0.6.0
版本发布时间: 2021-07-09 07:37:30
Project-MONAI/MONAI最新发布版本:1.4.0(2024-10-17 08:54:28)
Added
- Overview document for feature highlights in v0.6
- 10 new transforms, a masked loss wrapper, and a
NetAdapter
for transfer learning - APIs to load networks and pre-trained weights from Clara Train Medical Model ARchives (MMARs)
- Base metric and cumulative metric APIs, 4 new regression metrics
- Initial CSV dataset support
- Decollating mini-batch as the default first postprocessing step
- Initial backward compatibility support via
monai.utils.deprecated
- Attention-based vision modules and
UNETR
for segmentation - Generic module loaders and Gaussian mixture models using the PyTorch JIT compilation
- Inverse of image patch sampling transforms
- Network block utilities
get_[norm, act, dropout, pool]_layer
-
unpack_items
mode forapply_transform
andCompose
- New event
INNER_ITERATION_STARTED
in the deepgrow interactive workflow -
set_data
API for cache-based datasets to dynamically update the dataset content - Fully compatible with PyTorch 1.9
-
--disttests
and--min
options forruntests.sh
- Initial support of pre-merge tests with Nvidia Blossom system
Changed
- Base Docker image upgraded to
nvcr.io/nvidia/pytorch:21.06-py3
fromnvcr.io/nvidia/pytorch:21.04-py3
- Optionally depend on PyTorch-Ignite v0.4.5 instead of v0.4.4
- Unified the demo, tutorial, testing data to the project shared drive, and
Project-MONAI/MONAI-extra-test-data
- Unified the terms:
post_transform
is renamed topostprocessing
,pre_transform
is renamed topreprocessing
- Unified the postprocessing transforms and event handlers to accept the "channel-first" data format
-
evenly_divisible_all_gather
andstring_list_all_gather
moved tomonai.utils.dist
Removed
- Support of 'batched' input for postprocessing transforms and event handlers
-
TorchVisionFullyConvModel
-
set_visible_devices
utility function -
SegmentationSaver
andTransformsInverter
handlers
Fixed
- Issue of handling big-endian image headers
- Multi-thread issue for non-random transforms in the cache-based datasets
- Persistent dataset issue when multiple processes sharing a non-exist cache location
- Typing issue with Numpy 1.21.0
- Loading checkpoint with both
model
andoptmizier
usingCheckpointLoader
whenstrict_shape=False
-
SplitChannel
has different behaviour depending on numpy/torch inputs - Transform pickling issue caused by the Lambda functions
- Issue of filtering by name in
generate_param_groups
- Inconsistencies in the return value types of
class_activation_maps
- Various docstring typos
- Various usability enhancements in
monai.transforms