Commit Graph

163 Commits

Author SHA1 Message Date
Guillaume Lagrange 7baa33bdaa
Fix target convert in batcher and align guide imports (#2215)
* Fix target convert in batcher

* Align hidden code in training and update loss to use config

* Align imports with example

* Remove unused import and fix guide->crate
2024-08-29 08:58:51 -04:00
Guillaume Lagrange 40d321cc0d
Fix tensor data elem type conversion in book (#2211) 2024-08-28 10:55:10 -04:00
syl20bnr a600a7b54e Bump Burn version in the Burn Book 2024-08-27 15:13:40 -04:00
syl20bnr 8e78106680 Bump burn version to 0.15.0 2024-08-27 15:13:40 -04:00
Bjorn Beishline 17de832c6e
Make compatible with thumbv6m-none-eabi + add raspberry pi pico example (#2096)
* Made compatible with thumbv6m-none-eabi

* Added example of no_std on rp2040

* Added documentation on usage in no_std

* Rename rp2040 example and add README.md
2024-08-23 07:39:39 -04:00
Guillaume Lagrange 48a64d3b8a
Add images and csv dataset source to book (#2179) 2024-08-22 15:47:05 -04:00
Guillaume Lagrange 73d4b11aa2
Add a dataset/dataloader/batcher usage section (#2161)
* Add a dataset/dataloader/batcher usage section

* Fix typos
2024-08-22 10:52:56 -05:00
Dilshod Tadjibaev 75a2850047
Add closeness tensor report (#2184)
* Add closeness tensor report

* Add documentation section

* Fix for no-std

* Fix epsilon formatting

* Update report.rs

* Fix import references

* Fix doc test

* Use colored crate instead of passing codes

* Small refactor to use iter directly

* Move colored dep to std

* Add missing

* Fix missing epsilon
2024-08-22 10:19:27 -05:00
Joseph Guhlin 2755c36ed7
Switches epoch and iteration to be in the proper order for the custom training loop (#2171) 2024-08-19 11:37:12 -04:00
Guillaume Lagrange be5eb910d4
Remove CubeCL GELU kernel example reference (moved to CubeCL repo) (#2150) 2024-08-09 15:23:47 -04:00
Dilshod Tadjibaev 1c681f46ec
Precision option for tensor display (#2139) 2024-08-08 15:01:42 -05:00
Guillaume Lagrange 0802d063d8
Fix inner backend typo in book guide (#2135) 2024-08-08 11:23:00 -05:00
Genna Wingert a01004dd4a
Add Hard sigmoid activation function (#2112)
* Add Hard Sigmoid activation function

* Add ONNX import conversion for HardSigmoid

* Update supported operators list

* Update book

* Make test comparison approximate to eliminate precision issues

* Add burn-candle test

* Fix name in E2E test generator
2024-08-07 13:01:42 -05:00
Dilshod Tadjibaev cd848b1c94
Add is_nan and contains_nan tensor ops (#2088)
* Add is_nan and contains_nan tensor ops

* Enable nan test for burn-candle

* Disabling tests due to #2089
2024-08-06 12:16:12 -05:00
Periwink ade664d4d8
Add top-k accuracy (#2097)
* make contacts deterministic across Worlds

* add top k acc

* update book

---------

Co-authored-by: Charles Bournhonesque <cbournhonesque@snapchat.com>
2024-08-06 12:01:28 -05:00
mepatrick73 f7639bd35a
Repeat operation (#2090)
* renaming repeat to repeat_dim

* implementing repeat function

* renaming repeat files to repeat_dim

* renaming part 2

* renaming part 3

* renaming part 4

* renaming part 5

* adding test file

* adding unit test

* adding rust book documentation

* adding function args doc

* fixing tests

* changing repeat api to match pytorch equivalent

* fixing clippy error
2024-08-02 20:33:47 -04:00
Dilshod Tadjibaev bb13729b20
Improve ONNX import book section (#2059)
* Improve ONNX importing section

* Update onnx-model.md
2024-08-01 17:10:18 -05:00
Ragy Abraham 04d7ff24f2
Add polars DataFrame support for Dataset (#2029)
* initial commit to try implement from_dataframes for a burn dataset

* added the beginnings of tests. removed ref to self in utility method

* added unit test for dataframe module. added utility methods to convert polars rows to burn dataset values

* putting polars and dataframe mod behind a fearure flag

* testing both methods

* added a if let OK so that it doesn't panic. if we can't convert serde map to json string. added comments

* using polars serializer, renaming vars

* removed prints. just unwrapping

* setting feature flags back

* return Value::Null rather than panic if we can't serialize list value. no longer convert to object before converting to string. no longer using serde_json to_string method

* Use native deserializer instead of serde_json

* added support for lazyframes. added support to deserialize a few more data. added a few more tests

* Remove lazy, add more testing and other fixes

* Update the book

* Remove lazy feature

* Put back lazy feature for polars

---------

Co-authored-by: Dilshod Tadjibaev <939125+antimora@users.noreply.github.com>
2024-07-31 17:22:49 -05:00
Dilshod Tadjibaev 297173124f
Add 1d and 2d modules for interpolate with scaling (also fix ONNX Resize op) (#2081)
* Add interpolate module

* Update module.md

* Add interpolate 1d and 2d modules

* Consolidated InterpolateMode for 1d and 2d

* Remove CoordinateTransformationMode

* Add 1d tests for interpolate

* Refactor and fixes of ONNX Resize OP

* Fix clippy

* Fix docs

* Fix no_std
2024-07-31 12:08:26 -05:00
Guillaume Lagrange 0d5025edbb
Refactor tensor quantization for q_* ops (#2025)
* Move QuantizationScheme to burn-tensor

* Refactor QuantizedTensorPrimitive to include the quantization strategy

* Fix QFloat tensor data display

* Refactor quantization methods to use scheme and qparams (on backend device)

* Fix clippy

* Fix fmt

* Add qtensor primitive tests
2024-07-19 10:39:50 -04:00
Sylvain Benner 0e77e19635
Remove mention of example in backend section of the book (#2014) 2024-07-15 09:34:40 -04:00
Guillaume Lagrange 3afff434bd
Module weight quantization (#2000)
* Add q_into_data and q_reshape

* Fix tch quantize f16 and q_into_data

* Convert to actual dtype/kind in dequantize

* Add module quantization and q_from_data

* Fix clippy

* Add documentation

* Handle deserialize data conversion

* Fix typo

* Add calibration tests

* Fix clippy precision

* Add QTensorOps require_grad methods to avoid dequantizing

* Add Dequantize mapper docs

* Remove dead code
2024-07-15 08:20:37 -04:00
Guillaume Lagrange c0211e2f94
Add static tensor quantization (#1963)
* Add QuantizationBackend, QTensorOps and QTensor

* Refactor QTensorOps as part of Backend trait

* Add tensor dequantize, QFloat dtype and default affine/symmetric quant

* Add ndarray default quantization implementation

* Fix clippy

* Add rayon parallel iter

* Add quantization operations to book

* Add q_shape and q_device ops to avoid converting the tensor just to get attributes

* Implement autodiff grad ops

* Mark autodiff todo for QAT

* Remove note

* Add q_inner and q_from_inner
2024-07-08 10:16:58 -04:00
Arthur Brussee 3f9e97946f
Feat: Dynamic cube count dispatch (#1975) 2024-07-06 19:17:01 -04:00
nathaniel 882a27c52c Revert "Revert "Implement 3D and transposed 3D convolutions. (#1945)""
This reverts commit b8b47ea6e6.
2024-07-05 18:57:01 -04:00
nathaniel 1ad2a63f28 Fix typo 2024-07-05 09:40:32 -04:00
nathaniel b8b47ea6e6 Revert "Implement 3D and transposed 3D convolutions. (#1945)"
This reverts commit d696d74e3d.
2024-07-05 09:40:32 -04:00
Guillaume Lagrange 5236e12c81
Add models and examples reference (#1966)
Co-authored-by: Sylvain Benner <sylvain@benner.online>

---------

Co-authored-by: Sylvain Benner <sylvain@benner.online>
2024-07-04 16:22:08 -04:00
Guillaume Charifi d696d74e3d
Implement 3D and transposed 3D convolutions. (#1945)
* Implement 3D and transposed 3D convolutions.

* Merge changes from onnx-ir #1921 pr

---------

Co-authored-by: Dilshod Tadjibaev <939125+antimora@users.noreply.github.com>
2024-07-02 17:54:35 -05:00
Dilshod Tadjibaev 6f2ba34382
Print module part3 - Update book (#1940)
* Update book example guide

* Update Module book section on module display
2024-07-01 12:42:17 -05:00
Guillaume Lagrange cdd1fa1672
Refactor tensor data (#1916)
* Move distribution to module

* Add new TensorData with serialization support

* Implement display and from for TensorData

* Add missing Cargo.lock

* Add missing bytemuck feature

* Add zeros, ones, full and random TensorData methods

* Refactor Data -> TensorData usage

* Fix tests

Since TensorData is not generic over the element type anymore no type inference can be done by the compiler. We must explicitly cast the expected results to the expected backend type.

* Remove commented line

* Fix import

* Add record-backward-compat

* Remove dim const generic from TensorData

* Support NestedValue de/serialization with TensorData

* Fix burn-jit tests

* Remove eprinln

* Refactor onnx import to use TensorData

* Fix tch from_data

* Fix nested value serialization for u8

* Fix missing import

* Fix reduce min onnx test

* Fix deprecated attribute

* Remove shape getter

* Remove strict assert in tests

* Add tensor data as_bytes

* Add tensor check for rank mismatch

* Fix typo (dimensions plural)

* Fix error message

* Update book examples with from_data and fix Display impl for TensorData

* Add deprecation note
2024-06-26 20:22:19 -04:00
towerpark 3faf544bc4
Book: Fix the link to burn-train in "Learner" page (#1920)
Add the missing "crates/" to the link.

Co-authored-by: towerpark <t56ouhw1d@mozmail.com>
2024-06-25 09:15:34 -04:00
Arthur Brussee ac9f942a46
Remove GraphicsAPI generic for WgpuRuntime (#1888) 2024-06-17 09:04:25 -04:00
George b71c300638
Feat: Add `movedim` tensor operator (#1876)
*  (burn-tensor): add movedim function to tensor API

---------

Co-authored-by: Georgy Andreev <g.andreev@insilicomedicine.com>
2024-06-14 09:01:38 -04:00
towerpark 9a32e53e65
Book: Fix typos in the name of MessagePack format (#1868)
In the Record page, there are 4 places where "Pack" is written as
"Park." Also, the fix makes them the same as the official name, which
has no space and is in CamelCase.

Co-authored-by: towerpark <t56ouhw1d@mozmail.com>
2024-06-10 13:30:53 -04:00
Zirconium409122 e407c76def
Remainder operator doc (#1836)
* Adds remainder ops implementation for Tensor.

* Adds test for % operator.

* Add remainder and % operator entry in tensor.md

---------

Co-authored-by: Jonas Kantic <jk.mail@posteo.net>
2024-06-01 16:49:54 -05:00
Nathaniel Simard 36d4bcd705
[Refactor - Breaking] Refactor cube operations with better names & Support subgroup operations (#1839) 2024-05-31 17:07:21 -04:00
McArthur a2ad424fc8
Indices Operator (#1735) 2024-05-29 09:05:31 -04:00
Guillaume Lagrange e4836241e1
Fix `DataSerialize` conversion for elements of the same type (#1832) 2024-05-28 18:12:44 -04:00
Jonathan Richard 8de05e1419
Add configurable application logger to learner builder (#1774)
* refactor: add TracingSubscriberLogger trait and FileTracingSubscriberLogger struct

* Remove unused log module and renames, fmt

* Renamed tracing subscriber logger

* renamed to application logger installer

* book learner configuration update update

* fix typo

* unused import
2024-05-16 16:25:33 -04:00
Ahmed Yarub Hani Al Nuaimi 10737527d8
#1747 Upgrade Rust dependencies (#1748)
* #1747
Upgrade Rust dependencies

* Revert upgrade for tch

The update of tch on windows gives an error:

INTEL MKL ERROR: The specified module could not be found. mkl_vml_avx2.1.dll.
Intel MKL FATAL ERROR: cannot load mkl_vml_avx2.1.dll or mkl_vml_def.1.dll.

* Keep only .cargo/config.toml file which works with rust > 1.75

---------

Co-authored-by: Sylvain Benner <sylvain@benner.online>
2024-05-10 16:25:19 -04:00
Jonathan Richard e233c38b0f
Add hidden code snippets to guide example in Burn book [redo] (#1742)
* added hidden code snippets in Burn book guide example

* Update backend.md

* Revert last commit
2024-05-06 20:29:28 -04:00
mepatrick73 adbe97dc4d
Fixing various syntax errors in the Burn book (#1740) 2024-05-06 17:25:22 -04:00
Sylvain Benner 1f8b5d3efb
[guide] Remove ambiguity lib vs. executable (#1649) 2024-04-26 15:42:02 -04:00
WU Chen b387829731
Implement bidirectional LSTM (#1035)
* resolve conflict

* move `gate_product` to `GateController`

* BiLstm needs to use its own initializer when init

* resolve conflicts

* add some comments

* improve doc

* correct the description of GateController

* fix fmt

* add `LstmState`

* add test for state

* set batch 2 in bilstm test

* resolve conflict

* fix

* fix doc

* change the batch size back to 1

* change the batch size back to 1

* modify docstring; delete dead comment
2024-04-26 13:28:36 -05:00
Guillaume Lagrange fd26c1a241
Fix ONNX and PyTorch import section links in burn book (#1681) 2024-04-22 18:38:05 -04:00
Sylvain Benner 2d264e9a74
[burn-book] Fix broken URL to SUPPORTED-ONNX-OPS.md (#1651) 2024-04-17 08:15:32 -04:00
Sylvain Benner e700aa0cbf
[burn-book] Fix typos in getting started (#1650) 2024-04-17 08:04:20 -04:00
Nico Zweifel 5a3f345734
WindowDataset/windows function (#1553) 2024-04-17 07:51:53 -04:00
Guillaume Lagrange 0ee2021567
Fix guide project name in the book (#1631) 2024-04-16 09:38:13 -04:00