Ha YongWook

If you have some trouble to get the data, you can just use the original data [here](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)! :)

The problem seems still there. I've made a little trick of detouring this `unsupported namedtuple` problem. It's a kind of mixed solution of @fmassa 's option 1 and 2. It...

> I tried out your solution @YongWookHa, however, now I am getting an error to calculate loss function > Error: > > `File "/home/min/a/ghosh37/distiller/distiller/apputils/image_classifier.py", line 588, in train loss =...

Updated the issue. I thought the handler returns the correct value only in the `cuda:0`. However, it turns out that alternating requests return the correct value. In a cycle of...

@microsoft-github-policy-service agree

I am facing same problem. It's about dynamic batch size.

Hello, @moha23. An year passed! :) ```python x_out = Subtract()([x_in, x_recon]) recon_loss = 0.5 * K.sum(K.mean(x_out**2, 0)) + 0.5 * np.log(2*np.pi) * np.prod(K.int_shape(x_out)[1:]) ``` As I think, in `recon_loss`, `...

Similar error occurs during bulk inserting large(approx. 500M points) collection. ``` 2025-06-01T07:32:22.743212Z ERROR qdrant::startup: Panic backtrace: 0: 1: 2: 3: 4: 5: 6: 7: 8: 9: 2025-06-01T07:32:22.743230Z ERROR qdrant::startup: Panic...