braindecode 1.4.0.dev172002252__tar.gz → 1.5.0.dev964__tar.gz

{braindecode-1.4.0.dev172002252/braindecode.egg-info → braindecode-1.5.0.dev964}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.4.0.dev172002252
+Version: 1.5.0.dev964
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.4.0.dev172002252 → braindecode-1.5.0.dev964}/braindecode/datasets/base.py

@@ -298,34 +298,95 @@ def _build_windowed_repr(
 
 
 def _zarr_to_memmap(zarr_path, group_name):
-    """Decompress a zarr array to a float64 ``.npy`` memmap (one-time, atomic).
-
-    Saved as float64 so MNE objects can wrap the memmap zero-copy
-    (MNE requires float64 internally).  Copy-on-write mode (``'c'``)
-    means preprocessing writes go to RAM, the file stays untouched.
+    """Materialise a zarr array as a float64 ``.npy`` memmap, race-free.
+
+    Decompress the ``group_name`` array inside ``zarr_path`` into a
+    float64 ``.npy`` file inside a sibling ``.<zarr>_memmap/`` cache
+    directory and return the path to that file.  The dtype is float64
+    because MNE objects wrap the memmap zero-copy and MNE requires
+    float64 internally.  Callers open the result with
+    ``np.load(path, mmap_mode='c')`` so preprocessing writes land in
+    anonymous copy-on-write pages and never mutate the on-disk file.
+
+    Concurrency contract
+    --------------------
+    Safe to call from any number of threads or processes concurrently
+    on the same ``(zarr_path, group_name)``, on local POSIX, NFSv3,
+    Lustre and SMB.  The published ``.npy`` file is **created exactly
+    once and never replaced**: subsequent callers either hit the
+    already-materialised file on the fast path or lose the
+    publication race and discard their own copy.
+
+    The atomic publication step is ``os.link``, not ``rename``.
+    ``os.link(tmp, dst)`` either creates ``dst`` pointing at ``tmp``'s
+    inode or fails with :class:`FileExistsError` when ``dst`` already
+    exists — the "create only if absent" primitive we need, available
+    on every POSIX filesystem.  ``rename`` was the wrong primitive:
+    it atomically *replaces* its destination, which unlinks the inode
+    that concurrent readers may already have ``mmap``'d.  On NFSv3
+    that produced ``.nfsXXXX`` silly-rename files and intermittent
+    ``SIGBUS`` when workers page-faulted on the unlinked inode.
+
+    Under ``N`` concurrent writers, every racer materialises the data
+    into its own per-pid temp file and then tries to publish it; at
+    most one ``os.link`` wins, and the losers silently ``unlink``
+    their temp file in a ``finally`` block.  The wasted I/O scales
+    with the number of racers; for the workloads braindecode targets
+    (a handful of concurrent workers per group) it is negligible.
+
+    Crash recovery: if a writer dies mid-run the only debris is a
+    ``<group>.<pid>.tmp.npy`` file.  Such files are namespaced by pid
+    so they can never collide with a live writer, they are never
+    read by the fast path, and they do not prevent subsequent
+    callers from producing a correct result.  Caches written by
+    earlier braindecode versions remain valid: the fast path only
+    requires ``<group>.npy`` to exist.
     """
     zarr_p = Path(zarr_path)
     cache_dir = zarr_p.parent / f".{zarr_p.name}_memmap"
     npy_path = cache_dir / f"{group_name}.npy"
 
-    if not npy_path.exists():
-        arr = zarr.open(zarr_path, mode="r")[group_name]["data"]
-        cache_dir.mkdir(parents=True, exist_ok=True)
-        tmp_path = cache_dir / f"{group_name}.{os.getpid()}.tmp.npy"
-        # Write chunk-by-chunk to avoid materializing the full array in RAM
+    # Fast path: the file is already fully materialised.  A single
+    # stat() is all the steady-state workload pays.
+    if npy_path.exists():
+        return npy_path
+
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    arr = zarr.open(zarr_path, mode="r")[group_name]["data"]
+    tmp_path = cache_dir / f"{group_name}.{os.getpid()}.tmp.npy"
+    try:
+        # Write chunk-by-chunk to avoid materialising the whole zarr
+        # array in RAM.
         mm = np.lib.format.open_memmap(
             tmp_path, mode="w+", dtype=np.float64, shape=arr.shape
         )
-        chunk0 = arr.chunks[0] if hasattr(arr, "chunks") else arr.shape[0]
-        for start in range(0, arr.shape[0], chunk0):
-            end = min(start + chunk0, arr.shape[0])
-            mm[start:end] = np.asarray(arr[start:end], dtype=np.float64)
-        mm.flush()
-        del mm
         try:
-            tmp_path.rename(npy_path)
-        except OSError:
-            tmp_path.unlink(missing_ok=True)
+            chunk0 = arr.chunks[0] if hasattr(arr, "chunks") else arr.shape[0]
+            for start in range(0, arr.shape[0], chunk0):
+                end = min(start + chunk0, arr.shape[0])
+                mm[start:end] = np.asarray(arr[start:end], dtype=np.float64)
+            mm.flush()
+        finally:
+            del mm
+
+        # Atomic publication.  ``os.link`` never replaces an existing
+        # destination, so the published inode is immutable for the
+        # lifetime of the cache directory.  Concurrent readers never
+        # see their mmap'd inode vanish from under them.
+        try:
+            os.link(tmp_path, npy_path)
+        except FileExistsError:
+            # Another writer beat us to it.  Their file is the
+            # canonical one; ours is discarded in the finally block.
+            pass
+    finally:
+        # Always remove our private per-pid temp file.  It is
+        # namespaced by pid so this cannot clobber a concurrent
+        # writer's in-progress tmp file.
+        try:
+            os.unlink(tmp_path)
+        except FileNotFoundError:
+            pass
 
     return npy_path
 

{braindecode-1.4.0.dev172002252 → braindecode-1.5.0.dev964}/braindecode/models/__init__.py

@@ -8,6 +8,7 @@ from .bendr import BENDR
 from .biot import BIOT
 from .brainmodule import BrainModule
 from .cbramod import CBraMod
+from .codebrain import CodeBrain
 from .contrawr import ContraWR
 from .ctnet import CTNet
 from .deep4 import Deep4Net
@@ -72,6 +73,7 @@ __all__ = [
     "BIOT",
     "BENDR",
     "CBraMod",
+    "CodeBrain",
     "ContraWR",
     "CTNet",
     "Deep4Net",

{braindecode-1.4.0.dev172002252 → braindecode-1.5.0.dev964}/braindecode/models/attentionbasenet.py

@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+# Authors: Sarthak Tayal <sarthaktayal2@gmail.com>
+#
+# License: BSD (3-clause)
 import math
 
 from einops.layers.torch import Rearrange
@@ -275,8 +278,6 @@ class AttentionBaseNet(EEGModuleMixin, nn.Module):
         activation: type[nn.Module] = nn.ELU,
         extra_params: bool = False,
     ):
-        super(AttentionBaseNet, self).__init__()
-
         super().__init__(
             n_outputs=n_outputs,
             n_chans=n_chans,

{braindecode-1.4.0.dev172002252 → braindecode-1.5.0.dev964}/braindecode/models/biot.py

@@ -439,7 +439,7 @@ class _BIOTEncoder(nn.Module):
         self.channel_tokens = nn.Embedding(
             num_embeddings=n_chans, embedding_dim=emb_size
         )
-        self.index = nn.Parameter(torch.LongTensor(range(n_chans)), requires_grad=False)
+        self.register_buffer("index", torch.arange(n_chans, dtype=torch.long))
 
     def stft(self, sample):
         """