-
Hi Hanxiao,
I train this model https://github.com/quark0/darts/blob/master/rnn/genotypes.py#L33 on PTB. I obtain the similar validation performance (val ppl = 59.0), but the test ppl (61.3) is much…
D-X-Y updated
5 years ago
-
I am using V100 gpu which has 16G memory. Here is the error log-
```
07/10 07:05:24 PM valid 000 2.609589e+00 47.656250 76.562500
THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCStorage.cu l…
-
Hi @NeroLoh, I found that it takes amost half of an hour before it runs to sess.run. While in [enas](https://github.com/melodyguan/enas), it costs relatively less time. Do you have the same situation?
-
Hi, thanks for the nice implementation. I am trying to modify the codes to support multi-gpu but it didn't work out. I don't know how to parallel the Architect. Do you have any suggestions or are you …
-
train_grads_pos and train_grads_neg in func compute_unrolled_step are equal due to the unchanged train_loss, which finally leads to a 1st-order implement.
https://github.com/NeroLoh/darts-tensorflo…
-
Hi,
It seems that during training, the cell uses a weighted sum over all edges to generate features from one node to another node, as `https://github.com/quark0/darts/blob/master/cnn/model_search.p…
D-X-Y updated
6 years ago
-
Thanks for the sharing the implementation. Please, anybody know why when training, I get the 'truth' = empty string, here is the output of the debugger:
Epoch 1
... Truth 0 : UNK UNK with UNK white…
-
**Is your feature request related to a problem? Please describe.**
Now that decanting into 2 dose potions is possible barbarian herblore is a viable training method (it is 1t and you can create potio…
-
Hi,
During training, you add one batchnorm layer after the pooling layer, as https://github.com/quark0/darts/blob/master/cnn/model_search.py#L18. However, when testing the searched architecture, th…
D-X-Y updated
6 years ago
-
SELECT 14, bq.id, 'Legal'
FROM (
SELECT
`u`.`id` AS `id`,
CASE
WHEN layout = 'transform' OR layout = 'flip' THEN
GROUP_CONCAT(CASE WHEN…