tensorcodec 0.1.3__tar.gz → 0.1.5__tar.gz

tensorcodec-0.1.5/LICENSE

@@ -0,0 +1,204 @@
+Copyright (c) 2026 Suhwan Choi
+
+
+                                 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.

{tensorcodec-0.1.3 → tensorcodec-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tensorcodec
-Version: 0.1.3
+Version: 0.1.5
 Classifier: Development Status :: 3 - Alpha
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Operating System :: MacOS :: MacOS X
@@ -15,9 +15,10 @@ License-File: licenses/FFmpeg-NOTICE.md
 License-File: licenses/OpenSSL.txt
 License-File: licenses/README.md
 License-File: licenses/Zstandard.txt
+License-File: licenses/dav1d.txt
 Summary: NumPy audio/video decoding with TorchCodec-compatible playback semantics
 Author-email: Suhwan Choi <milkclouds00@gmail.com>
-License-Expression: MIT
+License-Expression: Apache-2.0
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
 Project-URL: Issues, https://github.com/MilkClouds/tensorcodec/issues
@@ -34,9 +35,9 @@ CPU video/audio decoding with TorchCodec-style APIs and NumPy output.
 <a href="https://pypi.org/project/tensorcodec/"><img src="https://img.shields.io/pypi/v/tensorcodec" alt="PyPI"></a>
 <a href="https://pypi.org/project/tensorcodec/"><img src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="Python"></a>
 <!-- wheel-size-badge:start -->
-<a href="#package-size"><img src="https://img.shields.io/badge/wheel-10.4%20MiB-blue" alt="Wheel download"></a>
+<a href="#package-size"><img src="https://img.shields.io/badge/wheel-10.5%20MiB-blue" alt="Wheel download"></a>
 <!-- wheel-size-badge:end -->
-<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue" alt="License: MIT"></a>
+<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-blue" alt="License: Apache-2.0"></a>
 </p>
 
 [Quick start](#quick-start) · [Features](#features) · [Package size](#package-size) · [Compatibility](docs/compatibility.md)
@@ -48,8 +49,9 @@ CPU video/audio decoding with TorchCodec-style APIs and NumPy output.
 - **Validated playback semantics.** Frame selection, ordering, timestamps and audio
   ranges are checked against TorchCodec 0.17.0 and independently generated media.
 - **Efficient batch decoding.** Rust/PyO3 bindings to FFmpeg process frame batches
-  in a single native call, avoiding per-frame Python calls.
-- **Lightweight installation.** Linux wheels are 10.2–10.4 MiB (v0.1.2), including
+  in a single native call, avoiding per-frame Python calls. Closing a decoder
+  releases its FFmpeg resources without waiting for Python's cyclic GC.
+- **Lightweight installation.** Linux wheels are 10.3–10.5 MiB (v0.1.4), including
   FFmpeg shared libraries. NumPy is the only Python dependency.
 
 ## Quick start
@@ -77,9 +79,29 @@ with AudioDecoder("audio.wav", sample_rate=16000, num_channels=1) as audio:
 Arrays keep their storage after the decoder closes. Paths, URLs, encoded bytes,
 1-D uint8 arrays and seekable file objects are supported.
 
+For time-based windows without an initial full packet scan (since v0.1.4):
+
+```python
+with VideoDecoder("video.mkv", seek_mode="timestamp") as decoder:
+    frames = decoder.get_frames_played_at([10.0, 10.1, 10.2])
+```
+
+Decoder transforms (since v0.1.5) resize and crop inside the decoder, as TorchCodec's do:
+
+```python
+from tensorcodec.transforms import CenterCrop, Resize
+
+with VideoDecoder("video.mp4", transforms=[Resize((256, 340)), CenterCrop((224, 224))]) as decoder:
+    frames = decoder.get_frames_at([0, 10])  # (2, 3, 224, 224)
+```
+
+This TensorCodec extension selects by actual PTS and retries seeks that overshoot.
+It supports time queries, including ranges with explicit `fps`, but not frame
+indices, `len(decoder)`, or `get_all_frames()`. See [the contract](docs/compatibility.md#timestamp-mode).
+
 ## Features
 
-TensorCodec 0.1.3 relative to TorchCodec 0.17.0.
+TensorCodec 0.1.5 relative to TorchCodec 0.17.0.
 ✓ supported · △ partial support · — not implemented.
 
 | Component | TensorCodec | TorchCodec 0.17.0 |
@@ -89,7 +111,7 @@ TensorCodec 0.1.3 relative to TorchCodec 0.17.0.
 | Image decoders | — | ✓ |
 | Video / audio / image encoders | — | ✓ |
 | Clip samplers | — | ✓ |
-| Decoder transforms | — | ✓ |
+| Decoder transforms | ✓ Resize, CenterCrop, RandomCrop | ✓ |
 
 FPS-based frame queries are supported; clip samplers are a separate API.
 
@@ -132,7 +154,7 @@ Linux CPU wheels, Python 3.12. Download / unpacked size in MiB.
 
 | Package | x86_64 | ARM64 |
 | --- | ---: | ---: |
-| TensorCodec | 10.2 / 24.7 | 10.4 / 22.9 |
+| TensorCodec | 10.3 / 24.8 | 10.5 / 23.0 |
 | PyAV | 33.4 / 125.5 | 31.2 / 90.4 |
 | TorchCodec + PyTorch (CPU) | 196.7 / 704.7 | 160.3 / 585.7 |
 <!-- wheel-size:end -->
@@ -201,5 +223,6 @@ Tests generate media with FFmpeg/ffprobe and Python's `wave` module.
 
 </details>
 
-TensorCodec's own code is [MIT licensed](LICENSE).
+TensorCodec's own code is licensed under [Apache-2.0](LICENSE).
+Versions through v0.1.4 were released under MIT.
 

{tensorcodec-0.1.3 → tensorcodec-0.1.5}/README.md

@@ -9,9 +9,9 @@ CPU video/audio decoding with TorchCodec-style APIs and NumPy output.
 <a href="https://pypi.org/project/tensorcodec/"><img src="https://img.shields.io/pypi/v/tensorcodec" alt="PyPI"></a>
 <a href="https://pypi.org/project/tensorcodec/"><img src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="Python"></a>
 <!-- wheel-size-badge:start -->
-<a href="#package-size"><img src="https://img.shields.io/badge/wheel-10.4%20MiB-blue" alt="Wheel download"></a>
+<a href="#package-size"><img src="https://img.shields.io/badge/wheel-10.5%20MiB-blue" alt="Wheel download"></a>
 <!-- wheel-size-badge:end -->
-<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue" alt="License: MIT"></a>
+<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-blue" alt="License: Apache-2.0"></a>
 </p>
 
 [Quick start](#quick-start) · [Features](#features) · [Package size](#package-size) · [Compatibility](docs/compatibility.md)
@@ -23,8 +23,9 @@ CPU video/audio decoding with TorchCodec-style APIs and NumPy output.
 - **Validated playback semantics.** Frame selection, ordering, timestamps and audio
   ranges are checked against TorchCodec 0.17.0 and independently generated media.
 - **Efficient batch decoding.** Rust/PyO3 bindings to FFmpeg process frame batches
-  in a single native call, avoiding per-frame Python calls.
-- **Lightweight installation.** Linux wheels are 10.2–10.4 MiB (v0.1.2), including
+  in a single native call, avoiding per-frame Python calls. Closing a decoder
+  releases its FFmpeg resources without waiting for Python's cyclic GC.
+- **Lightweight installation.** Linux wheels are 10.3–10.5 MiB (v0.1.4), including
   FFmpeg shared libraries. NumPy is the only Python dependency.
 
 ## Quick start
@@ -52,9 +53,29 @@ with AudioDecoder("audio.wav", sample_rate=16000, num_channels=1) as audio:
 Arrays keep their storage after the decoder closes. Paths, URLs, encoded bytes,
 1-D uint8 arrays and seekable file objects are supported.
 
+For time-based windows without an initial full packet scan (since v0.1.4):
+
+```python
+with VideoDecoder("video.mkv", seek_mode="timestamp") as decoder:
+    frames = decoder.get_frames_played_at([10.0, 10.1, 10.2])
+```
+
+Decoder transforms (since v0.1.5) resize and crop inside the decoder, as TorchCodec's do:
+
+```python
+from tensorcodec.transforms import CenterCrop, Resize
+
+with VideoDecoder("video.mp4", transforms=[Resize((256, 340)), CenterCrop((224, 224))]) as decoder:
+    frames = decoder.get_frames_at([0, 10])  # (2, 3, 224, 224)
+```
+
+This TensorCodec extension selects by actual PTS and retries seeks that overshoot.
+It supports time queries, including ranges with explicit `fps`, but not frame
+indices, `len(decoder)`, or `get_all_frames()`. See [the contract](docs/compatibility.md#timestamp-mode).
+
 ## Features
 
-TensorCodec 0.1.3 relative to TorchCodec 0.17.0.
+TensorCodec 0.1.5 relative to TorchCodec 0.17.0.
 ✓ supported · △ partial support · — not implemented.
 
 | Component | TensorCodec | TorchCodec 0.17.0 |
@@ -64,7 +85,7 @@ TensorCodec 0.1.3 relative to TorchCodec 0.17.0.
 | Image decoders | — | ✓ |
 | Video / audio / image encoders | — | ✓ |
 | Clip samplers | — | ✓ |
-| Decoder transforms | — | ✓ |
+| Decoder transforms | ✓ Resize, CenterCrop, RandomCrop | ✓ |
 
 FPS-based frame queries are supported; clip samplers are a separate API.
 
@@ -107,7 +128,7 @@ Linux CPU wheels, Python 3.12. Download / unpacked size in MiB.
 
 | Package | x86_64 | ARM64 |
 | --- | ---: | ---: |
-| TensorCodec | 10.2 / 24.7 | 10.4 / 22.9 |
+| TensorCodec | 10.3 / 24.8 | 10.5 / 23.0 |
 | PyAV | 33.4 / 125.5 | 31.2 / 90.4 |
 | TorchCodec + PyTorch (CPU) | 196.7 / 704.7 | 160.3 / 585.7 |
 <!-- wheel-size:end -->
@@ -176,4 +197,5 @@ Tests generate media with FFmpeg/ffprobe and Python's `wave` module.
 
 </details>
 
-TensorCodec's own code is [MIT licensed](LICENSE).
+TensorCodec's own code is licensed under [Apache-2.0](LICENSE).
+Versions through v0.1.4 were released under MIT.

tensorcodec-0.1.5/benchmarks/README.md

@@ -0,0 +1,99 @@
+# TensorCodec benchmarks
+
+These tools measure the current TensorCodec implementation and optional comparison
+backends. Performance depends on the input, seek mode, thread count, storage and
+cache state. Measure your workload before choosing a decoder.
+
+## Setup
+
+Use the [development environment](../README.md#development-and-verification).
+TensorCodec-only runs need NumPy and TensorCodec; TorchCodec comparisons also need
+the pinned oracle group. FFmpeg CLI with the requested encoders is required to
+generate fixtures. Run from the repository root.
+
+```sh
+uv run --no-sync python -m benchmarks --list-decoders
+uv run --no-sync python -m benchmarks --prepare --num-videos 4 --video-duration 10
+uv run --no-sync python -m benchmarks --no-io --decoders tensorcodec \
+  --runs 3 --output json --save benchmarks/results/speed.json
+```
+
+For a CPU comparison, explicitly select the same thread count and seek mode:
+
+```sh
+uv run --no-sync python -m benchmarks --no-io \
+  --decoders tensorcodec 'torchcodec(seek=exact,thr=1)' \
+  --runs 3 --output json --save benchmarks/results/speed.json
+```
+
+## Measurements
+
+| Scenario | Workload | Included costs |
+| --- | --- | --- |
+| `temporal_window` | Random playback queries, 11 samples over a 1-second window | Decoder open, exact-mode packet scan, seeking, decoding, NumPy output |
+| `sequential_range` | Decode the full video range | Decoder open, range selection, decoding, NumPy output |
+
+The TensorCodec adapter opens and closes a decoder for each request. Results do
+not represent a persistent decoder cache such as MediaRef's. Compare exact and
+approximate modes separately: approximate mode does not guarantee exact VFR frame
+selection. GPU comparison adapters include transfer back to CPU NumPy arrays.
+
+For codec/container throughput experiments:
+
+```sh
+uv run --no-sync python -m benchmarks.container_bench --help
+uv run --no-sync python -m benchmarks.container_bench
+```
+
+This tool generates fresh inputs with FFmpeg. Its codec matrix measures speed;
+it does not assert pixel or timestamp correctness. See
+[container and seek behavior](../docs/container_robustness.md) for tested guarantees.
+
+## Optional I/O and plotting
+
+To separate opening from an 11-frame playback window, counting bytes returned by
+file reads (including rereads, **not** physical disk or network traffic):
+
+```sh
+ffprobe -v error -select_streams v:0 -show_frames \
+  -show_entries frame=pts,duration,key_frame -of json video.mp4 > frames.json
+uv run --no-sync python -m benchmarks.open_cost video.mp4 --start 10 \
+  --backends tensorcodec torchcodec --mappings frames.json
+```
+
+Both libraries scan packets to EOF on each fresh default `exact` open. Precomputed
+`custom_frame_mappings` skip that scan while preserving exact selection; header
+probing and window reads remain. Generate mappings once for the **same encoded
+stream**, outside training. PTS alone is insufficient: durations and keyframe flags
+are also required, in the stream's integer time base. The tool checks mapped
+window pixels/PTS/durations against exact, and rotates mode order between trials;
+it does not control OS caches. `approximate` is measured separately without an
+accuracy guarantee. Container seek indexes are not generally complete frame maps
+(e.g. MKV Cues); they cannot universally replace an exact scan.
+
+FUSE measurements require Linux FUSE access, `pyfuse3` and `trio`. Install these
+only in the benchmark environment, then omit `--no-io`. The runner can fall back
+to speed-only results when FUSE is unavailable; check that `io_bytes` is populated
+before reporting I/O figures. FUSE timing includes its own filesystem overhead.
+
+```sh
+uv run --no-sync python -m benchmarks --decoders tensorcodec \
+  'torchcodec(seek=exact,thr=1)' --scenarios temporal_window \
+  --runs 3 --output json --save benchmarks/results/io.json
+```
+
+Install `matplotlib` in the benchmark environment to plot measurements:
+
+```sh
+uv run --no-sync python -m benchmarks.plot_results \
+  --speed benchmarks/results/speed.json --io benchmarks/results/io.json
+```
+
+## Reporting results
+
+Generated JSON and charts stay in `benchmarks/results/`, which is gitignored.
+Publish results only with the TensorCodec/TorchCodec/FFmpeg/NumPy versions,
+hardware, corpus, seek/thread settings, cache conditions and commands. Identify
+timeouts as partial results. Check frame selection and pixel agreement separately
+using the [compatibility contract](../docs/compatibility.md); throughput alone is
+not a correctness check.

tensorcodec-0.1.5/benchmarks/__init__.py

@@ -0,0 +1 @@
+"""tensorcodec benchmark suite — FPS and disk I/O measurement for video decoders."""

tensorcodec-0.1.5/benchmarks/__main__.py

@@ -0,0 +1,5 @@
+"""Allow ``python -m benchmarks`` to launch the runner."""
+
+from benchmarks.runner import main
+
+main()

tensorcodec-0.1.5/benchmarks/container_bench.py

@@ -0,0 +1,157 @@
+"""Container & codec robustness benchmark.
+
+Generates synthetic videos in various codec × container combinations and
+measures random-seek performance for tensorcodec and (optionally) TorchCodec.
+
+Usage::
+
+    uv run --no-sync python -m benchmarks.container_bench
+    uv run --no-sync python -m benchmarks.container_bench --duration 60 --queries 200
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+import random
+import subprocess
+import tempfile
+import time
+
+import numpy as np
+
+# ---------------------------------------------------------------------------
+# Video generation
+# ---------------------------------------------------------------------------
+
+COMBOS: list[tuple[str, str, str, str, dict]] = [
+    # (codec_label, extension, av_codec, pix_fmt, encoder_opts)
+    ("h264", "mp4", "libx264", "yuv420p", {"g": "10"}),
+    ("h264", "mkv", "libx264", "yuv420p", {"g": "10"}),
+    ("h264", "avi", "libx264", "yuv420p", {"g": "10"}),
+    ("h264", "ts", "libx264", "yuv420p", {"g": "10"}),
+    ("h265", "mp4", "libx265", "yuv420p", {"g": "10", "x265-params": "log-level=error"}),
+    ("h265", "mkv", "libx265", "yuv420p", {"g": "10", "x265-params": "log-level=error"}),
+    ("h265", "ts", "libx265", "yuv420p", {"g": "10", "x265-params": "log-level=error"}),
+    ("vp9", "mkv", "libvpx-vp9", "yuv420p", {"g": "10", "quality": "realtime", "speed": "8"}),
+    ("vp9", "webm", "libvpx-vp9", "yuv420p", {"g": "10", "quality": "realtime", "speed": "8"}),
+    ("mpeg4", "mp4", "mpeg4", "yuv420p", {"g": "10"}),
+    ("mpeg4", "mkv", "mpeg4", "yuv420p", {"g": "10"}),
+    ("mpeg4", "avi", "mpeg4", "yuv420p", {"g": "10"}),
+    ("mjpeg", "mkv", "mjpeg", "yuvj420p", {}),
+    ("mjpeg", "avi", "mjpeg", "yuvj420p", {}),
+]
+
+
+def _create_video(
+    path: str,
+    codec: str,
+    pix_fmt: str = "yuv420p",
+    duration_sec: int = 30,
+    fps: int = 30,
+    opts: dict | None = None,
+) -> None:
+    cmd = [
+        "ffmpeg",
+        "-hide_banner",
+        "-loglevel",
+        "error",
+        "-y",
+        "-f",
+        "lavfi",
+        "-i",
+        f"testsrc2=size=640x480:rate={fps}:duration={duration_sec}",
+        "-c:v",
+        codec,
+        "-pix_fmt",
+        pix_fmt,
+    ]
+    for key, value in (opts or {}).items():
+        cmd.extend([f"-{key}", str(value)])
+    subprocess.run([*cmd, path], capture_output=True, check=True)
+
+
+# ---------------------------------------------------------------------------
+# Benchmark helpers
+# ---------------------------------------------------------------------------
+
+
+def _bench_tensorcodec(path: str, windows: list[list[float]]) -> str:
+    from tensorcodec.decoders import VideoDecoder
+
+    try:
+        with VideoDecoder(path) as d:
+            d.get_frames_played_at([1.0])
+    except (RuntimeError, ValueError, OSError):
+        return "FAIL"
+    t0 = time.perf_counter()
+    total = 0
+    for w in windows:
+        with VideoDecoder(path) as d:
+            total += d.get_frames_played_at(w).data.shape[0]
+    return f"{total / (time.perf_counter() - t0):.0f}"
+
+
+def _bench_torchcodec(path: str, windows: list[list[float]], seek_mode: str) -> str:
+    try:
+        from torchcodec.decoders import VideoDecoder
+    except ImportError:
+        return "N/A"
+    try:
+        VideoDecoder(path, seek_mode=seek_mode, num_ffmpeg_threads=1).get_frames_played_at([1.0])
+    except (RuntimeError, ValueError, OSError):
+        return "FAIL"
+    t0 = time.perf_counter()
+    total = 0
+    for w in windows:
+        dec = VideoDecoder(path, seek_mode=seek_mode, num_ffmpeg_threads=1)
+        total += dec.get_frames_played_at(w).data.shape[0]
+    return f"{total / (time.perf_counter() - t0):.0f}"
+
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Container robustness benchmark")
+    parser.add_argument("--duration", type=int, default=30, help="Video duration in seconds")
+    parser.add_argument("--queries", type=int, default=100, help="Number of random-seek queries")
+    parser.add_argument("--seed", type=int, default=42)
+    args = parser.parse_args()
+
+    random.seed(args.seed)
+    lo = max(2.0, args.duration * 0.1)
+    hi = args.duration - 1.0
+    ts = [random.uniform(lo, hi) for _ in range(args.queries)]
+    windows = [[t + o for o in np.arange(-1.0, 0.05, 0.1).tolist()] for t in ts]
+
+    with tempfile.TemporaryDirectory(prefix="container_bench_") as tmp:
+        hdr = (
+            f"{'codec.container':20s} {'tensorcodec':>10s} {'TC(apx)':>10s} {'TC(ext)':>10s}  {'apx/tensorcodec':>10s}"
+        )
+        print(hdr)
+        print("-" * len(hdr))
+
+        for codec_label, ext, av_codec, pix, opts in COMBOS:
+            path = os.path.join(tmp, f"{codec_label}.{ext}")
+            try:
+                _create_video(path, av_codec, pix, args.duration, opts=opts)
+            except (OSError, subprocess.CalledProcessError) as e:
+                print(f"{codec_label}.{ext:20s} CREATE FAILED: {e}")
+                continue
+
+            r1 = _bench_tensorcodec(path, windows)
+            r2 = _bench_torchcodec(path, windows, "approximate")
+            r3 = _bench_torchcodec(path, windows, "exact")
+            try:
+                ratio = f"{float(r2) / float(r1):.2f}x"
+            except (ValueError, ZeroDivisionError):
+                ratio = "N/A"
+            label = f"{codec_label}.{ext}"
+            print(f"{label:20s} {r1:>10s} {r2:>10s} {r3:>10s}  {ratio:>10s}")
+
+
+if __name__ == "__main__":
+    main()