Train configuration problem about translating-images-into-maps HOT 21 OPEN

Here: https://huggingface.co/roam/TIIM/tree/main
Only trained 4 epoch, don't expect too much on the result.

from translating-images-into-maps.

@basbaba How can I produce lane data?

Recently I'm working on nuScenes map datasets and found the Lane data in it's NuScenesMap:

def _load_layers():
self.lane = self._load_layer('lane')

you can get it by NuScenesMap or directly from json file.

from translating-images-into-maps.

I'm training mono-semantic-maps on a full nuscene dataset, with 16GB nvidia T4, 200 epoch, it's about 460 hours(each epoch 2.3 hours). I do think translating-imgs-into-maps will cost more time.
On mini dataset, translating-imgs-into-maps took about 7 hours for 600 epoch under the default configuration.

from translating-images-into-maps.

Thanks you very much, with the mini dataset, is the prediction result good or not?

from translating-images-into-maps.

I am working on a thesis related to this topic, can I ask for your code for reference, thank you very much

from translating-images-into-maps.

mono-semantic-maps url:
https://github.com/tom-roddick/mono-semantic-maps

you'd better train with the full dataset, prediction on mini-trained model is terrible.

from translating-images-into-maps.

Do you use a personal computer or rent a platform, I was able to run it but colab pro is not enough for 1 month, because there are only 100 computing units

from translating-images-into-maps.

I'm working on a server in office when there is no job running on it. In fact you don't need to do 200 epochs in one time, I think after training 10 epochs, a testable model would be generated. By saving and reloading you can get a procedural checkpoint for tests.

from translating-images-into-maps.

Hi, I bought a google colab pro account but it still doesn't meet the requirements, can you share me some checkpoints, thank you very much

from translating-images-into-maps.

Tomorrow when arriving office, I'll try to post a checkpoint to huggingface. It's trained on the full nuscene database.

from translating-images-into-maps.

Thank you very much, nice to meet you

from translating-images-into-maps.

@basbaba can you share your nuscenes convert code please

from translating-images-into-maps.

1. There is a pull request(New DataLoader) to this project, you can find here: https://github.com/avishkarsaha/translating-images-into-maps/pulls

2. I modified few things from the New DataLoader
3. the modified code is zipped and pushed to https://huggingface.co/roam/TIIM/tree/main
4. After downloading nuscenes full dataset, remember to pre-process it using https://github.com/tom-roddick/mono-semantic-maps
5. import dataloader_new.py to load data from the processed dataset

from translating-images-into-maps.

@basbaba How can I produce lane data?

from translating-images-into-maps.

If you mean how to get lane from datasets, I have no ideal. In Nuscenes, there is a definition:
NUSCENES_CLASS_NAMES = [
'drivable_area', 'ped_crossing', 'walkway', 'carpark', 'car', 'truck',
'bus', 'trailer', 'construction_vehicle', 'pedestrian', 'motorcycle',
'bicycle', 'traffic_cone', 'barrier'
]
'drivable_area', 'ped_crossing', 'walkway' may be what you want.

from translating-images-into-maps.

how did you go about getting the ground truth image, i did the same in https://github.com/tom-roddick/mono-semantic-maps however it is not the same as the ground truth in the mini episode, can you give me an example image of your ground truth. Thank you very much

from translating-images-into-maps.

from translating-images-into-maps.

Almost the same

from translating-images-into-maps.

@basbaba do you have facebook, skype or any social network, i want to exchange something about datasets and how to train models, there are some places i'm a bit confused, tks you very much

from translating-images-into-maps.

tks u, i am [email protected]

from translating-images-into-maps.

you can add contact me, https://t.me/ducthang1703

from translating-images-into-maps.