Skip to content

Commit 3fd73f1

Browse files
KumoLiuericspod
andauthored
8110 update changelog for v1.4 (#8135)
part of #8110 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. --------- Signed-off-by: YunLiu <[email protected]> Co-authored-by: Eric Kerfoot <[email protected]>
1 parent 796271c commit 3fd73f1

File tree

2 files changed

+96
-3
lines changed

2 files changed

+96
-3
lines changed

CHANGELOG.md

Lines changed: 94 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,98 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
55

66
## [Unreleased]
77

8+
## [1.4.0] - 2024-10-15
9+
## What's Changed
10+
### Added
11+
* Implemented Conjugate Gradient Solver to generate confidence maps. (#7876)
12+
* Added norm parameter to `ResNet` (#7752, #7805)
13+
* Introduced alpha parameter to `DiceFocalLoss` for improved flexibility (#7841)
14+
* Integrated Tailored ControlNet Implementations (#7875)
15+
* Integrated Tailored Auto-Encoder Model (#7861)
16+
* Integrated Tailored Diffusion U-Net Model (7867)
17+
* Added Maisi morphological functions (#7893)
18+
* Added support for downloading bundles from NGC private registry (#7907, #7929, #8076)
19+
* Integrated generative refactor into the core (#7886, #7962)
20+
* Made `ViT` and `UNETR` models compatible with TorchScript (#7937)
21+
* Implemented post-download checks for MONAI bundles and compatibility warnings (#7938)
22+
* Added NGC prefix argument when downloading bundles (#7974)
23+
* Added flash attention support in the attention block for improved performance (#7977)
24+
* Enhanced `MLPBlock` for compatibility with VISTA-3D (#7995)
25+
* Added support for Neighbor-Aware Calibration Loss (NACL) for calibrated models in segmentation tasks (#7819)
26+
* Added label_smoothing parameter to `DiceCELoss` for enhanced model calibration (#8000)
27+
* Add `include_fc` and `use_combined_linear` argument in the `SABlock` (#7996)
28+
* Added utilities, networks, and an inferer specific to VISTA-3D (#7999, #7987, #8047, #8059, #8021)
29+
* Integrated a new network, `CellSamWrapper`, for cell-based applications (#7981)
30+
* Introduced `WriteFileMapping` transform to map between input image paths and their corresponding output paths (#7769)
31+
* Added `TrtHandler` to accelerate models using TensorRT (#7990, #8064)
32+
* Added box and points conversion transforms for more flexible spatial manipulation (#8053)
33+
* Enhanced `RandSimulateLowResolutiond` transform with deterministic support (#8057)
34+
* Added a contiguous argument to the `Fourier` class to facilitate contiguous tensor outputs (#7969)
35+
* Allowed `ApplyTransformToPointsd` to receive a sequence of reference keys for more versatile point manipulation (#8063)
36+
* Made `MetaTensor` an optional print in `DataStats` and `DataStatsd` for more concise logging (#7814)
37+
#### misc.
38+
* Refactored Dataset to utilize Compose for handling transforms. (#7784)
39+
* Combined `map_classes_to_indices` and `generate_label_classes_crop_centers` into a unified function (#7712)
40+
* Introduced metadata schema directly into the codebase for improved structure and validation (#7409)
41+
* Renamed `optional_packages_version` to `required_packages_version` for clearer package dependency management. (#7253)
42+
* Replaced `pkg_resources` with the more modern packaging module for package handling (#7953)
43+
* Refactored MAISI-related networks to align with the new generative components (#7989, #7993, #8005)
44+
* Added a badge displaying monthly download statistics to enhance project visibility (#7891)
45+
### Fixed
46+
#### transforms
47+
* Ensured deterministic behavior in `MixUp`, `CutMix`, and `CutOut` transforms (#7813)
48+
* Applied a minor correction to `AsDiscrete` transform (#7984)
49+
* Fixed handling of integer weightmaps in `RandomWeightedCrop` (#8097)
50+
* Resolved data type bug in `ScaleIntensityRangePercentile` (#8109)
51+
#### data
52+
* Fixed negative strides issue in the `NrrdReader` (#7809)
53+
* Addressed wsireader issue with retrieving MPP (7921)
54+
* Ensured location is returned as a tuple in wsireader (#8007)
55+
* Corrected interpretation of space directions in nrrd reader (#8091)
56+
#### metrics and losses
57+
* Improved memory management for `NACLLoss` (#8020)
58+
* Fixed reduction logic in `GeneralizedDiceScore` (#7970)
59+
#### networks
60+
* Resolved issue with loading pre-trained weights in `ResNet` (#7924)
61+
* Fixed error where `torch.device` object had no attribute gpu_id during TensorRT export (#8019)
62+
* Corrected function for loading older weights in `DiffusionModelUNet` (#8031)
63+
* Switched to `torch_tensorrt.Device` instead of `torch.device` during TensorRT compilation (#8051)
64+
#### engines and handlers
65+
* Attempted to resolve the "experiment already exists" issue in `MLFlowHandler` (#7916)
66+
* Refactored the model export process for conversion and saving (#7934)
67+
#### misc.
68+
* Adjusted requirements to exclude Numpy version 2.0 (#7859)
69+
* Updated deprecated `scipy.ndimage` namespaces in optional imports (#7847, #7897)
70+
* Resolved `load_module()` deprecation in Python 3.12 (#7881)
71+
* Fixed Ruff type check issues (#7885)
72+
* Cleaned disk space in the conda test pipeline (#7902)
73+
* Replaced deprecated `pkgutil.find_loader` usage (#7906)
74+
* Enhanced docstrings in various modules (#7913, #8055)
75+
* Test cases fixing (#7905, #7794, #7808)
76+
* Fix mypy issue introduced in 1.11.0 (#7941)
77+
* Cleaned up warnings during test collection (#7914)
78+
* Fix incompatible types in assignment issue (#7950)
79+
* Fix outdated link in the docs (#7971)
80+
* Addressed CI issues (#7983, #8013)
81+
* Fix module can not import correctly issue (#8015)
82+
* Fix AttributeError when using torch.min and max (#8041)
83+
* Ensure synchronization by adding `cuda.synchronize` (#8058)
84+
* Ignore warning from nptyping as workaround (#8062)
85+
* Suppress deprecated warning when importing monai (#8067)
86+
* Fix link in test bundle under MONAI-extra-test-data (#8092)
87+
### Changed
88+
* Base Docker image upgraded to `nvcr.io/nvidia/pytorch:24.08-py3` from `nvcr.io/nvidia/pytorch:23.08-py3`
89+
* Change blossom-ci to ACL security format (#7843)
90+
* Move PyType test to weekly test (#8025)
91+
* Adjusted to meet Numpy 2.0 requirements (#7857)
92+
### Deprecated
93+
* Dropped support for Python 3.8 (#7909)
94+
* Remove deprecated arguments and class for v1.4 (#8079)
95+
### Removed
96+
* Remove use of deprecated python 3.12 strtobool (#7900)
97+
* Removed the pipeline for publishing to testpypi (#8086)
98+
* Cleaning up some very old and now obsolete infrastructure (#8113, #8118, #8121)
99+
8100
## [1.3.2] - 2024-06-25
9101
### Fixed
10102
#### misc.
@@ -1040,7 +1132,8 @@ the postprocessing steps should be used before calling the metrics methods
10401132

10411133
[highlights]: https://github.com/Project-MONAI/MONAI/blob/master/docs/source/highlights.md
10421134

1043-
[Unreleased]: https://github.com/Project-MONAI/MONAI/compare/1.3.2...HEAD
1135+
[Unreleased]: https://github.com/Project-MONAI/MONAI/compare/1.4.0...HEAD
1136+
[1.4.0]: https://github.com/Project-MONAI/MONAI/compare/1.3.2...1.4.0
10441137
[1.3.2]: https://github.com/Project-MONAI/MONAI/compare/1.3.1...1.3.2
10451138
[1.3.1]: https://github.com/Project-MONAI/MONAI/compare/1.3.0...1.3.1
10461139
[1.3.0]: https://github.com/Project-MONAI/MONAI/compare/1.2.0...1.3.0

docs/source/installation.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -254,10 +254,10 @@ Since MONAI v0.2.0, the extras syntax such as `pip install 'monai[nibabel]'` is
254254
- The options are
255255

256256
```
257-
[nibabel, skimage, scipy, pillow, tensorboard, gdown, ignite, torchvision, itk, tqdm, lmdb, psutil, cucim, openslide, pandas, einops, transformers, mlflow, clearml, matplotlib, tensorboardX, tifffile, imagecodecs, pyyaml, fire, jsonschema, ninja, pynrrd, pydicom, h5py, nni, optuna, onnx, onnxruntime, zarr, lpips, pynvml, huggingface_hub, segment-anything]
257+
[nibabel, skimage, scipy, pillow, tensorboard, gdown, ignite, torchvision, itk, tqdm, lmdb, psutil, cucim, openslide, pandas, einops, transformers, mlflow, clearml, matplotlib, tensorboardX, tifffile, imagecodecs, pyyaml, fire, jsonschema, ninja, pynrrd, pydicom, h5py, nni, optuna, onnx, onnxruntime, zarr, lpips, pynvml, huggingface_hub]
258258
```
259259

260260
which correspond to `nibabel`, `scikit-image`,`scipy`, `pillow`, `tensorboard`,
261-
`gdown`, `pytorch-ignite`, `torchvision`, `itk`, `tqdm`, `lmdb`, `psutil`, `cucim`, `openslide-python`, `pandas`, `einops`, `transformers`, `mlflow`, `clearml`, `matplotlib`, `tensorboardX`, `tifffile`, `imagecodecs`, `pyyaml`, `fire`, `jsonschema`, `ninja`, `pynrrd`, `pydicom`, `h5py`, `nni`, `optuna`, `onnx`, `onnxruntime`, `zarr`, `lpips`, `nvidia-ml-py`, `huggingface_hub`, `pyamg` and `segment-anything` respectively.
261+
`gdown`, `pytorch-ignite`, `torchvision`, `itk`, `tqdm`, `lmdb`, `psutil`, `cucim`, `openslide-python`, `pandas`, `einops`, `transformers`, `mlflow`, `clearml`, `matplotlib`, `tensorboardX`, `tifffile`, `imagecodecs`, `pyyaml`, `fire`, `jsonschema`, `ninja`, `pynrrd`, `pydicom`, `h5py`, `nni`, `optuna`, `onnx`, `onnxruntime`, `zarr`, `lpips`, `nvidia-ml-py`, `huggingface_hub` and `pyamg` respectively.
262262

263263
- `pip install 'monai[all]'` installs all the optional dependencies.

0 commit comments

Comments
 (0)