Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Differnet chenggui #22

Open
wants to merge 73 commits into
base: master
Choose a base branch
from
Open

Differnet chenggui #22

wants to merge 73 commits into from

Conversation

ChengguiSun
Copy link

No description provided.

lihyin and others added 30 commits September 13, 2020 21:54
@lihyin
Add Pytorch installation instructions for potential issues in Windows
ac3c501
@lihyin
Add the Readme tips to resolve GPU Out of Memory issue and more speci…
6104c35 
…fic instructions how to run the training
@jinzishuai
train without test: save model and weight
16d69d6
@jinzishuai
Add timing
9ab1a3e
@jinzishuai
runTest.py not working
2ada233
@jinzishuai
runTest.py working
a505a2f
@jinzishuai
to use the model: no need to load the weights
7c8b3f4
@jinzishuai
load the model file directly
0201156
@jinzishuai
run test without loading training data
ac0e602
@jinzishuai
Problem with Linux
f4d31e1
@jinzishuai
Enable LFS: add model_zerobox_test
4cbcef3
@jinzishuai
stop using git-lfs
710f323
@jinzishuai
we don't need score_obs at testing: without good images (still need f…
4116214 
…older)
@jinzishuai
cleanup lfs
394ba7e
@jinzishuai
consistent results with zerobox test_differnet.py
c484fac
@lihyin
Merge pull request #3 from zerobox-ai/jinshi/PoC
70103d5 
Jinshi/po c
@lihyin
Separate validation and test datasets; Add test.py for test only
5f88cd5
@lihyin
Fix how to get target_threshold; Add target_tpr in config.py;
8fccb26
@kuangzijian
added new function differences_as_input. instead of using the input i…
27c831d 
…mages, we calculate the differences between each set of 2 images, then we feed the differences as our input to the model
@kuangzijian
updated differences function
03b70c3
@txrxrxr
Added function to randomly shrink image size of width and lenth
2b03c72
@txrxrxr
Added new random shrink
ffdd7e4
@kuangzijian
Added new annotation and data extratction method.
672c7c5
@txrxrxr
Added function to randomly shrink image size of width and length
57a4fa9
@kuangzijian
Updated the data extraction method
3c89256
@kuangzijian
Updated the utils not using the differences as input
96ea14b
@kuangzijian
Updated the data_extraction.py structure
6b9c57e
@kuangzijian
Updated the data_extraction structure
39fe3a1
@kuangzijian
Revert back the Utils, and remove the part that apply the concept of …
c656115 
…ResNet and train on the differences between samples and the averaged sample. #158
@kuangzijian
Revert back the Utils, and remove the part that apply the concept of …
a43d71f 
…ResNet and train on the differences between samples and the averaged sample. #158
kuangzijian and others added 27 commits December 5, 2020 01:31
@kuangzijian
updated utils to include save_transformed_image in the config.py
c9bd62f
@kuangzijian
Merge remote-tracking branch 'origin/zijian' into zijian
f945989
@kuangzijian
draw ground truth bounding box on saved original frames
f5b056b
@kuangzijian
Included prediction visualization part
0eb3a40
@kuangzijian
Updated config.py
26fe50f
@kuangzijian
Updated visualization part
8d7b731
@txrxrxr
Added new model MaskDifferNet.
9541774
@txrxrxr
Merge branch 'zijian' of https://github.com/zerobox-ai/differnet into…
3a2ec55 
… zijian
@kuangzijian
Merge branch 'zijian' of https://github.com/zerobox-ai/differnet into…
57265d9 
… zijian
@txrxrxr
Added visual for MaskDifferNet.
bc9177f
@kuangzijian
Added optimizer parameters for VAE
beb4b1b
@kuangzijian
Merge remote-tracking branch 'origin/zijian' into zijian
2161fef 
# Conflicts:
#	model.py
@kuangzijian
code clean up
fdcf954
@kuangzijian
modified prediction class, to check if frame_name_is_given on each im…
d04da3b 
…age file
@kuangzijian
Modify predict.py code for differnet to have better result visualization
ce354e1
@kuangzijian
updated model naming format
8d58892
@txrxrxr
Changed export gradient map to generate the map for both good and def…
ba3856d 
…ect samples on the transformed images.
@kuangzijian
merge test and predict into one file
3e1351c
@kuangzijian
added mask calculation functions and apply calculated mask to input i…
76f9536 
…mages function
@kuangzijian
fixed typo
2bff3dd
@kuangzijian
code clean up
9aae1db
@kuangzijian
output json file name fix; model.pth load file name fix
745b0a4
@kuangzijian
moved test code out of the train.py (into the new test.py); renamed m…
983ae9f 
…ain to run_traning.py
@kuangzijian
Add todo list.
e381c68
@kuangzijian
Added ROC curve in Test.
aa7ad9d
@kuangzijian
Shrink Mask
d52dfb9
@ChengguiSun
change datafolder to experiment6.1
6d64912
@ChengguiSun
Copy link
Author

update workfolder directory in config file

@marco-rudolph marco-rudolph marked this pull request as ready for review April 30, 2021 11:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
6 participants
@ChengguiSun @lihyin @jinzishuai @kuangzijian @txrxrxr @Jason0917