DDU

DDU copied to clipboard

DDU for semantic segmentation

1

Hi Thanks for this interesting work. I read you other article on applying DDU to semantic segmentation, and I was wondering if there's another repository specific for that one ?...

AlkaSaliss

provide a pre-trained ImageNet model

1

I appreciate your work and would like to extend it to some scenarios. Could you provide a pre-trained ImageNet model with your modified network (average pooling and spectral normalization)?

kpqnkkaa

@omegafragger What is the meaning of lines below in your `get_embeddings()` function in `gmm_utils.py`? `out = net(data)` `out = net.feature` Is there any meaning in this overwriting on `out`?

ho-suk-93

Error in gmm_fit(embeddings, labels, num_classes)

3

UnboundLocalError: local variable 'gmm' referenced before assignment But when I removed the "break" in for loop,it worked.

ReusJeffery

I've taken a look at your code, and it seems like it's not quite ready for any modifications

LailaAlhussain

Feature Densities Always Zero

2

Hello, I'm having an issue with the active learning script. I'm running: `CUDA_VISIBLE_DEVICES=7 python active_learning_script.py --seed 1 --model resnet18 -sn -mod --al-type gmm` and I have set a breakpoint right...

JacobOaks

First, thank you for your great work! I am testing your metrics on our model. I will cite your work if I can get fine results. However, Softmax and GDA...

ho-suk-93

Multiplication of prior with log likelihood - Code not found !!

4

@BlackHC Can you please tell me where you are multiplying the prior with the log_prob of the logits during evaluation.  As mentioned in the line 12: We have to...

jeethesh-pai

Error in computing gaussian_model

9

The gaussian mixture model computations from mean and covariance matrix (obtained from feature's of model - nn.feature), is constantly throwing the error that covariance matrix is not positive definite ```...

Karthik-Ragunath

Karthik-Ragunath