Skip to content

Support dynamic and 3D instanceNormalization#515

Merged
kevinch-nv merged 1 commit intoonnx:masterfrom
kevinch-nv:dynamic-instancenorm
Aug 12, 2020
Merged

Support dynamic and 3D instanceNormalization#515
kevinch-nv merged 1 commit intoonnx:masterfrom
kevinch-nv:dynamic-instancenorm

Conversation

@kevinch-nv
Copy link
Copy Markdown
Collaborator

Signed-off-by: Kevin Chen kevinch@nvidia.com

@kevinch-nv kevinch-nv merged commit 088554a into onnx:master Aug 12, 2020
@kevinch-nv kevinch-nv deleted the dynamic-instancenorm branch August 12, 2020 23:01
kevinch-nv added a commit that referenced this pull request Oct 20, 2020
* Prefix logging messages with [TRT] (#497)

* Add local build instructions (#498)

* fix duplicate layer names bug (#446) (#467)

Suppose we have a network with (not all distinct) layer names

layer
layer_1
layer

When ImporterContext sees "layer", it sees it's not in mLayerNameCounts,
and sets mLayerNameCounts["layer"] = 1 and adds a TRT layer with name "layer".
It then sees "layer_1", concludes it's not in mLayerNameCounts, so it sets
mLayerNameCounts["layer_1"] = 1 and adds a TRT layer with name "layer_1".
NOW when it sees "layer", it sees that mLayerNameCounts["layer"] == 1,
so we produce a "uniqueName" of
"layer" + "_" + std::to_string(mLayerNameCounts["layer"] ), ie "layer_1",
which is a name conflict for the TRT net.

This change keeps track of all inserted names in a set and in the case of
duplicates, tries suffix-appended modifications of the duplicated name
by ever increasing integers until a name appears which has not been used.

* Support Dynamic and 3D instanceNormalization (#515)

* Add restrictions on multi-input convolutions (#521)

* Update resize limitations in TensorRT (#538)

Signed-off-by: Kevin Chen <kevinch@nvidia.com>

Co-authored-by: Thomas Peters <thomas.d.peters@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant