lausannen / nas-fcos Goto Github PK

Hi, thanks for your work!
I wonder what is the GPU latency(e.g., on a TITAN-Xp) of your best model (NAS-FCOS, w/ improvement, X-64x4d-101, Box AP = 46.1 on coco test-dev).

Three years have passed, when will the search code be open sourced?

您好，请问一下这个代码是不完整的吗？

how can i fix this issue?

Thanks

Hello,

I was wondering if it is necessary to have dataset on device. For example to train a model for a resource constrained device (Say Tx2 or mobile phone), does the implementation require the dataset (COCO) to be present on the target device.

Could you let me know a possible solution in a situation wherein we cant load the entire data on a resource constrained device

Hi,

I want to train the code for single class object detection. Will i be able to train using the code from this repository?

Hi， I found the trained model you provided (R_50_NAS) is NAS FPN model, not NAS FPN + head model. In the paper, you say "It turns out that our NAS-FCOS model still achieves better performance (AP = 38.9 with FPN search only, and AP = 39.8 with both FPN and Head searched) than the DeformFPN-FCOS model (AP = 38.4) under this circumstance." So, the R_50_NAS is NAS FCOS of FPN search only?

Hi, I have tested your code on coco dataset. no matter training or testing, there is no output when executing fpn module and the code exited without any errors.the code is as follows:
in single_stage_detector.py :

there is no output and the code is exited without any errors or warnnings:

training script:python -m torch.distributed.launch --nproc_per_node=2 --master_port=1213 tools/train_net.py --config-file "configs/search/R_50_NAS_retinanet.yaml"
testing script:python -m torch.distributed.launch --nproc_per_node=1 tools/test_net.py --config-file "configs/search/R_50_NAS_retinanet.yaml"

Have you met this problem?could you explan the reason? thanks!

rt, thanks~

Hello, I have become interested in NAS and object detection but was surprised by how out-of-date the current software is. I'm curious to know how long it would take to update the code so that it would be compatible with the latest versions of the software dependencies.

Thank you for sharing your great works!

I'm trying hard but I think it's maybe impossible to download it from Baidu for non-china people as it's so hard to make even just an account for that site.
So, please I would like to ask you to share the pretrained model on dropbox or google drive.

Thank you so much!

We worry that NAS is more sensitive to datasets, such as if we add some data to our datasets the performance will be bad!

I read the following installation instructions for the project you gave me, which is the installation process of maskrcnn_bench. How to install your open source project and search the network on your own dataset for target detection?Thank you very much for your answers in your spare time