benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-336482849
@Ldpe2G I did a first PR to fix this before #8226, but it seems stuck in the
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334823004
FYI works perfectly with your suggestion.
Thanks for your help @Ldpe2G .
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334485858
Yhea, you're right. Almost same error message with RMSE, but this time it is
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334454251
ok, will check once home.
I had the same issue with RMSE if I remember
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334422769
FYI
`metric.update(batch.label, mod.getOutputsMerged)`
throws the exact
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334410375
Ok, will try with metric instead of updateMetric.
I did a self contained
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334366042
Yes it is.
```scala
mod.forward(batch)
val m =
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334366042
Yes it is.
```scala
mod.forward(batch)
val m =
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334366042
No it is not (sorry had to editI it is my answer).Yes, it is.
```scala
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334366042
Yes, I is.
```scala
mod.forward(batch)
val m =
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334258853
I changed to the intermediate api
```scala
val logger =
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334062559
Right, I also find this error message very strange after looking closely at
the
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-334054179
Yes, I am conducting a segmentation tasks.
My label has only one channel,
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-333992969
ok, I checked and log the shapes as suggested and realize that it is not the
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-333862739
@Ldpe2G all right, I am going to check that (pretty sure it was
(1,1,868,868),
benqua commented on issue #8129: [scala] Module api: label (1,1,868,868) and
prediction (1,868,868)should have the same length
URL:
https://github.com/apache/incubator-mxnet/issues/8129#issuecomment-333796027
If that helps, the last layer of my network is:
```scala
val out=
16 matches
Mail list logo