diffct 2.0.0__py3-none-any.whl → 2.0.2__py3-none-any.whl

diffct/__init__.py

@@ -49,7 +49,7 @@ try:
 except ImportError:
     pass
 
-__version__ = '2.0.0'
+__version__ = '2.0.2'
 
 __all__ = [
     'Projector',

diffct/analytical.py

@@ -34,6 +34,7 @@ from .utils import (
     _get_numba_external_stream_for,
     _grid_2d,
     _grid_3d,
+    _on_device_of,
 )
 from .kernels import (
     _parallel_2d_fbp_backproject_kernel,
@@ -365,6 +366,7 @@ def _as_contig_f32(t, device):
     return DeviceManager.ensure_device(t, device).to(dtype=torch.float32).contiguous()
 
 
+@_on_device_of("sinogram")
 def parallel_weighted_backproject(sinogram, ray_dir, det_origin, det_u_vec,
                                   detector_spacing, H, W, voxel_spacing=1.0):
     """Voxel-driven parallel-beam FBP backprojection with analytical constant.
@@ -448,6 +450,7 @@ def _analytical_geometry(src_pos, det_center, n, isocenter):
     return isocenter, float(sid_n.mean().item()), float(sdd_n.mean().item())
 
 
+@_on_device_of("sinogram")
 def fan_weighted_backproject(sinogram, src_pos, det_center, det_u_vec,
                              detector_spacing, H, W, voxel_spacing=1.0, *, isocenter=None):
     """Voxel-driven fan-beam FBP backprojection with analytical constant.
@@ -503,6 +506,7 @@ def fan_weighted_backproject(sinogram, src_pos, det_center, det_u_vec,
     return reco * scale
 
 
+@_on_device_of("sinogram")
 def cone_weighted_backproject(sinogram, src_pos, det_center, det_u_vec, det_v_vec,
                               D, H, W, du, dv, voxel_spacing=1.0, *, isocenter=None):
     """Voxel-driven cone-beam FDK backprojection with analytical constant.

diffct/geometry.py

@@ -13,6 +13,17 @@ from typing import Callable, Tuple
 # Trajectory Generation Functions
 # ============================================================================
 
+def _check_source_positions(src_pos):
+    """Reject non-finite sources and sources at the isocenter, which have no viewing direction."""
+    if not torch.isfinite(src_pos).all():
+        raise ValueError("source_path_fn returned non-finite source positions")
+    if (torch.linalg.vector_norm(src_pos.detach(), dim=1) == 0).any():
+        raise ValueError(
+            "source_path_fn returned a source at the isocenter; every source needs a "
+            "nonzero distance from the origin"
+        )
+
+
 def circular_trajectory_3d(n_views, sid, sdd, start_angle=0.0, end_angle=None, device='cuda', dtype=torch.float32):
     """Generate circular trajectory geometry for cone-beam CT.
 
@@ -500,11 +511,11 @@ def custom_trajectory_3d(n_views, sid, sdd,
 
     Examples
     --------
-    >>> # Define a custom figure-8 trajectory
+    >>> # Circular orbit with a two-lobe (figure-8) vertical motion
     >>> def figure8_path(angles, sid):
     ...     src_pos = torch.zeros((len(angles), 3), device=angles.device, dtype=angles.dtype)
     ...     src_pos[:, 0] = -sid * torch.sin(angles)
-    ...     src_pos[:, 1] = sid * torch.cos(angles) * torch.sin(angles)
+    ...     src_pos[:, 1] = sid * torch.cos(angles)
     ...     src_pos[:, 2] = 50 * torch.sin(2 * angles)
     ...     return src_pos
     >>>
@@ -523,6 +534,7 @@ def custom_trajectory_3d(n_views, sid, sdd,
     if src_pos.shape != (n_views, 3):
         raise ValueError(f"source_path_fn must return tensor of shape ({n_views}, 3), "
                         f"got {src_pos.shape}")
+    _check_source_positions(src_pos)
 
     # Keep the entire frame in the source-path autograd graph. Constructing
     # tensors from scalar tensors detaches them; rewriting view slices in
@@ -750,6 +762,7 @@ def custom_trajectory_2d_fan(n_views, sid, sdd,
     if src_pos.shape != (n_views, 2):
         raise ValueError(f"source_path_fn must return tensor of shape ({n_views}, 2), "
                         f"got {src_pos.shape}")
+    _check_source_positions(src_pos)
 
     # Preallocate remaining position matrices
     det_center = torch.zeros((n_views, 2), device=device, dtype=dtype)

diffct/operators.py

@@ -523,6 +523,15 @@ class Projector:
             *self.detector_spacing, self.voxel_spacing,
         )
 
+    @property
+    def process_group(self):
+        """Process group of a distributed operator, or None for the default group.
+
+        Pass it as ``group=`` to collectives that combine per-rank results of this
+        operator, so they use the same ranks as the operator.
+        """
+        return self._process_group
+
     def project(self, volume):
         """Project a ``(H, W)`` or ``(D, H, W)`` CUDA tensor to float32.
 

diffct/projectors.py

@@ -12,6 +12,7 @@ from .utils import (
     DeviceManager,
     TorchCUDABridge,
     _get_numba_external_stream_for,
+    _on_device_of,
     _trig_tables,
     _validate_3d_memory_layout,
     _grid_2d,
@@ -77,6 +78,7 @@ class _GeometryVJPFunction(torch.autograd.Function):
     """First-order geometry gradient; differentiating it again raises."""
 
     @staticmethod
+    @_on_device_of("volume")
     def forward(ctx, beam, volume, grad_sino, detector_spacing, voxel_spacing, *geometry):
         return _geometry_vjp(beam, volume, grad_sino, geometry, detector_spacing, voxel_spacing)
 
@@ -119,23 +121,17 @@ class ParallelProjectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import ParallelProjectorFunction
+    >>> from diffct import ParallelProjectorFunction, circular_trajectory_2d_parallel
     >>>
-    >>> # Create a 2D image with gradient tracking
     >>> image = torch.randn(128, 128, device='cuda', requires_grad=True)
-    >>> # Define projection parameters
-    >>> angles = torch.linspace(0, torch.pi, 180, device='cuda')
-    >>> num_detectors = 128
-    >>> detector_spacing = 1.0
-    >>> # Compute forward projection
-    >>> projector = ParallelProjectorFunction.apply
-    >>> sinogram = projector(image, angles, num_detectors, detector_spacing)
-    >>> # Compute loss and gradients
-    >>> loss = sinogram.sum()
-    >>> loss.backward()
-    >>> print(f"Gradient shape: {image.grad.shape}")  # (128, 128)
+    >>> ray_dir, det_origin, det_u_vec = circular_trajectory_2d_parallel(180, device='cuda')
+    >>> sinogram = ParallelProjectorFunction.apply(image, ray_dir, det_origin, det_u_vec, 192, 1.0)
+    >>> sinogram.sum().backward()
+    >>> image.grad.shape
+    torch.Size([128, 128])
     """
     @staticmethod
+    @_on_device_of("image")
     def forward(ctx, image, ray_dir, det_origin, det_u_vec, num_detectors, detector_spacing=1.0, voxel_spacing=1.0):
         """Compute the 2D parallel beam forward projection with arbitrary trajectories using CUDA acceleration.
 
@@ -254,16 +250,17 @@ class ParallelBackprojectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import ParallelBackprojectorFunction
+    >>> from diffct import ParallelBackprojectorFunction, circular_trajectory_2d_parallel
     >>>
-    >>> sinogram = torch.randn(180, 128, device='cuda', requires_grad=True)
-    >>> angles = torch.linspace(0, torch.pi, 180, device='cuda')
-    >>> recon = ParallelBackprojectorFunction.apply(sinogram, angles, 1.0, 128, 128)
-    >>> loss = recon.sum()
-    >>> loss.backward()
-    >>> print(sinogram.grad.shape)  # (180, 128)
+    >>> sinogram = torch.randn(180, 192, device='cuda', requires_grad=True)
+    >>> ray_dir, det_origin, det_u_vec = circular_trajectory_2d_parallel(180, device='cuda')
+    >>> image = ParallelBackprojectorFunction.apply(sinogram, ray_dir, det_origin, det_u_vec, 1.0, 128, 128)
+    >>> image.sum().backward()
+    >>> sinogram.grad.shape
+    torch.Size([180, 192])
     """
     @staticmethod
+    @_on_device_of("sinogram")
     def forward(ctx, sinogram, ray_dir, det_origin, det_u_vec, detector_spacing=1.0, H=128, W=128, voxel_spacing=1.0):
         """Compute the 2D parallel beam backprojection with arbitrary trajectories using CUDA acceleration.
 
@@ -384,16 +381,17 @@ class FanProjectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import FanProjectorFunction
+    >>> from diffct import FanProjectorFunction, circular_trajectory_2d_fan
     >>>
     >>> image = torch.randn(256, 256, device='cuda', requires_grad=True)
-    >>> angles = torch.linspace(0, 2 * torch.pi, 360, device='cuda')
-    >>> sinogram = FanProjectorFunction.apply(image, angles, 512, 1.0, 1500.0, 1000.0)
-    >>> loss = sinogram.sum()
-    >>> loss.backward()
-    >>> print(image.grad.shape)  # (256, 256)
+    >>> src_pos, det_center, det_u_vec = circular_trajectory_2d_fan(360, sid=1000.0, sdd=1500.0, device='cuda')
+    >>> sinogram = FanProjectorFunction.apply(image, src_pos, det_center, det_u_vec, 512, 1.0)
+    >>> sinogram.sum().backward()
+    >>> image.grad.shape
+    torch.Size([256, 256])
     """
     @staticmethod
+    @_on_device_of("image")
     def forward(ctx, image, src_pos, det_center, det_u_vec, num_detectors, detector_spacing, voxel_spacing=1.0):
         """Compute the 2D fan beam forward projection with arbitrary trajectories using CUDA acceleration.
 
@@ -511,16 +509,17 @@ class FanBackprojectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import FanBackprojectorFunction
+    >>> from diffct import FanBackprojectorFunction, circular_trajectory_2d_fan
     >>>
     >>> sinogram = torch.randn(360, 512, device='cuda', requires_grad=True)
-    >>> angles = torch.linspace(0, 2 * torch.pi, 360, device='cuda')
-    >>> recon = FanBackprojectorFunction.apply(sinogram, angles, 1.0, 256, 256, 1500.0, 1000.0)
-    >>> loss = recon.sum()
-    >>> loss.backward()
-    >>> print(sinogram.grad.shape)  # (360, 512)
+    >>> src_pos, det_center, det_u_vec = circular_trajectory_2d_fan(360, sid=1000.0, sdd=1500.0, device='cuda')
+    >>> image = FanBackprojectorFunction.apply(sinogram, src_pos, det_center, det_u_vec, 1.0, 256, 256)
+    >>> image.sum().backward()
+    >>> sinogram.grad.shape
+    torch.Size([360, 512])
     """
     @staticmethod
+    @_on_device_of("sinogram")
     def forward(ctx, sinogram, src_pos, det_center, det_u_vec, detector_spacing, H, W, voxel_spacing=1.0):
         """Compute the 2D fan beam backprojection with arbitrary trajectories using CUDA acceleration.
 
@@ -639,16 +638,19 @@ class ConeProjectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import ConeProjectorFunction
+    >>> from diffct import ConeProjectorFunction, circular_trajectory_3d
     >>>
     >>> volume = torch.randn(128, 128, 128, device='cuda', requires_grad=True)
-    >>> angles = torch.linspace(0, 2 * torch.pi, 360, device='cuda')
-    >>> projections = ConeProjectorFunction.apply(volume, angles, 256, 256, 1.0, 1.0, 1500.0, 1000.0)
-    >>> loss = projections.sum()
-    >>> loss.backward()
-    >>> print(volume.grad.shape)  # (128, 128, 128)
+    >>> src_pos, det_center, det_u_vec, det_v_vec = circular_trajectory_3d(360, sid=1000.0, sdd=1500.0, device='cuda')
+    >>> projections = ConeProjectorFunction.apply(
+    ...     volume, src_pos, det_center, det_u_vec, det_v_vec, 256, 256, 1.0, 1.0
+    ... )
+    >>> projections.sum().backward()
+    >>> volume.grad.shape
+    torch.Size([128, 128, 128])
     """
     @staticmethod
+    @_on_device_of("volume")
     def forward(ctx, volume, src_pos, det_center, det_u_vec, det_v_vec, det_u, det_v, du, dv, voxel_spacing=1.0):
         """Compute the 3D cone beam forward projection with arbitrary trajectories using CUDA acceleration.
 
@@ -784,20 +786,19 @@ class ConeBackprojectorFunction(torch.autograd.Function):
     Examples
     --------
     >>> import torch
-    >>> from diffct.differentiable import ConeBackprojectorFunction
+    >>> from diffct import ConeBackprojectorFunction, circular_trajectory_3d
     >>>
     >>> projections = torch.randn(360, 256, 256, device='cuda', requires_grad=True)
-    >>> angles = torch.linspace(0, 2 * torch.pi, 360, device='cuda')
-    >>> D, H, W = 128, 128, 128
-    >>> du, dv = 1.0, 1.0
-    >>> sdd, sid = 1500.0, 1000.0
-    >>> backprojector = ConeBackprojectorFunction.apply
-    >>> volume = backprojector(projections, angles, D, H, W, du, dv, sdd, sid)
-    >>> loss = volume.sum()
-    >>> loss.backward()
-    >>> print(f"Projection gradient shape: {projections.grad.shape}")  # (360, 256, 256)
+    >>> src_pos, det_center, det_u_vec, det_v_vec = circular_trajectory_3d(360, sid=1000.0, sdd=1500.0, device='cuda')
+    >>> volume = ConeBackprojectorFunction.apply(
+    ...     projections, src_pos, det_center, det_u_vec, det_v_vec, 128, 128, 128, 1.0, 1.0
+    ... )
+    >>> volume.sum().backward()
+    >>> projections.grad.shape
+    torch.Size([360, 256, 256])
     """
     @staticmethod
+    @_on_device_of("sinogram")
     def forward(ctx, sinogram, src_pos, det_center, det_u_vec, det_v_vec, D, H, W, du, dv, voxel_spacing=1.0):
         """Compute the 3D cone beam backprojection with arbitrary trajectories using CUDA acceleration.
 

diffct/utils.py

@@ -5,7 +5,12 @@ PyTorch-CUDA bridging, stream caching, trigonometric table generation,
 memory layout validation, and CUDA grid computation.
 """
 
+import atexit
+import contextlib
+import functools
+import inspect
 import math
+import weakref
 import numpy as np
 import torch
 from numba import cuda
@@ -150,6 +155,68 @@ def _get_numba_external_stream_for(pt_stream=None):
     return numba_stream
 
 
+@contextlib.contextmanager
+def _cuda_context(device):
+    """Make ``device`` the current device for PyTorch and Numba.
+
+    Kernel launches then use the CUDA context and the current stream of the
+    device that holds the data, not of the device that happens to be current.
+    """
+    device = torch.device(device)
+    with torch.cuda.device(device), cuda.gpus[device.index]:
+        yield
+
+
+def _on_device_of(name):
+    """Run the decorated function in the CUDA context of its argument ``name``.
+
+    The argument may be passed by position or by keyword.
+    """
+    def decorate(fn):
+        signature = inspect.signature(fn)
+
+        @functools.wraps(fn)
+        def wrapper(*args, **kwargs):
+            bound = signature.bind_partial(*args, **kwargs).arguments
+            tensor = bound[name] if name in bound else None
+            if not (isinstance(tensor, torch.Tensor) and tensor.is_cuda):
+                return fn(*args, **kwargs)
+            with _cuda_context(tensor.device):
+                return fn(*args, **kwargs)
+        return wrapper
+    return decorate
+
+
+def _keep_cuda_modules_at_exit():
+    """Stop numba-cuda from unloading CUDA modules while the interpreter exits.
+
+    numba-cuda queues module unloads and other deallocations, and flushes a
+    queue once it passes a count or byte limit. After kernels were loaded on
+    several GPUs, a flush during interpreter shutdown can unload the same
+    library twice and corrupt the heap, so the process crashes after all work
+    is done. The process exit releases these resources anyway.
+
+    Raising the limits is not enough: the byte limit is
+    ``int(capacity * CUDA_DEALLOCS_RATIO)``, and queues with no capacity set
+    have a limit of 0 bytes for any finite ratio. numba-cuda skips the flush
+    while a queue is disabled, so disable every queue for the rest of the exit.
+    """
+    from numba.cuda.cudadrv.driver import _PendingDeallocs
+
+    _PendingDeallocs.is_disabled = property(lambda self: True)
+
+
+class _ExitOrderAnchor:
+    pass
+
+
+# weakref.finalize registers its atexit hook with its first finalizer. Create one
+# now, so that the handler below is registered later and runs before it.
+_EXIT_ORDER_ANCHOR = _ExitOrderAnchor()
+weakref.finalize(_EXIT_ORDER_ANCHOR, lambda: None)
+atexit.register(_keep_cuda_modules_at_exit)
+
+
 # ============================================================================
 # GPU-aware Trigonometric Table Generation
 # ============================================================================
@@ -185,6 +252,8 @@ def _trig_tables(angles, dtype=_DTYPE, device=None):
     """
     if isinstance(angles, torch.Tensor):
         device = angles.device if device is None else device
+        if not isinstance(dtype, torch.dtype):
+            dtype = torch.from_numpy(np.zeros(0, dtype=dtype)).dtype
         # Compute both cos and sin in one call to avoid redundant kernel launches
         angles_device = angles.to(dtype=dtype, device=device)
         cos = torch.cos(angles_device)

{diffct-2.0.0.dist-info → diffct-2.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: diffct
-Version: 2.0.0
+Version: 2.0.2
 Summary: Differentiable CUDA projectors for CT: arbitrary trajectories, multi-GPU and multi-node execution, geometry gradients
 Project-URL: Homepage, https://github.com/sypsyp97/diffct
 Project-URL: Documentation, https://sypsyp97.github.io/diffct/
@@ -31,7 +31,7 @@ Description-Content-Type: text/markdown
 
 <h1 align="center">diffct</h1>
 
-<p align="center">English · <a href="README.zh.md">简体中文</a></p>
+<p align="center">English · <a href="https://github.com/sypsyp97/diffct/blob/main/README.zh.md">简体中文</a></p>
 
 <p align="center">
   Differentiable CUDA projectors for CT: arbitrary trajectories, multi-GPU, multi-node, geometry gradients.
@@ -43,15 +43,15 @@ Description-Content-Type: text/markdown
   <a href="https://pypi.org/project/diffct/"><img src="https://img.shields.io/pypi/v/diffct.svg?style=flat-square&logo=pypi&logoColor=white" alt="PyPI version"></a>
   <a href="https://sypsyp97.github.io/diffct/"><img src="https://img.shields.io/github/actions/workflow/status/sypsyp97/diffct/docs.yml?branch=main&label=docs&style=flat-square" alt="Documentation"></a>
   <a href="https://github.com/sypsyp97/diffct/actions"><img src="https://img.shields.io/github/actions/workflow/status/sypsyp97/diffct/ci.yml?branch=main&label=CI&style=flat-square" alt="CI/CD"></a>
-  <a href="https://deepwiki.com/sypsyp97/diffct"><img src="docs/assets/deepwiki-badge.svg" alt="Ask DeepWiki"></a>
+  <a href="https://deepwiki.com/sypsyp97/diffct"><img src="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/deepwiki-badge.svg" alt="Ask DeepWiki"></a>
 </p>
 
 <p align="center">
-  <img src="docs/assets/diffct_intro.gif" width="100%" alt="diffct intro: projection, sinogram, trajectories, multi-GPU split, reconstruction and geometry calibration">
+  <img src="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/diffct_intro.gif" width="100%" alt="diffct intro: projection, sinogram, trajectories, multi-GPU split, reconstruction and geometry calibration">
 </p>
 
 <p align="center">
-  <a href="docs/assets/diffct_intro.mp4">Intro video (MP4)</a> ·
+  <a href="https://github.com/sypsyp97/diffct/blob/main/docs/assets/diffct_intro.mp4">Intro video (MP4)</a> ·
   <a href="https://www.preprints.org/manuscript/202605.1446/v1">Technical report</a> ·
   <a href="https://doi.org/10.20944/preprints202605.1446.v1">DOI</a>
 </p>
@@ -65,7 +65,9 @@ Description-Content-Type: text/markdown
   <a href="#citation">Citation</a>
 </p>
 
-> **Version 2.0** replaces the circular-orbit API of 1.x with per-view trajectories. Code written for 1.x needs changes; see the [migration notes](docs/MIGRATION.md).
+> **Install** with the CUDA extra, `pip install "diffct[cu12]"` or `pip install "diffct[cu13]"`, after PyTorch. A plain `pip install diffct` needs a system CUDA Toolkit.
+>
+> **Version 2.0** replaces the circular-orbit API of 1.x with per-view trajectories. Code written for 1.x needs changes; see the [migration notes](https://github.com/sypsyp97/diffct/blob/main/docs/MIGRATION.md).
 > For Apple Silicon, use the [MLX port by Linda-Sophie Schneider](https://github.com/Linda-SophieSchneider/DiffCT-MLX).
 
 ## Why diffct
@@ -76,18 +78,20 @@ To our knowledge, diffct is the only open-source GPU CT library that combines ar
 - **Matched operators.** `project()` and `backproject()` form an exact adjoint pair for the cell-constant Siddon model. Both support PyTorch autograd, with volume/sinogram gradients and Hessian-vector products.
 - **Multi-GPU and multi-node.** Use `devices=[0, 1, 2, 3]` in one process, or one process per GPU with torchrun and NCCL. Views are partitioned and the volume is replicated. Speedup depends on workload and communication costs.
 - **Analytical helpers.** `diffct.analytical` provides ramp filters (ram-lak, shepp-logan, cosine, hamming, hann), fan, cone and Parker weights, and FBP and FDK backprojection.
-- **Validated.** FDK matches ASTRA 2.5.0 `FDK_CUDA`: PSNR within 0.3 dB. Geometry gradients match an independent float64 reference to about 1e-6. The [recorded A100 validation](docs/VALIDATION.md) reports 229 passing pytest tests. Full notes: [REFERENCE](docs/REFERENCE.md#validation-summary).
 
-Capabilities, limits and isocenter rules: [docs/REFERENCE.md](docs/REFERENCE.md#capabilities-and-limits).
+Capabilities, limits and isocenter rules: [docs/REFERENCE.md](https://github.com/sypsyp97/diffct/blob/main/docs/REFERENCE.md#capabilities-and-limits).
 
 ## Install
 
-You need a CUDA GPU and PyTorch. Install PyTorch for your CUDA version first.
+You need an NVIDIA GPU. Install PyTorch for your CUDA version first. Then install diffct with the extra for the same CUDA major version:
 
 ```bash
-pip install "diffct[cu12]"    # [cu13] for CUDA 13; install PyTorch for your CUDA first
+pip install "diffct[cu12]"    # PyTorch built for CUDA 12
+pip install "diffct[cu13]"    # PyTorch built for CUDA 13
 ```
 
+The extra installs the CUDA compiler libraries that Numba CUDA needs to compile the kernels. A plain `pip install diffct` does not install them. Use it only if a CUDA Toolkit is already installed on the system.
+
 From source, with the examples:
 
 ```bash
@@ -130,11 +134,11 @@ loss = 0.5 * (A.project(x) - sinogram).square().sum()
 loss.backward()                     # x.grad = A^T (A x - y)
 ```
 
-**Custom or calibrated trajectories.** Pass calibrated tensors directly instead of a generator; no circular fit is needed. See [REFERENCE](docs/REFERENCE.md#custom-or-calibrated-trajectories).
+**Custom or calibrated trajectories.** Pass calibrated tensors directly instead of a generator; no circular fit is needed. See [REFERENCE](https://github.com/sypsyp97/diffct/blob/main/docs/REFERENCE.md#custom-or-calibrated-trajectories).
 
-**Geometry gradients.** Set `requires_grad=True` on trajectory tensors before you build `Projector`. See [REFERENCE](docs/REFERENCE.md#geometry-gradients).
+**Geometry gradients.** Set `requires_grad=True` on trajectory tensors before you build `Projector`. See [REFERENCE](https://github.com/sypsyp97/diffct/blob/main/docs/REFERENCE.md#geometry-gradients).
 
-**Several GPUs and nodes.** Use `devices=[0, 1, 2, 3]` in one process, or one process per GPU with torchrun for one or more nodes. See [REFERENCE](docs/REFERENCE.md#several-gpus-and-nodes) and [DISTRIBUTED.md](docs/DISTRIBUTED.md).
+**Several GPUs and nodes.** Use `devices=[0, 1, 2, 3]` in one process, or one process per GPU with torchrun for one or more nodes. See [REFERENCE](https://github.com/sypsyp97/diffct/blob/main/docs/REFERENCE.md#several-gpus-and-nodes) and [DISTRIBUTED.md](https://github.com/sypsyp97/diffct/blob/main/docs/DISTRIBUTED.md).
 
 ```python
 A = Projector(trajectory, (128, 128, 128), (384, 256), detector_spacing=0.8, devices=[0, 1, 2, 3])
@@ -144,8 +148,8 @@ A = Projector(trajectory, (128, 128, 128), (384, 256), detector_spacing=0.8, dev
 
 <p align="center">
   <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/assets/scaling_dark.png">
-    <img src="docs/assets/scaling_light.png" width="100%" alt="Time per forward, adjoint and CGLS iteration on 1, 4 and 8 GPUs, 64^3 and 128^3">
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/scaling_dark.png">
+    <img src="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/scaling_light.png" width="100%" alt="Time per forward, adjoint and CGLS iteration on 1, 4 and 8 GPUs, 64^3 and 128^3">
   </picture>
 </p>
 
@@ -155,7 +159,7 @@ A = Projector(trajectory, (128, 128, 128), (384, 256), detector_spacing=0.8, dev
 | Adjoint (backprojection) | 20.66 ms | 5.89 ms (3.5×) | 4.62 ms (4.5×) |
 | CGLS iteration | 30.08 ms | 8.08 ms (3.7×) | 5.59 ms (5.4×) |
 
-Circular trajectory, 360 views, detector (2n, 1.5n) cells at pitch 1.25, A100 64 GB on Leonardo Booster. Small volumes scale less: at 64³, one CGLS iteration takes 4.63 ms on 1 GPU, 1.57 ms on 4 and 1.56 ms on 8. Raw data: [docs/assets/scaling.json](docs/assets/scaling.json).
+Circular trajectory, 360 views, detector (2n, 1.5n) cells at pitch 1.25, A100 64 GB GPUs. Small volumes scale less: at 64³, one CGLS iteration takes 4.63 ms on 1 GPU, 1.57 ms on 4 and 1.56 ms on 8. Raw data: [docs/assets/scaling.json](https://github.com/sypsyp97/diffct/blob/main/docs/assets/scaling.json).
 
 To measure one against several GPUs on your machine (default scan of the script, not the table setup):
 
@@ -168,7 +172,7 @@ python examples/benchmark_projector.py --devices 0 1
 **Measured walnut.** 240 measured views, circular cone beam, 256³: FDK (Hann window), SIRT (200 iterations), CGLS (20), TV (300, weight 0.3); axial and coronal centre slices.
 
 <p align="center">
-  <img src="docs/assets/walnut_measured.png" width="100%" alt="Measured walnut: FDK, SIRT, CGLS and TV reconstructions">
+  <img src="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/walnut_measured.png" width="100%" alt="Measured walnut: FDK, SIRT, CGLS and TV reconstructions">
 </p>
 
 ```bash
@@ -178,7 +182,7 @@ python examples/walnut_reconstruction.py --figure out.png
 **Simulated helical scan of the walnut.** The FDK walnut volume as ground truth, 720 views, 1% noise, 256³. PSNR: FDK 26.67 dB, CGLS (30 iterations) 34.13 dB, SIRT (200) 34.52 dB, TV (200, weight 1.0) 37.77 dB.
 
 <p align="center">
-  <img src="docs/assets/walnut_helical.png" width="100%" alt="Simulated helical scan of the walnut: FDK, CGLS, SIRT and TV reconstructions">
+  <img src="https://raw.githubusercontent.com/sypsyp97/diffct/main/docs/assets/walnut_helical.png" width="100%" alt="Simulated helical scan of the walnut: FDK, CGLS, SIRT and TV reconstructions">
 </p>
 
 ```bash
@@ -186,23 +190,22 @@ python examples/walnut_reconstruction.py --algorithms --save-volume walnut256.np
 python examples/iterative_reconstruction.py --size 256 --views 720 --trajectory helical --noise 0.01 --phantom walnut256.npy --figure out.png
 ```
 
-Walnut data: Meaney 2022, Zenodo 6986012, CC BY 4.0; see [examples/data/NOTICE](examples/data/NOTICE).
+Walnut data: Meaney 2022, Zenodo 6986012, CC BY 4.0; see [examples/data/NOTICE](https://github.com/sypsyp97/diffct/blob/main/examples/data/NOTICE).
 
 ## Examples
 
-`quickstart.py`, `analytical_reconstruction.py`, `iterative_reconstruction.py`, `walnut_reconstruction.py`, `geometry_calibration.py`, `benchmark_projector.py`, `plot_trajectory.py`, and the Slurm template `slurm/multi_node.sbatch`. Launch modes, distributed-loss rules and measured results are in [examples/README.md](examples/README.md).
+`quickstart.py`, `analytical_reconstruction.py`, `iterative_reconstruction.py`, `walnut_reconstruction.py`, `geometry_calibration.py`, `benchmark_projector.py`, `plot_trajectory.py`, and the Slurm template `slurm/multi_node.sbatch`. Launch modes and distributed-loss rules are in [examples/README.md](https://github.com/sypsyp97/diffct/blob/main/examples/README.md).
 
 ## Documentation
 
 | Document | Contents |
 |---|---|
-| [Trajectory guide](docs/source/trajectories.rst) | Trajectory tuples and `Projector` usage |
-| [docs/REFERENCE.md](docs/REFERENCE.md) | Capabilities and limits, custom trajectories, geometry gradients, multi-GPU details, geometry and units |
-| [docs/DISTRIBUTED.md](docs/DISTRIBUTED.md) | Execution/memory choices, distributed loss rules, Slurm and cross-node checks |
-| [docs/VALIDATION.md](docs/VALIDATION.md) | Test commands, validation details and the limits of each check |
-| [docs/MIGRATION.md](docs/MIGRATION.md) | Moving from the circular-only API |
-| [docs/video/README.md](docs/video/README.md) | How the intro video is rendered |
-| [CHANGELOG.md](CHANGELOG.md) | Release history |
+| [Trajectory guide](https://github.com/sypsyp97/diffct/blob/main/docs/source/trajectories.rst) | Trajectory tuples and `Projector` usage |
+| [docs/REFERENCE.md](https://github.com/sypsyp97/diffct/blob/main/docs/REFERENCE.md) | Capabilities and limits, custom trajectories, geometry gradients, multi-GPU details, geometry and units |
+| [docs/DISTRIBUTED.md](https://github.com/sypsyp97/diffct/blob/main/docs/DISTRIBUTED.md) | Execution/memory choices, distributed loss rules, Slurm and cross-node checks |
+| [docs/MIGRATION.md](https://github.com/sypsyp97/diffct/blob/main/docs/MIGRATION.md) | Moving from the circular-only API |
+| [docs/video/README.md](https://github.com/sypsyp97/diffct/blob/main/docs/video/README.md) | How the intro video is rendered |
+| [CHANGELOG.md](https://github.com/sypsyp97/diffct/blob/main/CHANGELOG.md) | Release history |
 
 Run the test suite on a CUDA host with `python -m pytest tests/ -q`.
 
@@ -234,7 +237,7 @@ If you use this library in your research, please cite the software and the techn
 
 ## License and acknowledgements
 
-Apache 2.0, see [LICENSE](LICENSE). The project draws on
+Apache 2.0, see [LICENSE](https://github.com/sypsyp97/diffct/blob/main/LICENSE). The project draws on
 [PYRO-NN](https://github.com/csyben/PYRO-NN) and
 [geometry_gradients_CT](https://github.com/mareikethies/geometry_gradients_CT).
-Issues and pull requests are welcome. The walnut data are CC BY 4.0 (Meaney 2022); see [NOTICE](NOTICE).
+Issues and pull requests are welcome. The walnut data are CC BY 4.0 (Meaney 2022); see [NOTICE](https://github.com/sypsyp97/diffct/blob/main/NOTICE).

diffct-2.0.2.dist-info/RECORD

@@ -0,0 +1,18 @@
+diffct/__init__.py,sha256=pt0oFJ4ntPNI3sDcV-2chCYoySpJ9lpCXHoYT7c0cDY,2191
+diffct/analytical.py,sha256=cDJFMJOYzSaHLr9TUkiKtu5R6TR2d9b7GPZnCI48-VY,25206
+diffct/constants.py,sha256=IKC_0u9aoNCG4M13KcRrl2plO0dTiokac-2aCYJJMb4,3060
+diffct/differentiable.py,sha256=cFirhqXRpUemL7y7Sl_0uqZKGJNj__ptQEcTwYNKzys,1879
+diffct/geometry.py,sha256=ZFXqrn2b1kmwzlXqDFGHPVOhHkuAsjRuFbUF8slnOYQ,38154
+diffct/operators.py,sha256=UK3AoUSpt1n910QybmEt2MxoawNBkv4CHqyszRrQAGc,24922
+diffct/projectors.py,sha256=C7Jp4IGuAtGkJQ6Z7ywpUpCsyptC6z1LRa9MSQrWU-E,41273
+diffct/utils.py,sha256=wBAVsXBaBqNhyk4G0Q7qdCa-KQOOjZAd-ojvImJaK58,14496
+diffct/kernels/__init__.py,sha256=PhdgiZEyPzdnJ6tVmX6zzUvQH4EESwW8rfC_jCTlzhU,1106
+diffct/kernels/cone_beam.py,sha256=TBtjX51f-WkaFqm6umQfr6zm2JQGjFIDsgs-skMj090,24620
+diffct/kernels/fan_beam.py,sha256=5rRdIiqYL7ghJkk-MGlW5kfcznUlZhoOA-NKZtFhPJ4,16498
+diffct/kernels/geometry_vjp.py,sha256=K8pKSqqw86ejvDkv-VLnv_qvxfWzs9IentSr6SROYe4,19102
+diffct/kernels/parallel_beam.py,sha256=k6lOCAPvY1F9P9E2d-dYPx55328-66OKQ-MhPuP7hmw,16517
+diffct-2.0.2.dist-info/METADATA,sha256=viWNaRkii8-GcApKeTdj1vAjUvN9tBrP66VsXVkboWs,13315
+diffct-2.0.2.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+diffct-2.0.2.dist-info/licenses/LICENSE,sha256=a1fjzGs44LpDnV_LmA2Tzp8z-eJKoNVVdLOnh-F6J6E,11344
+diffct-2.0.2.dist-info/licenses/NOTICE,sha256=du9I2sDF5IDfiY9vF64WWzMJh-MarpVXyLfWQmhbvmI,714
+diffct-2.0.2.dist-info/RECORD,,

diffct-2.0.0.dist-info/RECORD

@@ -1,18 +0,0 @@
-diffct/__init__.py,sha256=dvV3ttkCyMsaINHz1oBB-I_e9OLM6LYOR0RpG1tVlDo,2191
-diffct/analytical.py,sha256=lNY3lzzauxo6XbCYdwZ5mY7zqFXKlVAt1vxoHPpCdEE,25106
-diffct/constants.py,sha256=IKC_0u9aoNCG4M13KcRrl2plO0dTiokac-2aCYJJMb4,3060
-diffct/differentiable.py,sha256=cFirhqXRpUemL7y7Sl_0uqZKGJNj__ptQEcTwYNKzys,1879
-diffct/geometry.py,sha256=uN6J5fO4I4_dF3ecGP5IUaQIB7_odPocbr2_AKd3r5U,37576
-diffct/operators.py,sha256=BfBkZpAXhWoCxOPgPF0VfNp1atenNYDTphM5Q6Xy2ns,24602
-diffct/projectors.py,sha256=9-kLHYJFeohz-fhKZiYFyRNY7vOKnRplazpnNfIhckc,41108
-diffct/utils.py,sha256=bfrmO_HlHmDkUQQQ0yf_fk-OSidSKRBpYUMNAnYxW_Q,11988
-diffct/kernels/__init__.py,sha256=PhdgiZEyPzdnJ6tVmX6zzUvQH4EESwW8rfC_jCTlzhU,1106
-diffct/kernels/cone_beam.py,sha256=TBtjX51f-WkaFqm6umQfr6zm2JQGjFIDsgs-skMj090,24620
-diffct/kernels/fan_beam.py,sha256=5rRdIiqYL7ghJkk-MGlW5kfcznUlZhoOA-NKZtFhPJ4,16498
-diffct/kernels/geometry_vjp.py,sha256=K8pKSqqw86ejvDkv-VLnv_qvxfWzs9IentSr6SROYe4,19102
-diffct/kernels/parallel_beam.py,sha256=k6lOCAPvY1F9P9E2d-dYPx55328-66OKQ-MhPuP7hmw,16517
-diffct-2.0.0.dist-info/METADATA,sha256=wj5VNajRfnkDnnJ2LvXyiMyBLblY2VvwZW2SPLvLBMk,12096
-diffct-2.0.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-diffct-2.0.0.dist-info/licenses/LICENSE,sha256=a1fjzGs44LpDnV_LmA2Tzp8z-eJKoNVVdLOnh-F6J6E,11344
-diffct-2.0.0.dist-info/licenses/NOTICE,sha256=du9I2sDF5IDfiY9vF64WWzMJh-MarpVXyLfWQmhbvmI,714
-diffct-2.0.0.dist-info/RECORD,,