Open leosh64 opened 2 years ago
I was just about to report this as well!
For example, yolov5n.onnx looks like this for me:
This width is somewhat justifiable since the final layers of the model do indeed need the width, but there is no reason for the connections that go from a conv to the following mul to go all the way to the right and back.
Hello all, any news on this bug? I am facing the same issue as weel:
It seems the second pass (link) of the horizontalCompaction
function is related to this issue.
Tested with yolov5n.onnx.
With the second pass | Without the second pass |
---|---|
So my bet is everyone should edit the code to adjust the view when needed.
There was a change to make unnecessary wide edges become narrow. I assume there are still wide lines, and if so, please share the model to this issue.
@seanshpark
I assume there are still wide lines, and if so, please share the model to this issue.
I've just encountered the issue with EfficientDet-d0.onnx
file in EfficientDet-d0.onnx.zip so just letting you know it.
The file is listed in test/models.json
. link
I still haven't understood the root cause of this problem but applying the change somehow resolved it.
@beru thank you for investigating. I tried the change on a few files and noticed it changes the symmetry of squeezenet1.1.onnx.
@lutzroeder
I tried the change on a few files and noticed it changes the symmetry of squeezenet1.1.onnx.
Thank you for checking it. And... could you also please check this change? link Applying the change yields preferrable result with the EfficientDet-d0.onnx
model.
I've debugged around horizontalCompaction
function for a few days to find out why the problem appears on xss['dl']
. With the change, graphs built by buildBlockGraph
function contain less edges so it could be that clustering has improved? It's hard (for me) to explain relations of how the change improves layouting results due to lack of understanding.
Edited: This change is more easier to understand.
For some networks, the visualization of the graph becomes unnecessarily wide. This makes it difficult to understand connections when zoomed in:
Throughout the model, there is no section that would justify such a wide visualization.
Below some screenshots when zoomed out:
The same issue (unnecessarily high) occurs in horizontal mode: