Skip to content

Onnx Yolo v4 example #253

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 7 commits into
base: master
Choose a base branch
from
Draft

Onnx Yolo v4 example #253

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b42c934
Add loaders for ELU, RELU activation layers (#78)
kokorins Jun 14, 2021
be12a17
Merge branch 'JetBrains:master' into master
kokorins Jun 21, 2021
3b36a51
Add parameter trainability to ELU, ReLU savers
kokorins Jun 21, 2021
b856671
Merge branch 'JetBrains:master' into master
kokorins Jun 23, 2021
d0626f2
Merge branch 'JetBrains:master' into master
kokorins Sep 26, 2021
62d7c69
Merge branch 'JetBrains:master' into master
kokorins Oct 2, 2021
a9671e9
Add ONNX Yolo v4 example
kokorins Oct 2, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Add parameter trainability to ELU, ReLU savers
  • Loading branch information
@kokorins
kokorins committed Jun 21, 2021
commit 3b36a5165d8f1215e4ff9225da7f4e453dd18dc1
6 changes: 4 additions & 2 deletions api/src/main/kotlin/org/jetbrains/kotlinx/dl/api/inference/keras/ModelSaver.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -393,15 +393,17 @@ private fun createKerasReLULayer(layer: ReLU): KerasLayer {
dtype = DATATYPE_FLOAT32,
max_value = layer.maxValue?.toDouble(),
negative_slope = layer.negativeSlope.toDouble(),
threshold = layer.threshold.toDouble()
threshold = layer.threshold.toDouble(),
trainable = layer.isTrainable
)
return KerasLayer(class_name = LAYER_RELU, config = configX)
}

private fun createKerasELULayer(layer: ELU): KerasLayer {
val configX = LayerConfig(
dtype = DATATYPE_FLOAT32,
alpha = layer.alpha.toDouble()
alpha = layer.alpha.toDouble(),
trainable = layer.isTrainable
)
return KerasLayer(class_name = LAYER_ELU, config = configX)
}
Expand Down