@@ -5,6 +5,69 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
55
66## [ Unreleased]
77
8+ ## [ 1.1.0] - 2022-12-19
9+ ### Added
10+ * Hover-Net based digital pathology workflows including new network, loss, postprocessing, metric, training, and inference modules
11+ * Various enhancements for Auto3dSeg ` AutoRunner ` including template caching, selection, and a dry-run mode ` nni_dry_run `
12+ * Various enhancements for Auto3dSeg algo templates including new state-of-the-art configurations, optimized GPU memory utilization
13+ * New bundle API and configurations to support experiment management including ` MLFlowHandler `
14+ * New ` bundle.script ` API to support model zoo query and download
15+ * ` LossMetric ` metric to compute loss as cumulative metric measurement
16+ * Transforms and base transform APIs including ` RandomizableTrait ` and ` MedianSmooth `
17+ * ` runtime_cache ` option for ` CacheDataset ` and the derived classes to allow for shared caching on the fly
18+ * Flexible name formatter for ` SaveImage ` transform
19+ * ` pending_operations ` MetaTensor property and basic APIs for lazy image resampling
20+ * Contrastive sensitivity for SSIM metric
21+ * Extensible backbones for ` FlexibleUNet `
22+ * Generalize ` SobelGradients ` to 3D and any spatial axes
23+ * ` warmup_multiplier ` option for ` WarmupCosineSchedule `
24+ * F beta score metric based on confusion matrix metric
25+ * Support of key overwriting in ` Lambdad `
26+ * Basic premerge tests for Python 3.11
27+ * Unit and integration tests for CUDA 11.6, 11.7 and A100 GPU
28+ * ` DataAnalyzer ` handles minor image-label shape inconsistencies
29+ ### Fixed
30+ * Review and enhance previously untyped APIs with additional type annotations and casts
31+ * ` switch_endianness ` in LoadImage now supports tensor input
32+ * Reduced memory footprint for various Auto3dSeg tests
33+ * Issue of ` @ ` in ` monai.bundle.ReferenceResolver `
34+ * Compatibility issue with ITK-Python 5.3 (converting ` itkMatrixF44 ` for default collate)
35+ * Inconsistent of sform and qform when using different backends for ` SaveImage `
36+ * ` MetaTensor.shape ` call now returns a ` torch.Size ` instead of tuple
37+ * Issue of channel reduction in ` GeneralizedDiceLoss `
38+ * Issue of background handling before softmax in ` DiceFocalLoss `
39+ * Numerical issue of ` LocalNormalizedCrossCorrelationLoss `
40+ * Issue of incompatible view size in ` ConfusionMatrixMetric `
41+ * ` NetAdapter ` compatibility with Torchscript
42+ * Issue of ` extract_levels ` in ` RegUNet `
43+ * Optional ` bias_downsample ` in ` ResNet `
44+ * ` dtype ` overflow for ` ShiftIntensity ` transform
45+ * Randomized transforms such as ` RandCuCIM ` now inherit ` RandomizableTrait `
46+ * ` fg_indices.size ` compatibility issue in ` generate_pos_neg_label_crop_centers `
47+ * Issue when inverting ` ToTensor `
48+ * Issue of capital letters in filename suffixes check in ` LoadImage `
49+ * Minor tensor compatibility issues in ` apps.nuclick.transforms `
50+ * Issue of float16 in ` verify_net_in_out `
51+ * ` std ` variable type issue for ` RandRicianNoise `
52+ * ` DataAnalyzer ` accepts ` None ` as label key and checks empty labels
53+ * ` iter_patch_position ` now has a smaller memory footprint
54+ * ` CumulativeAverage ` has been refactored and enhanced to allow for simple tracking of metric running stats.
55+ * Multi-threading issue for ` MLFlowHandler `
56+ ### Changed
57+ * Printing a MetaTensor now generates a less verbose representation
58+ * ` DistributedSampler ` raises a ValueError if there are too few devices
59+ * OpenCV and ` VideoDataset ` modules are loaded lazily to avoid dependency issues
60+ * ` device ` in ` monai.engines.Workflow ` supports string values
61+ * ` Activations ` and ` AsDiscrete ` take ` kwargs ` as additional arguments
62+ * ` DataAnalyzer ` is now more efficient and writes summary stats before detailed all case stats
63+ * Base Docker image upgraded to ` nvcr.io/nvidia/pytorch:22.10-py3 ` from ` nvcr.io/nvidia/pytorch:22.09-py3 `
64+ * Simplified Conda environment file ` environment-dev.yml `
65+ * Versioneer dependency upgraded to ` 0.23 ` from ` 0.19 `
66+ ### Deprecated
67+ * ` NibabelReader ` input argument ` dtype ` is deprecated, the reader will use the original dtype of the image
68+ ### Removed
69+ * Support for PyTorch 1.7
70+
871## [ 1.0.1] - 2022-10-24
972### Fixes
1073* DiceCELoss for multichannel targets
@@ -643,7 +706,8 @@ the postprocessing steps should be used before calling the metrics methods
643706
644707[ highlights ] : https://github.com/Project-MONAI/MONAI/blob/master/docs/source/highlights.md
645708
646- [ Unreleased ] : https://github.com/Project-MONAI/MONAI/compare/1.0.1...HEAD
709+ [ Unreleased ] : https://github.com/Project-MONAI/MONAI/compare/1.1.0...HEAD
710+ [ 1.1.0 ] : https://github.com/Project-MONAI/MONAI/compare/1.0.1...1.1.0
647711[ 1.0.1 ] : https://github.com/Project-MONAI/MONAI/compare/1.0.0...1.0.1
648712[ 1.0.0 ] : https://github.com/Project-MONAI/MONAI/compare/0.9.1...1.0.0
649713[ 0.9.1 ] : https://github.com/Project-MONAI/MONAI/compare/0.9.0...0.9.1
0 commit comments