You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
inference result with model trained with train.py is not good and model size is almost twise bigger then pretrained model #62
changed the title [-]Train result not good and,[/-][+]inference result with netword trained with train.py is not good and model size is almost twise bigger then pretrained model[/+]on May 16, 2019
changed the title [-]inference result with netword trained with train.py is not good and model size is almost twise bigger then pretrained model[/-][+]inference result with model trained with train.py is not good and model size is almost twise bigger then pretrained model[/+]on May 16, 2019
I tried to train PSPNet101 with cityscapes dataset.
I did below.
・download dataset
・edit cityscapes_trail_list.txt gtFine_labelTrainIds.png to gtFine_labeIds.png
・edit train.py DATA_DIRECTORY to suit my image data
・change batch size 2 to 1
・python train.py
After 15hours I finished the training .
Inference with inference.py is so poor.
Traind data I created is
File size of model.ckpt-60000.data-00000-of-00001 is about 502M byte.
File size of model.ckpt-60000.meta is about 2.7M byte.
Pretraind data is
File size of model.ckpt-0.data-00000-of-00001 size is 254M .
File size of model.ckpt-0.meta size is 254M .
I think the problem is the model trained is not proper because of the model.ckpt-60000.data-00000-of-00001 size is twice bigger than pretrained file model.ckpt-0.data-00000-of-00001.
Or the problem is model.ckpt-60000.meta size is too small compared wit pretrained file model.ckpt-0.meta size is 254M.
Activity
[-]Train result not good and,[/-][+]inference result with netword trained with train.py is not good and model size is almost twise bigger then pretrained model[/+][-]inference result with netword trained with train.py is not good and model size is almost twise bigger then pretrained model[/-][+]inference result with model trained with train.py is not good and model size is almost twise bigger then pretrained model[/+]kiitosu commentedon May 16, 2019
I tried to train PSPNet101 with cityscapes dataset.
I did below.
・download dataset
・edit cityscapes_trail_list.txt gtFine_labelTrainIds.png to gtFine_labeIds.png
・edit train.py DATA_DIRECTORY to suit my image data
・change batch size 2 to 1
・python train.py
After 15hours I finished the training .
Inference with inference.py is so poor.
Traind data I created is
File size of model.ckpt-60000.data-00000-of-00001 is about 502M byte.
File size of model.ckpt-60000.meta is about 2.7M byte.
Pretraind data is
File size of model.ckpt-0.data-00000-of-00001 size is 254M .
File size of model.ckpt-0.meta size is 254M .
I think the problem is the model trained is not proper because of the model.ckpt-60000.data-00000-of-00001 size is twice bigger than pretrained file model.ckpt-0.data-00000-of-00001.
Or the problem is model.ckpt-60000.meta size is too small compared wit pretrained file model.ckpt-0.meta size is 254M.
How could I solve this problem?
mistaker-likf commentedon Jan 15, 2020
My problem is same with you. Have you solve the issue?
kiitosu commentedon Jan 16, 2020
I'm sorry. No I haven't.