coral-cnn

coral-cnn copied to clipboard

Task importance analysis

5

`def task_importance_weights(label_array): uniq = torch.unique(label_array) num_examples = label_array.size(0) m = torch.zeros(uniq.shape[0]) for i, t in enumerate(torch.arange(torch.min(uniq), torch.max(uniq))): m_k = torch.max(torch.tensor([label_array[label_array > t].size(0), num_examples - label_array[label_array > t].size(0)])) m[i] = torch.sqrt(m_k.float())...

ZhugeKongan

some questions about progress-cacd

3

I have download the cacd dataset from the provided site. but I run the progress-cacd ,there comes some problems, TypeError: __call__(): incompatible function arguments. The following argument types are supported:...

Ayueer

Thank you for your amazing work. I wonder to know if the penultimate layer do not share weight (use a FC with num_dim*num_class parameters), will the accuracy improves since the...

zhiwenfan

Thanks for a great paper, it definitely solves the monotonic issue of the naive approach! I have a few questions for the authors: 1.) Is the loss described equivalent to...

GerardMaggiolino

About the monotonicity of the predict layer in the coral network

2

Hi, Sorry to bother. I had a problem when understanding the monotonicity of the coral network's predict layer. Here's the only statement I found modifying the bias layer adding to...

Tony-958

error in task_importance_weights function: afad-coral.py

1

Hi, I think the following function will throw an error if the dataset does not have some age values represented: ``` def task_importance_weights(label_array): uniq = torch.unique(label_array) num_examples = label_array.size(0) m...

jpcenteno80

Please compare with regression network

3

According to the design of your CORAL framework, it is clear that the output in the penultimate layer, which has only 1 node, is proportional to the age of the...

makecent

While traning my model i'm facing issue.

4

Epoch: 001/200 | Batch 0000/20149 | Cost: 70.1415 Epoch: 001/200 | Batch 0050/20149 | Cost: 59.7190 Epoch: 001/200 | Batch 0100/20149 | Cost: 56.4751 Epoch: 001/200 | Batch 0150/20149 |...

NarasimmanSaravana1994

About coral-cnn model

11

You used nn.AvgPool2d(7, stride=1, padding=2) at the end of the cnn network, the network input is 120 x 120, the input of pooling layer is 4 x 4, then after...

konioyxgq

predict result issue

8

I used my own data set. First, the picture work with preprocess-cacd.py, and then using cacd-coral.py to get the age prediction. I tested 5 pictures and it didn't work well....

konioyxgq