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.

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

I can't reproduce the same result with almost the same surroundings! please help me,thank you! #39

Open
tjpulkl opened this issue Oct 30, 2019 · 0 comments

Comments

@tjpulkl
Copy link

tjpulkl commented Oct 30, 2019

this is relate parameters :
CS_PATH='./dataset/LIP'
LR=1e-3
WD=5e-4
BS=14 #changed by lkl from 24 to 14 on 20191027
GPU_IDS=0,1,2,3
RESTORE_FROM='./dataset/resnet101-imagenet.pth'
INPUT_SIZE='384,384'
SNAPSHOT_DIR='./snapshots'
DATASET='train'
NUM_CLASSES=20
EPOCHS=150
But, The evaluate results are as following:
9600 processd
9920 processd
Pixel accuracy: 86.441436
Mean accuracy: 62.053916
Mean IU: 50.475799
almost 3%lower than the paper.
Could you please tell me some reasons about this problem?
The evaluate parameters are as following:
CS_PATH='./dataset/LIP'
BS=32
GPU_IDS='0'
INPUT_SIZE='384,384'
SNAPSHOT_FROM='./snapshots/LIP_epoch_149.pth'
DATASET='val'
NUM_CLASSES=20

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant