_vXmwbw,269
+careamics/dataset_ng/patch_extractor/image_stack/image_stack_protocol.py,sha256=NnhqyDmZPuQgU_gjNugNWNX9_NetRguwLg9LfTmd7U8,1649
 careamics/dataset_ng/patch_extractor/image_stack/in_memory_image_stack.py,sha256=FS9dEY5GXKEf0oeNe7Vb005HTby4thUvzTzWwCxe3Zk,1927
 careamics/dataset_ng/patch_extractor/image_stack/zarr_image_stack.py,sha256=hmNOl6-FMUNQS65YMSa4eAz3Rp_2es98p1_UY6S8B50,6590
-careamics/dataset_ng/patching_strategies/__init__.py,sha256=NLSjecNI_BOhkfznjogBEkq8BP74aixjpLhhRdkS9Bo,366
-careamics/dataset_ng/patching_strategies/patching_strategy_protocol.py,sha256=gcbprNfRxG5gEBQzqZyJIhjCfwsC80PQvx0JQ-iunJg,2308
-careamics/dataset_ng/patching_strategies/random_patching.py,sha256=AGlvn1NsjPJY5Ku8DEn92DaKkvAjX293coqMnwi7_UY,13410
+careamics/dataset_ng/patching_strategies/__init__.py,sha256=2KwdY_TeD9WQju150WbV2IF19TincHU3lbcL0fqZF5o,549
+careamics/dataset_ng/patching_strategies/patching_strategy_protocol.py,sha256=ukw5G9hIOPEJz-DEFDMuJsGYou7wUeRjALNU8qdgn9g,3475
+careamics/dataset_ng/patching_strategies/random_patching.py,sha256=cNUt9iM7_j_P3OdN5iQ3K1OGNeAl61Zglem9DQU1GUc,13497
 careamics/dataset_ng/patching_strategies/sequential_patching.py,sha256=fngTPpY6D93guFwSdHuCakDebin7eEtK7Y2OFmJ1IG8,2485
+careamics/dataset_ng/patching_strategies/tiling_strategy.py,sha256=NI48Qg3L-YqtXZXNhusbzX8QWGtGOLAXMGRbTo_Sm1w,6367
+careamics/dataset_ng/patching_strategies/whole_sample.py,sha256=o1Z4iHKveq9X--LRV-gdUQqB-TPVxr2RvaKHmgDnCx0,1249
 careamics/file_io/__init__.py,sha256=vgMI77X820VOWywAEW5W20FXfmbqBzx4V63D3V3_HhI,334
 careamics/file_io/read/__init__.py,sha256=wf8O_o80ghrlWQ-RGEuSqcc2LU55P1B-oxTacDToygo,259
 careamics/file_io/read/get_func.py,sha256=O_pdymjh2mc-JZ1je3ZnPAcsHc7Je3a005AMgAa0xuw,1388
@@ -100,7 +108,7 @@ careamics/file_io/write/__init__.py,sha256=CUt33cRjG9hm18L9a7XqaUKWQ_3xiuQ9ztz4A
 careamics/file_io/write/get_func.py,sha256=hyGHe1RX-lfa9QFAnwRCz_gS0NRiRnXEtg4Bdeh2Esc,1627
 careamics/file_io/write/tiff.py,sha256=tBGIgl-I1sMyBivgx-dOTBykXBODkgwPH8MT3_4KAE8,1050
 careamics/lightning/__init__.py,sha256=ATCVAGnX08Ik4TxbIv0-cXb52UinR42JgvZh_GIMSpc,588
-careamics/lightning/lightning_module.py,sha256=_gMGKGSHOEoh00jblCX5egMI91Z0UJpIjEQ74AaVGss,24177
+careamics/lightning/lightning_module.py,sha256=-uGXKMJxFRsowIuFjh2mz5tSvVyEyeS5DfyE4DolCkA,24357
 careamics/lightning/predict_data_module.py,sha256=JNwujK6QwObSx6P25ghpGl2f2gGT3KVgYMTlonZzH20,12745
 careamics/lightning/train_data_module.py,sha256=HyXeDZ_u3JLzyh1tqRBIH93spMj0iQhAP4nmHPEI4aM,26554
 careamics/lightning/callbacks/__init__.py,sha256=eA5ltzYNzuO0uMEr1jG4wP01b0s29s5I03WGJ290qkw,312
@@ -111,6 +119,11 @@ careamics/lightning/callbacks/prediction_writer_callback/file_path_utils.py,sha2
 careamics/lightning/callbacks/prediction_writer_callback/prediction_writer_callback.py,sha256=8HHUSKcG7G0FSCVPnpGQHLfpara5mnKAwsiiyWp2wzo,8210
 careamics/lightning/callbacks/prediction_writer_callback/write_strategy.py,sha256=lxsLjLskRpYnzdyWCdOICUJxF9YzuUi1RH0LJnOCVgo,12594
 careamics/lightning/callbacks/prediction_writer_callback/write_strategy_factory.py,sha256=F1IpbNNgkv5eK8Xpqp7wqv2lsqEdP1wMRlBL7RBn93U,7114
+careamics/lightning/dataset_ng/data_module.py,sha256=gb0dhuV-ROd-3o1FNIL57gZkK23Og_LFPf9CNVhkbHw,19126
+careamics/lightning/dataset_ng/lightning_modules/__init__.py,sha256=Kx7NkwAS9rqfozxamMWcJa3U8zw47HT5T8R1E0Uk8Rc,164
+careamics/lightning/dataset_ng/lightning_modules/care_module.py,sha256=W1DfXrpFVTvBncyxK0RZ8IZ_iFdkdIKPAPeznnX8THc,2030
+careamics/lightning/dataset_ng/lightning_modules/n2v_module.py,sha256=8XTBGxFbG1N3g8HAa230NE2NZ8Nn7CnpMV4MVRvQc-4,2174
+careamics/lightning/dataset_ng/lightning_modules/unet_module.py,sha256=tx48pcuj3CdsQf7tIP-00BtB9kGEnAUX8wnyZh_3lBw,4780
 careamics/losses/__init__.py,sha256=nSWbkBcFhkyUkIT2wVcULqpieyY2Oro39NXZTtfQpXo,351
 careamics/losses/loss_factory.py,sha256=oPacrkwiabsmiW_r--IxX-XPRbzezZUvOuWKbUw5LiI,1518
 careamics/losses/fcn/__init__.py,sha256=kf92MKFGHr6upiztZVgWwtGPf734DZyub92Rn8uEq8o,18
@@ -120,22 +133,24 @@ careamics/losses/lvae/loss_utils.py,sha256=QxzA2N1TglR4H0X0uyTWWytDagE1lA9IB_TK1
 careamics/losses/lvae/losses.py,sha256=wHT1dx04BZ_OI-_S7cFQ5hFmMetm6FSnuZfwZBBtIpY,17977
 careamics/lvae_training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 careamics/lvae_training/calibration.py,sha256=xHbiLcY2csYos3s7rRSqp7P7G-9wzULcSo1JfVzfIjE,7239
-careamics/lvae_training/eval_utils.py,sha256=FxZmmT6vMRluLYnnCEQtLcz5Q45OAqmxXbQo6KPbQEk,30372
+careamics/lvae_training/eval_utils.py,sha256=PWKlG2XrvdfZTG0_brcADaAA0owTeNRT1g673gYtk5k,34410
 careamics/lvae_training/get_config.py,sha256=dwVfaQS7nzjQss0E1gGLUpQpjPcOWwLgIhbu3Z0I1rg,3068
 careamics/lvae_training/lightning_module.py,sha256=ryr7iHqCMzCl5esi6_gEcnKFDQkMrw0EXK9Zfgv1Nek,27186
 careamics/lvae_training/metrics.py,sha256=KTDAKhe3vh-YxzGibjtkIG2nnUyujbnwqX4xGwaRXwE,6718
 careamics/lvae_training/train_lvae.py,sha256=lJEBlBGdISVkZBcEnPNRYgJ7VbapYzZHRaFOrZ0xYGE,11080
 careamics/lvae_training/train_utils.py,sha256=e-d4QsF-li8MmAPkAmB1daHpkuU16nBTnQFZYqpTjn4,3567
-careamics/lvae_training/dataset/__init__.py,sha256=dvdHHaRA9ZfOt_uOnXkYyra2_b0Wsxs8qmrze6zxJAE,377
-careamics/lvae_training/dataset/config.py,sha256=hGIggj5uOZrFBK54o9vii0sG5WGhF_E32URKIIzQMec,4342
+careamics/lvae_training/dataset/__init__.py,sha256=TcsPOoeYXWZh2mTEOodYf4u5dd12TzzkxAaxLzBrMyA,538
+careamics/lvae_training/dataset/config.py,sha256=upMx0NvYtKBi0SHH6WHMfVDzwLzgIk3Nw7z5vRoEvj0,4392
 careamics/lvae_training/dataset/lc_dataset.py,sha256=r4PffRXzuTJ0tLWei4B3wq6f1Q34raaZQzZ0IQXi8OI,10762
-careamics/lvae_training/dataset/multich_dataset.py,sha256=5yMC6bgEIYHBsjFj5gXlc68xJQz8A05TYbYfOo-TdUQ,41672
+careamics/lvae_training/dataset/ms_dataset_ref.py,sha256=uyyz9RjiV3iszQAmavhLhU6PT2B_n6pch3F22ZS4M0o,40892
+careamics/lvae_training/dataset/multich_dataset.py,sha256=kw2gFZPDEp6WdsJwjQ-2EFvxZHe-HI83FhI4C5k39b4,42593
+careamics/lvae_training/dataset/multicrop_dset.py,sha256=MJNUwZmWXszEvr15zX-M9oW9VRxRhMVfh8bTHwFNqWQ,6419
 careamics/lvae_training/dataset/multifile_dataset.py,sha256=hJBs6iBrf_FcyUYzg8rDjvKEICHxDYyXVOj-5L0F6FE,10273
-careamics/lvae_training/dataset/types.py,sha256=SQ99hV9R3iwrRLJs-aRkL3OlmrWWkCrca2JqkntoWZs,633
+careamics/lvae_training/dataset/types.py,sha256=7uCrbL_FQeQfAPz-mHnqHKpZC1x4sdvq9wswmBvOPO0,616
 careamics/lvae_training/dataset/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 careamics/lvae_training/dataset/utils/data_utils.py,sha256=8PvRPqSbYHPCl87cycZHxXIFOT_EoBV-8XCt3ZLh36s,3125
 careamics/lvae_training/dataset/utils/empty_patch_fetcher.py,sha256=OFjeqhZ6vFULJsF5tnoByhEhE8aLHujFToU_yyqMCP4,2266
-careamics/lvae_training/dataset/utils/index_manager.py,sha256=Gt1I-7lBaQDBgqguOmofAFDdAsJQfz7ktvq4_I80F9c,10084
+careamics/lvae_training/dataset/utils/index_manager.py,sha256=rihMe5zOfXvPFvM_2paP0EzK4WhaG6RhRFLy8TxnNas,21654
 careamics/lvae_training/dataset/utils/index_switcher.py,sha256=ZoMi8LsaIkm8MFqIFaxN4oQGyzCcwOlCom8SYNus15E,6716
 careamics/model_io/__init__.py,sha256=khMIkk107LL5JGze0OVfl5Lfi14R3_e4W21tW0iJ1kE,155
 careamics/model_io/bmz_io.py,sha256=XQvRUxM4keEiYlnWNTZUxeLgLl3_c-_drOZcH4mjEDo,7801
@@ -163,10 +178,10 @@ careamics/prediction_utils/lvae_tiling_manager.py,sha256=SI-JaJvLrKWBSHdm-FjcqWd
 careamics/prediction_utils/prediction_outputs.py,sha256=fw-bJ2szWJD7BgZlECmxy5sgeXGFJl4T8cRNzLR1aUQ,4069
 careamics/prediction_utils/stitch_prediction.py,sha256=8YRW2rea-is5tYI0Q1bw3bpX7VMFmbpxSP_y6x9Yfug,3893
 careamics/transforms/__init__.py,sha256=n7D3SbcVSRaMOl5F5Rozo2_lY8dn0DH28ywYIdbXxBo,561
-careamics/transforms/compose.py,sha256=QMCuqp0C5mJ5N6xh3ISKY7HfjfKp6NqDwQiKXoxEjug,5326
+careamics/transforms/compose.py,sha256=ETnI_Z4ZfBWNA12D-KEtr_P8wKeyBQVHvostGG2f_SI,5395
 careamics/transforms/n2v_manipulate.py,sha256=t9rtMbYV6P1IVp4yzuJfq5-giWyfGrxL8ZhzP29Pp8k,5686
 careamics/transforms/n2v_manipulate_torch.py,sha256=Lxi94cbE0aEZ1fFD0m4T7VDrDSt3cbHPdYISa8XYemw,4830
-careamics/transforms/normalize.py,sha256=fxs813ydCWrIzrxFzkbk1gW8OGSr0esQSrNUFSJuGL0,7715
+careamics/transforms/normalize.py,sha256=sVa6uiI2vB1CZJBdgJ6KOlujRmsOQ72YXnhPuQ1QGuE,8314
 careamics/transforms/pixel_manipulation.py,sha256=WSx2sqcZ2wUkm6qPi4pG3Ai0sE8ONPOpYLSvkW5M3bY,13393
 careamics/transforms/pixel_manipulation_torch.py,sha256=W2sTQrM00TwmcoFf1bcYapAwE66pKIVVeAtBIW6ovK4,14343
 careamics/transforms/struct_mask_parameters.py,sha256=jE29Li9sx3olaRnqYfJsSlKi2t0WQzJmCm9aCbIQEsA,421
@@ -178,7 +193,7 @@ careamics/utils/__init__.py,sha256=mLwBQ7wTL2EwDwL3NcX53EHPNklojU45Jcc728y4EWQ,4
 careamics/utils/autocorrelation.py,sha256=M_WYzrEOQngc5iSXWar4S3-EOnK6DfYHPC2vVMeu_Bs,945
 careamics/utils/base_enum.py,sha256=bz1D8mDx5V5hdnJ3WAzJXWHJTbgwAky5FprUt9F5cMA,1387
 careamics/utils/context.py,sha256=SoTZfzG6fO4SDOGHOTL2Xlm1n1CSgb9B57GVhrEkFls,1436
-careamics/utils/lightning_utils.py,sha256=DMMmqx-AlNtddBCqm8b_W3h09qUetz32OMPhdDieFwg,1769
+careamics/utils/lightning_utils.py,sha256=LXzsNiItm8b7yc4NlbEoUEw6_re0SBY8_cmQk1jkf_o,2036
 careamics/utils/logging.py,sha256=5U4VsQ4m4OajtirLH6qUjrM1CAc-oXeCsd6JyROjkWE,10337
 careamics/utils/metrics.py,sha256=i9TQNzVF6lUL9c6OwRZFFDhelZfinkEDpWSCKeduscc,10853
 careamics/utils/path_utils.py,sha256=8AugiG5DOmzgSnTCJI8vypXaPE0XhnR-9pzeiFUZ-0I,554
@@ -188,8 +203,8 @@ careamics/utils/receptive_field.py,sha256=Y2h4c8S6glX3qcx5KHDmO17Kkuyey9voxfoXyq
 careamics/utils/serializers.py,sha256=mILUhz75IMpGKnEzcYu9hlOPG8YIiIW09fk6eZM7Y8k,1427
 careamics/utils/torch_utils.py,sha256=_Cf3HdlIRl5hxfpUg9aofCSlcW7GSsIJxsbSORXko0U,3010
 careamics/utils/version.py,sha256=WKtMlrNmXymJqzMfguBX558D6tb6aoAZfbABRh_ViIs,1142
-careamics-0.0.11.dist-info/METADATA,sha256=AKeMVWNP52xha3axDHE2j_y5wn5OroRFbxvQB1GVUVY,3917
-careamics-0.0.11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-careamics-0.0.11.dist-info/entry_points.txt,sha256=2fSNVXJWDJgFLATVj7MkjFNvpl53amG8tUzC3jf7G1s,53
-careamics-0.0.11.dist-info/licenses/LICENSE,sha256=6zdNW-k_xHRKYWUf9tDI_ZplUciFHyj0g16DYuZ2udw,1509
-careamics-0.0.11.dist-info/RECORD,,
+careamics-0.0.12.dist-info/METADATA,sha256=9novknFJRrDqqO-HD55Wk5TXC7hrZT2sFU1Pt4M0WTI,3919
+careamics-0.0.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+careamics-0.0.12.dist-info/entry_points.txt,sha256=2fSNVXJWDJgFLATVj7MkjFNvpl53amG8tUzC3jf7G1s,53
+careamics-0.0.12.dist-info/licenses/LICENSE,sha256=6zdNW-k_xHRKYWUf9tDI_ZplUciFHyj0g16DYuZ2udw,1509
+careamics-0.0.12.dist-info/RECORD,,

careamics/dataset_ng/dataset/__init__.py

@@ -1,3 +0,0 @@
-__all__ = ["CareamicsDataset"]
-
-from .dataset import CareamicsDataset

careamics/dataset_ng/dataset/dataset.py

@@ -1,184 +0,0 @@
-from collections.abc import Sequence
-from enum import Enum
-from pathlib import Path
-from typing import Literal, NamedTuple, Optional, Union
-
-import numpy as np
-from numpy.typing import NDArray
-from torch.utils.data import Dataset
-from typing_extensions import ParamSpec
-
-from careamics.config import DataConfig, InferenceConfig
-from careamics.config.support import SupportedData
-from careamics.dataset.patching.patching import Stats
-from careamics.dataset_ng.patch_extractor import (
-    ImageStackLoader,
-    PatchExtractor,
-    create_patch_extractor,
-)
-from careamics.dataset_ng.patching_strategies import (
-    FixedRandomPatchingStrategy,
-    PatchingStrategy,
-    PatchSpecs,
-    RandomPatchingStrategy,
-)
-from careamics.transforms import Compose
-
-P = ParamSpec("P")
-
-
-class Mode(str, Enum):
-    TRAINING = "training"
-    VALIDATING = "validating"
-    PREDICTING = "predicting"
-
-
-class ImageRegionData(NamedTuple):
-    data: NDArray
-    source: Union[Path, Literal["array"]]
-    data_shape: Sequence[int]
-    dtype: str  # dtype should be str for collate
-    axes: str
-    region_spec: PatchSpecs
-
-
-InputType = Union[Sequence[np.ndarray], Sequence[Path]]
-
-
-class CareamicsDataset(Dataset):
-    def __init__(
-        self,
-        data_config: Union[DataConfig, InferenceConfig],
-        mode: Mode,
-        inputs: InputType,
-        targets: Optional[InputType] = None,
-        image_stack_loader: Optional[ImageStackLoader[P]] = None,
-        *args: P.args,
-        **kwargs: P.kwargs,
-    ):
-        self.config = data_config
-        self.mode = mode
-
-        data_type_enum = SupportedData(self.config.data_type)
-        self.input_extractor = create_patch_extractor(
-            inputs,
-            self.config.axes,
-            data_type_enum,
-            image_stack_loader,
-            *args,
-            **kwargs,
-        )
-        if targets is not None:
-            self.target_extractor: Optional[PatchExtractor] = create_patch_extractor(
-                targets,
-                self.config.axes,
-                data_type_enum,
-                image_stack_loader,
-                *args,
-                **kwargs,
-            )
-        else:
-            self.target_extractor = None
-
-        self.patching_strategy = self._initialize_patching_strategy()
-
-        self.input_stats, self.target_stats = self._initialize_statistics()
-
-        self.transforms = self._initialize_transforms()
-
-    def _initialize_patching_strategy(self) -> PatchingStrategy:
-        patching_strategy: PatchingStrategy
-        if self.mode == Mode.TRAINING:
-            if isinstance(self.config, InferenceConfig):
-                raise ValueError("Inference config cannot be used for training.")
-            patching_strategy = RandomPatchingStrategy(
-                data_shapes=self.input_extractor.shape,
-                patch_size=self.config.patch_size,
-                # TODO: Add random seed to dataconfig
-                seed=getattr(self.config, "random_seed", None),
-            )
-        elif self.mode == Mode.VALIDATING:
-            if isinstance(self.config, InferenceConfig):
-                raise ValueError("Inference config cannot be used for validating.")
-            patching_strategy = FixedRandomPatchingStrategy(
-                data_shapes=self.input_extractor.shape,
-                patch_size=self.config.patch_size,
-                # TODO: Add random seed to dataconfig
-                seed=getattr(self.config, "random_seed", None),
-            )
-        elif self.mode == Mode.PREDICTING:
-            # TODO: patching strategy will be tilingStrategy in upcoming PR
-            raise NotImplementedError(
-                "Prediction mode for the CAREamicsDataset has not been implemented yet."
-            )
-        else:
-            raise ValueError(f"Unrecognised dataset mode {self.mode}.")
-
-        return patching_strategy
-
-    def _initialize_transforms(self) -> Optional[Compose]:
-        if isinstance(self.config, DataConfig):
-            return Compose(
-                transform_list=list(self.config.transforms),
-            )
-        # TODO: add TTA
-        return None
-
-    def _initialize_statistics(self) -> tuple[Stats, Optional[Stats]]:
-        # TODO: add running stats
-        # Currently assume that stats are provided in the configuration
-        input_stats = Stats(self.config.image_means, self.config.image_stds)
-        target_stats = None
-        if isinstance(self.config, DataConfig):
-            target_means = self.config.target_means
-            target_stds = self.config.target_stds
-            if target_means is not None and target_stds is not None:
-                target_stats = Stats(target_means, target_stds)
-        return input_stats, target_stats
-
-    def __len__(self):
-        return self.patching_strategy.n_patches
-
-    def _create_image_region(
-        self, patch: np.ndarray, patch_spec: PatchSpecs, extractor: PatchExtractor
-    ) -> ImageRegionData:
-        data_idx = patch_spec["data_idx"]
-        return ImageRegionData(
-            data=patch,
-            source=extractor.image_stacks[data_idx].source,
-            dtype=str(extractor.image_stacks[data_idx].data_dtype),
-            data_shape=extractor.image_stacks[data_idx].data_shape,
-            # TODO: should it be axes of the original image instead?
-            axes=self.config.axes,
-            region_spec=patch_spec,
-        )
-
-    def __getitem__(
-        self, index: int
-    ) -> tuple[ImageRegionData, Optional[ImageRegionData]]:
-        patch_spec = self.patching_strategy.get_patch_spec(index)
-        input_patch = self.input_extractor.extract_patch(**patch_spec)
-
-        target_patch = (
-            self.target_extractor.extract_patch(**patch_spec)
-            if self.target_extractor is not None
-            else None
-        )
-
-        if self.transforms is not None:
-            input_patch, target_patch = self.transforms(input_patch, target_patch)
-
-        input_data = self._create_image_region(
-            patch=input_patch, patch_spec=patch_spec, extractor=self.input_extractor
-        )
-
-        if target_patch is not None and self.target_extractor is not None:
-            target_data = self._create_image_region(
-                patch=target_patch,
-                patch_spec=patch_spec,
-                extractor=self.target_extractor,
-            )
-        else:
-            target_data = None
-
-        return input_data, target_data

careamics/dataset_ng/demo_patch_extractor_factory.py

@@ -1,37 +0,0 @@
-# %%
-import numpy as np
-
-from careamics.config import create_n2n_configuration
-from careamics.config.support import SupportedData
-from careamics.dataset_ng.patch_extractor.patch_extractor_factory import (
-    create_patch_extractors,
-)
-
-rng = np.random.default_rng()
-
-# %%
-# define example data
-array1 = np.arange(36).reshape(1, 6, 6)
-array2 = np.arange(50).reshape(2, 5, 5)
-target1 = rng.integers(0, 1, size=array1.shape, endpoint=True)
-target2 = rng.integers(0, 1, size=array2.shape, endpoint=True)
-
-# %%
-config = create_n2n_configuration(
-    "test_exp",
-    data_type="array",
-    axes="SYX",
-    patch_size=[8, 8],
-    batch_size=1,
-    num_epochs=1,
-)
-data_config = config.data_config
-
-# %%
-data_type = SupportedData(data_config.data_type)
-train_inputs, train_targets = create_patch_extractors(
-    [array1, array2], [target1, target2], axes=data_config.axes, data_type=data_type
-)
-
-# %%
-train_inputs.extract_patch(data_idx=0, sample_idx=0, coords=(2, 2), patch_size=(3, 3))