lt-tensor 0.0.1a0__tar.gz

lt_tensor-0.0.1a0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

lt_tensor-0.0.1a0/PKG-INFO

@@ -0,0 +1,31 @@
+Metadata-Version: 2.4
+Name: lt-tensor
+Version: 0.0.1a0
+Summary: General utilities for PyTorch and others. Built for general use.
+Home-page: https://github.com/gr1336/lt-tensor/
+Author: gr1336
+License: Apache Software License (Apache-2.0)
+Classifier: Development Status :: 1 - Planning
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Utilities
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.2.0
+Requires-Dist: torchaudio>=2.2.0
+Requires-Dist: numpy>=1.26.4
+Requires-Dist: tokenizers
+Requires-Dist: pyyaml>=6.0.0
+Requires-Dist: numba>0.60.0
+Requires-Dist: lt-utils==0.0.1a0
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: summary
+
+General utilities for PyTorch and others. Built for general use.

lt_tensor-0.0.1a0/README.md

@@ -0,0 +1 @@
+General utilities for PyTorch and others. Built for general use.

lt_tensor-0.0.1a0/lt_tensor/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1dev3"

lt_tensor-0.0.1a0/lt_tensor/_basics.py

@@ -0,0 +1,270 @@
+__all__ = ["Model"]
+
+
+import warnings
+from ._torch_commons import *
+
+ROOT_DEVICE = torch.device(torch.zeros(1).device)
+
+
+class _ModelDevice(nn.Module):
+    """
+    This makes it easier to assign a device and retrieves it later
+    """
+
+    _device: torch.device = ROOT_DEVICE
+
+    @property
+    def device(self):
+        return self._device
+
+    @device.setter
+    def device(self, device: Union[torch.device, str]):
+        assert isinstance(device, (str, torch.device))
+        self._device = torch.device(device) if isinstance(device, str) else device
+        self.tp_apply_device_to()
+
+    def tp_apply_device_to(self):
+        """Add here components that are needed to have device applied to them,
+        that usualy the '.to()' function fails to apply
+
+        example:
+        ```
+        def tp_apply_device_to(self):
+            self.my_tensor = self.my_tensor.to(device=self.device)
+        ```
+        """
+        pass
+
+    def to(self, *args, **kwargs):
+        device, dtype, non_blocking, convert_to_format = torch._C._nn._parse_to(
+            *args, **kwargs
+        )
+
+        if dtype is not None:
+            if not (dtype.is_floating_point or dtype.is_complex):
+                raise TypeError(
+                    "nn.Module.to only accepts floating point or complex "
+                    f"dtypes, but got desired dtype={dtype}"
+                )
+            if dtype.is_complex:
+                warnings.warn(
+                    "Complex modules are a new feature under active development whose design may change, "
+                    "and some modules might not work as expected when using complex tensors as parameters or buffers. "
+                    "Please file an issue at https://github.com/pytorch/pytorch/issues/new?template=bug-report.yml "
+                    "if a complex module does not work as expected."
+                )
+
+        def convert(t: Tensor):
+            try:
+                if convert_to_format is not None and t.dim() in (4, 5):
+                    return t.to(
+                        device,
+                        dtype if t.is_floating_point() or t.is_complex() else None,
+                        non_blocking,
+                        memory_format=convert_to_format,
+                    )
+                return t.to(
+                    device,
+                    dtype if t.is_floating_point() or t.is_complex() else None,
+                    non_blocking,
+                )
+            except NotImplementedError as e:
+                if str(e) == "Cannot copy out of meta tensor; no data!":
+                    raise NotImplementedError(
+                        f"{e} Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() "
+                        f"when moving module from meta to a different device."
+                    ) from None
+                else:
+                    raise
+
+        self._apply(convert)
+        self.device = device
+        return self
+
+    def ipu(self, device: Optional[Union[int, torch.device]] = None) -> T:
+        super().ipu(device)
+        dvc = "ipu"
+        if device is not None:
+            dvc += (
+                ":" + str(device) if isinstance(device, (int, float)) else device.index
+            )
+        self.device = dvc
+        return self
+
+    def xpu(self, device: Optional[Union[int, torch.device]] = None) -> T:
+        super().xpu(device)
+        dvc = "xpu"
+        if device is not None:
+            dvc += (
+                ":" + str(device) if isinstance(device, (int, float)) else device.index
+            )
+        self.device = dvc
+        return self
+
+    def cuda(self, device: Optional[Union[int, torch.device]] = None) -> T:
+        super().cuda(device)
+        dvc = "cuda"
+        if device is not None:
+            dvc += (
+                ":" + str(device) if isinstance(device, (int, float)) else device.index
+            )
+        self.device = dvc
+        return self
+
+    def mtia(self, device: Optional[Union[int, torch.device]] = None) -> T:
+        super().mtia(device)
+        dvc = "mtia"
+        if device is not None:
+            dvc += (
+                ":" + str(device) if isinstance(device, (int, float)) else device.index
+            )
+        self.device = dvc
+        return self
+
+    def cpu(self) -> T:
+        super().cpu()
+        self.device = "cpu"
+        return self
+
+
+class Model(_ModelDevice, ABC):
+    _autocast: bool = False
+
+    @property
+    def autocast(self):
+        return self._autocast
+
+    @autocast.setter
+    def autocast(self, value: bool):
+        self._autocast = value
+
+    def count_trainable_parameters(self, module_name: Optional[str] = None):
+        """Gets the number of trainable parameters from either the entire model or from a specific module."""
+        if module_name is not None:
+            assert hasattr(self, module_name), f"Module {module_name} does not exits"
+            module = getattr(self, module_name)
+            return sum(
+                [
+                    x.numel()
+                    for x in module.parameters()
+                    if hasattr(x, "requires_grad") and x.requires_grad
+                ]
+            )
+        return sum(
+            [
+                x.numel()
+                for x in self.parameters()
+                if hasattr(x, "requires_grad") and x.requires_grad
+            ]
+        )
+
+    def count_non_trainable_parameters(self, module_name: Optional[str] = None):
+        """Gets the number of non-trainable parameters from either the entire model or from a specific module."""
+        if module_name is not None:
+            assert hasattr(self, module_name), f"Module {module_name} does not exits"
+            module = getattr(self, module_name)
+            return sum(
+                [
+                    x.numel()
+                    for x in module.parameters()
+                    if not hasattr(x, "requires_grad") or not x.requires_grad
+                ]
+            )
+        return sum(
+            [
+                x.numel()
+                for x in self.parameters()
+                if not hasattr(x, "requires_grad") or not x.requires_grad
+            ]
+        )
+
+    def get_weights(self, module_name: Optional[str] = None) -> List[Tensor]:
+        """Returns the weights of the model entrie model or from a specified module"""
+        if module_name is not None:
+            assert hasattr(self, module_name), f"Module {module_name} does not exits"
+            module = getattr(self, module_name)
+            return [x.data.detach() for x in module.parameters()]
+        return [x.data.detach() for x in self.parameters()]
+
+    def print_trainable_parameters(
+        self, module_name: Optional[str] = None
+    ) -> List[Tensor]:
+        params = format(self.count_trainable_parameters(module_name), ",").replace(
+            ",", "."
+        )
+        if module_name:
+            print(f'Trainable Parameters from "{module_name}": {params}')
+        else:
+            print(f"Trainable Parameters: {params}")
+
+    def print_non_trainable_parameters(
+        self, module_name: Optional[str] = None
+    ) -> List[Tensor]:
+        params = format(self.count_non_trainable_parameters(module_name), ",").replace(
+            ",", "."
+        )
+        if module_name:
+            print(f'Non-Trainable Parameters from "{module_name}": {params}')
+        else:
+            print(f"Non-Trainable Parameters: {params}")
+
+    def save_weights(self, path: Union[Path, str]):
+        path = Path(path)
+        if path.exists():
+            assert (
+                path.is_file()
+            ), "The provided path exists but its a directory not a file!"
+            path.rmdir()
+        path.parent.mkdir(exist_ok=True, parents=True)
+        torch.save(obj=self.state_dict(), f=str(path))
+
+    def load_weights(
+        self,
+        path: Union[Path, str],
+        raise_if_not_exists: bool = False,
+        strict: bool = True,
+        assign: bool = False,
+        weights_only: bool = False,
+        mmap: Optional[bool] = None,
+        **torch_loader_kwargs,
+    ):
+        path = Path(path)
+        if not path.exists():
+            assert not raise_if_not_exists, "Path does not exists!"
+            return None
+        assert path.is_file(), "The provided path is not a valid file!"
+        state_dict = torch.load(
+            str(path), weights_only=weights_only, mmap=mmap, **torch_loader_kwargs
+        )
+        incompatible_keys = self.load_state_dict(
+            state_dict,
+            strict=strict,
+            assign=assign,
+        )
+        return incompatible_keys
+
+    @torch.no_grad()
+    def inference(self, *args, **kwargs):
+        if self.training:
+            self.eval()
+        if self.autocast:
+            with torch.autocast(device_type=self.device.type):
+                return self(*args, **kwargs)
+        return self(*args, **kwargs)
+
+    def train_step(
+        self,
+        *args,
+        **kwargs,
+    ):
+        """Train Step"""
+        if not self.training:
+            self.train()
+        return self(*args, **kwargs)
+
+    @abstractmethod
+    def forward(
+        self, *args, **kwargs
+    ) -> Union[Tensor, Sequence[Tensor], Dict[Any, Union[Any, Tensor]]]:
+        pass

lt_tensor-0.0.1a0/lt_tensor/_torch_commons.py

@@ -0,0 +1,12 @@
+import torch
+from torch import nn, optim
+import torch.nn.functional as F
+from torch.optim import Optimizer
+from torch.nn import Module, L1Loss, MSELoss
+from torch.nn.utils import remove_weight_norm
+from torch import Tensor, FloatTensor, device, LongTensor
+from torch.nn.utils.parametrizations import weight_norm, spectral_norm
+
+from lt_utils.common import *
+
+DeviceType: TypeAlias = Union[device, str]

lt_tensor-0.0.1a0/lt_tensor/lr_schedulers.py

@@ -0,0 +1,114 @@
+__all__ = [
+    "WarmupDecayScheduler",
+    "AdaptiveDropScheduler",
+    "WaveringLRScheduler",
+]
+
+import math
+from torch.optim import Optimizer
+from torch.optim.lr_scheduler import _LRScheduler
+
+
+class WarmupDecayScheduler(_LRScheduler):
+    def __init__(
+        self,
+        optimizer: Optimizer,
+        warmup_steps: int,
+        total_steps: int,
+        decay_type: str = "linear",  # or "cosine"
+        min_lr: float = 0.0,
+        last_epoch: int = -1,
+    ):
+        self.warmup_steps = warmup_steps
+        self.total_steps = total_steps
+        self.decay_type = decay_type
+        self.min_lr = min_lr
+        super().__init__(optimizer, last_epoch)
+
+    def get_lr(self):
+        step = self.last_epoch + 1
+        warmup = self.warmup_steps
+        total = self.total_steps
+        lrs = []
+
+        for base_lr in self.base_lrs:
+            if step < warmup:
+                lr = base_lr * step / warmup
+            else:
+                progress = (step - warmup) / max(1, total - warmup)
+                if self.decay_type == "linear":
+                    lr = base_lr * (1.0 - progress)
+                elif self.decay_type == "cosine":
+                    lr = base_lr * 0.5 * (1 + math.cos(math.pi * progress))
+                else:
+                    raise ValueError(f"Unknown decay type: {self.decay_type}")
+
+            lr = max(self.min_lr, lr)
+            lrs.append(lr)
+
+        return lrs
+
+
+class AdaptiveDropScheduler(_LRScheduler):
+    def __init__(
+        self,
+        optimizer,
+        drop_factor=0.5,
+        patience=10,
+        min_lr=1e-6,
+        cooldown=5,
+        last_epoch=-1,
+    ):
+        self.drop_factor = drop_factor
+        self.patience = patience
+        self.min_lr = min_lr
+        self.cooldown = cooldown
+        self.cooldown_counter = 0
+        self.best_loss = float("inf")
+        self.bad_steps = 0
+        super().__init__(optimizer, last_epoch)
+
+    def step(self, val_loss=None):
+        if val_loss is not None:
+            if val_loss < self.best_loss:
+                self.best_loss = val_loss
+                self.bad_steps = 0
+                self.cooldown_counter = 0
+            else:
+                self.bad_steps += 1
+                if self.bad_steps >= self.patience and self.cooldown_counter == 0:
+                    for i, group in enumerate(self.optimizer.param_groups):
+                        new_lr = max(group["lr"] * self.drop_factor, self.min_lr)
+                        group["lr"] = new_lr
+                    self.cooldown_counter = self.cooldown
+                    self.bad_steps = 0
+        if self.cooldown_counter > 0:
+            self.cooldown_counter -= 1
+
+    def get_lr(self):
+        return [group["lr"] for group in self.optimizer.param_groups]
+
+
+class WaveringLRScheduler(_LRScheduler):
+    def __init__(
+        self, optimizer, base_lr, max_lr, period=1000, decay=0.999, last_epoch=-1
+    ):
+        """
+        Sinusoidal-like oscillating LR. Can escape shallow local minima.
+        - base_lr: minimum LR
+        - max_lr: maximum LR
+        - period: full sine cycle in steps
+        - decay: multiplies max_lr each cycle
+        """
+        self.base_lr = base_lr
+        self.max_lr = max_lr
+        self.period = period
+        self.decay = decay
+        super().__init__(optimizer, last_epoch)
+
+    def get_lr(self):
+        cycle = self.last_epoch // self.period
+        step_in_cycle = self.last_epoch % self.period
+        factor = math.sin(math.pi * step_in_cycle / self.period)
+        amplitude = (self.max_lr - self.base_lr) * (self.decay**cycle)
+        return [self.base_lr + amplitude * factor for _ in self.optimizer.param_groups]