-
Notifications
You must be signed in to change notification settings - Fork 1.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add ms_flip and sliding window #576
Merged
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
wuyefeilin
added a commit
to wuyefeilin/PaddleSeg
that referenced
this pull request
Nov 13, 2020
ZeyuChen
pushed a commit
that referenced
this pull request
Jul 25, 2021
* update `category` to `class` * add voc and ade20k config * add ms_flip and sliding window (#576) * add result of hrnetw18 on voc * update README.md * add results of hrnetw48 on voc12aug * update progbar.py * update BatchNorm to BatchNorm2D * add ms_flip and sliding window docs * Update quick_start.md * update hrnet.py * limit num_workers for evaluation while training * update hrnet.py * rm name argument * update resnet_vd.py * add gcnet and ocrnet result of voc12 * Update README.md * make dygraph as home page * add gscnn * add gscnn * add apis docs * add unet++ * Update models.md * Update backbones.md * Update backbones.md * Update cvlibs.md * Update datasets.md * add api tutorial * fix bce loss bug * update paddle-2.0rc1 * only save latest model and best model * add keep_checkpoint_max * update unet.py * add flops calculation * rm prepare_context * add amp * update static api to paddle2.0 * add LimitLong transform * align the dygraph structure * add static amp * dygraph add parameters to control amp * update time calculation * add instruction * update dataset raise information * rm unused config files * update align corners True to False * update hrentw18 config file * update train.py * update deeplabv3p_resnet50_vd_cityscapes.yaml * add bias config to fcn head for hrnet * using BatchNorm in one gpu * update README.md * Update README.md * add config check module * update config.py * update num_classes check * add config check to predict.py * Update README.md * Update layer_libs.py * paddleseg/core/train.py * update README.md * add dygraph fleet * fix padding to symmetry * add fleet to static * update README.md * fix fp16 to fleet and add interpolate to black list * add fleet to static * update README.md * fix fp16 to fleet and add interpolate to black list * update hrnet config * update some * update hrnetw18_cityscapes_1024x512_215.yaml * update hrnet.yml * update train.py * fix fleetrun bug * fix syncbn in fleet * update deeplabv3p_resnet101_os8_voc12aug_512x512_40k.yml * fix variable confict * update time calculation * update logger format * update logger format * update deeplabv3p.yml * fix ade label bug * suport NHWC data format for DeepLabv3+ * fix the data_format bug * fix the data_format bug * fix data_format for evaluation * add script for fp16 training * add script for fp32 training * fix reverse for ResizeByLong * fix decouplde_segnet grad bug * add panoptic segmentation * update README.md * update README.md * fit to paddle2.1 * fit to paddle2.1 * update README.md * sync_batch_norm supports amp * rm paddleseg * update train process * update val process * update predict process * update models * recover to origin * update README.md * rm some useless * mv loss to paddleseg * update copyright * format import * update annotations * update annotations * update copyright and annotations * update static config location * add origin legacy thing * rm warmup and cosine_decay * alignalign dygraph * align dygraph * update README.md * update solver.py * update train.py * Update model_libs.py * Update README.md * add panoptice segmentation link * update shape * rm README.md Co-authored-by: zhangting2020 <zhangting_2017@163.com> Co-authored-by: Roc <lrslj@live.com> Co-authored-by: wuzewu <wuzewu@baidu.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.