-
https://github.com/manuel-delverme/constrained_optimization/blob/bcf17e4a00c656562f1d88d39d1cb6d911b00817/src/torch_constrained/constrained_optimizer.py#L58-L59
The user should be the one performin…
-
When running `MCCD` in the pipeline, the following error is produced:
```
09/12/2022 11:25:38 ERROR: 'SourceLocGrad' object has no attribute '_input_data_writeable'
Traceback (most recent call la…
-
I want to run a RNN (https://fluxml.ai/Flux.jl/stable/models/recurrence/) on the GPU, using the explicit (https://fluxml.ai/Flux.jl/stable/training/training/#Implicit-or-Explicit?) gradients.
This …
-
Hi All,
I've been trying to get per-sample gradients of a simple feed-forward network that contains a `torch.slogdet` as its final layer. When I go to apply `vmap` to `jacrev` the number of argumen…
-
BERT_BASE and BERT_LARGE contains 110M and 340M parameters respectively. Currently multi-GPU scaling is poor for this model and the result shows large overhead for cross-GPU ndarray copies.
The de…
-
您好,很高兴能阅读到您公开您论文的代码;对于论文中描述得FBP的部分对应的代码是下面decode对吗?
```
def decode(self, sin_fan):
AT, alpha, h, w_c=self.AT,self.alpha,self.h,self.w_c
cos_alpha = tf.math.cos(alpha)
s_fa…
-
Trying to train a model but i get this error after the start
`File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 852, in
main()
File "/content/diffusers/examples/dream…
-
**Describe the bug**
When I was trying something like exponentially weighted moving average, I saw the gradients may be incorrect.
**To Reproduce**
```py
ti.init(arch=ti.cuda)
row_num, co…
-
I do not quite understand the mechanism behind @customop('numpy').
I find that there's an intermediate variable 'Q' which is expensive to compute and appears in computing both the output and gradient…
-
I meet a problem about gradient!!!
the code is :
`
from seq2seq import SimpleSeq2Seq, Seq2Seq, AttentionSeq2Seq
import numpy as np
input_length = 5
input_dim = 3
output_length = 3
outp…