helloworld

I find this problem in some datasets, such as FRGC. Then I find it works when I change the `epsilon` (core/layers.py line 11) from 1e-7 to 1e-5 and reduce the...

I have the same question. This what I get after run simclr.py and then perform Kmeans on the learned representations on Cifar10 dataset. The clustering performance is much lower than...

Dear author, I obtain a silimar result with that in table 3 of the paper (ACC=65.9,NMI=59.8,ARI=50.9): > Evaluate with hungarian matching algorithm ... {'ACC': 0.6829, 'ARI': 0.4890204494614667, 'NMI': 0.5742197581324099, 'ACC...

I means it is better to report the results of Kmeans on $\Phi_\theta\left(X\right)$ rather than Kmeans on $\Phi_\eta\left(X\right)$ in the row `Pretext [7] + K-means` of table 1 for clarity....

Do you really used 140*100 = 14000 iteration in clustering optimization step? > No, in all of my experiments, I halt at line 123 of DEKM.py. The default setting of...

> the y - y' resulted in a vector with the same dimension as y, but having zero values in all of the dimension except the last dimension? Yes, it...

Because $\mathbf{y}^\prime$ is a scalar, thus we have $$\frac{\partial{L_4} }{\partial{\mathbf{h}} } =\frac{\partial{L_4} }{\partial{\mathbf{y}} }\frac{\partial{\mathbf{y}} }{\partial{\mathbf{h}} }=\sum_{i=1}^k \sum_{\mathbf{y} \in \mathcal{C}_i}2\mathbf{V}(\mathbf{y}-\mathbf{y}^\prime)$$

In the DEKM context, we interpret $L_4=\sum_i \sum_y ||y-y'||^2$ as a regression task, with $y'$ representing a predetermined constant target value. The objective of regression here is to adjust $y$...

This derivation uses two properties of the [trace function](https://en.wikipedia.org/wiki/Trace_(linear_algebra)): (1) Cyclic property $Tr(ABCD)=Tr(BCDA)$, and (2) trace additivity $\sum_i Tr(A_i)=Tr(\sum_i A_i)$.

> is it the version in the image? Yes, it is. Any question is welcom.