cyanogenoid / dspn Goto Github PK

what does it mean by "dataset = Circles()"? When I ran it, NameError was raised showing that name 'Circles' is not defined? Thanks

Hi, thank you for fast response!
I tested MNIST-set experiments on MLPDecoder and found that the output cardinality tends to go small when using the Chamfer loss.
While it is understandable that Chamfer loss only needs to keep "a few" points to minimize their loss (several target points map to the shared output point), I just want to check if this phenomena also happened to you (to check that it is not my problem, e.g., of environments).
Also, is it common to use an additional regularizer to enforce output and target to have similar number of points (i.e., || # of pred masks = # of target masks ||)?
I'm pretty new in this domain, hence thank you for your kind help! :)

Hey! Nice work! I was wondering if you have any performance measures such as the runtime? E.g. how long does one iteration/sample take for the object detection task? thx

Hi!
This is a nice work! I am studying your paper and trying to running the DSPN method on my own dataset. However, I find the repr_loss and set_loss can not convergence after some epoches.
So I wonder if the learning rate η = 800 is suit to my dataset, which is CrowdHuman dataset.
Or can you tell me how you adjust the learning rate in your experiments.
Or could you please give me any advice about using DSPN on custom dataset?
Thanks a lot!

Hi, it seems that the code use the average set loss (in "practical tricks" in Section 3.2) for the Chamfer loss but not for the Hungarian loss. Should I need to use the average one or only the final one to reproduce your bounding box and state prediction results?
Also, line 233-239 seems not used in the left of the code!

In the resnet convolutional encoder in https://github.com/Cyanogenoid/dspn/blob/master/dspn/model.py#L109 there is no activation function following the batchnorm layer. Is this intentional. If so, why what this decision made?

Trying to reproduce results on clevr-box by running scripts/clevr.sh clevr-box 1. Got following error.

Traceback (most recent call last):
File "train.py", line 414, in
main()
File "train.py", line 395, in main
run(net, train_loader, optimizer, train=True, epoch=epoch, pool=pool)
File "train.py", line 211, in run
input, target_set, target_mask
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/lila/home/fengc/PlayGround/dspn/dspn/model.py", line 85, in forward
latent_repr = self.input_encoder(input)
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/lila/home/fengc/PlayGround/dspn/dspn/model.py", line 117, in forward
x = self.end(x)
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/container.py", line 92, in forward
input = module(input)
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/fengc/anaconda2/envs/pyrodev/lib/python3.7/site-packages/torch-1.1.0-py3.7-linux-x86_64.egg/torch/nn/modules/conv.py", line 338, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size 512 512 3 3, expected input[32, 2048, 4, 4] to have 512 channels, but got 2048 channels instead

I fixed it myself but I wonder what you intended it to be. In case I am missing something here.

Thanks.