Closed Tranbaber closed 6 months ago
tools/train.py
could be used for training.configs/
folder. The __base__
folder contains basic configurations for dataset, models, training schedules and default settings.mmseg/models/
folder, and the framework is split into several submodules and each saved in respective subfolders. For more details, please refer to the MMsegmentation 0.29.1 tutorial.Thanks for your help, I see a lot of dataset profiles in the configs/base/datasets folder, which profile do I need to use if I need to train the model for both semantic segmentation and edge detection tasks? Want to train the same pre-trained model as you posted. @martin-liao
MS_tiny_cityscapes.py
for cityscapes dataset.
Oh... It seems that some hyperparameters in the data pre-processing code are not optimum. I am uploading processed data now and I will correct the mistakes later.
I downloaded the pre-training model and trained it using the commands in the image, but the prompt says that the model file can't be found, so I would like to ask where the model file should be placed? @martin-liao
Oh... It seems that some hyperparameters in the data pre-processing code are not optimum. I am uploading processed data now and I will correct the mistakes later.
Thank you for your great contribution to the open source community!
I downloaded the pre-training model and trained it using the commands in the image, but the prompt says that the model file can't be found, so I would like to ask where the model file should be placed? @martin-liao
Sorry, I was careless. Problem solved. @martin-liao
I downloaded the pre-training model and trained it using the commands in the image, but the prompt says that the model file can't be found, so I would like to ask where the model file should be placed? @martin-liao
Please put it under the /ckpt
folder. We recommend to use the Linux environment for convenience
I downloaded the pre-training model and trained it using the commands in the image, but the prompt says that the model file can't be found, so I would like to ask where the model file should be placed? @martin-liao
Please put it under the
/ckpt
folder. We recommend to use the Linux environment for convenience
Ok, thanks for the advice, I was trying to test it on my laptop first, the actual training will be in Linux! @martin-liao
configs/base/datasets/cityscapes.py:
configs/base/datasets/cityscapes_boundary.py:
Do you see any problem with my dataset path settings? I checked the dataset and these files are not missing, how can I solve this problem? @martin-liao
Hello Author! I found a small bug in your project, in mmseg/datasets/cityscapes.py you look for a label filename with the suffix "_gtFine_labelTrainIds.png", but using data_preprocess /cityscapes-preprocess/code/demoPreproc_gen_png_label.m generates a label filename suffix of "_gtFine_trainIds.png" and there is a mismatch. I'm not sure if this is a personal issue for me. I was able to train the network properly after modifying it. Thanks again to the author. @martin-liao
No, ``_gtFine_labelTrainIds.png" is right. Please refer to cityscapesscripts about converting the semantic+instance label to semantic label only.
Okay, thank you very much for your help. My current training process is looking fine right? Also I would like to ask about checkpoint saving, how many .pth files will be saved for a training session and where will they be saved to? @martin-liao
Hi, I have fixed the error in the data pre-processing code just now. Please use the newest code to generate training semantic boundary labels!
OK,Thanks a lots!
Generated semantic boundary map for aachen_000000_000019.png
should be similar to this:
I will upload the pre-processed data to baidu disk and onedrive later
I will upload the pre-processed data to baidu disk and onedrive later
Okay, thanks! I have another small question, if I want to do both instance segmentation and edge detection, what do I need to change? Because there is _gtFine_instanceIds.png in the dataset, is it possible to train for instance segmentation? I would like to ask the author for this question. @martin-liao
The answer is yes:
The answer is yes:
generating instance label following the cityscapesscripts for supervision;
the semantic boundary should be instance-sensitive instead of instance-insensitive for the IS task. If you are interested in the difference between instance-sensitive/insensitive, we suggest you read the simultaneous edge alignment and learning (SEAL)
OK,I will try it, Thanks!
As the problem has been solved, we close the issue now.
I have the following questions about training: