anilsathyan
I have a model with bilinear **upsample and instance norm** layers. It seems the latest pip package does not currently support these layers. How can i build/install latest code and...
I was trying to convert a pytorch model into keras via onnx. The pytorch model was successfully converted to onnx format. I tried two versions of the model: 1. Model...
Hi, what is the type of blur used here? Gaussian, Box or any other? What could be the opencv equivalent of the same?I tried to replicate the result with opencv...
It looks like a file 'deploy_samples.sh' is missing for testing in google colab. Also the upload widget is not working in colab.
I trained the model with duts dataset for 100 epochs(default) but the loss and accuracy seems to be low:- ``` INFO:root:AIM-Epoch[100/100](1/660) Lr:0.00010000 Loss:0.82403 Global:0.66851 Local:0.11801 Fusion-alpha:0.03752 Speed:4.63853s/iter Exa(h:m:s):00:50:56 INFO:root:AIM-Epoch[100/100](2/660) Lr:0.00010000...
Hey in you code depth multiplier value is 1 and width multiplier alpha can be configured and theoretically both seems to be different.If i change the depth multiplier value as...
I trained the SINet model on EG1800 and the baidu augmented datasets, using the default settings in the code. I tried both cross entropy and lovasz loss functions for training....
It seems TransposeConv + BN is not currently supported !!! Any plans to support this combination?? (Anyway this doesn't seem to be difficult to implement ...)
If I run image_demo.py the keypoint-coord values seems to be greater than 513 for the sample images of size 513? It seems, the scale is set to 1.0 by default...
Have you implemented custom XNOR Convolution Ops in Tensorflow ?. It seems the popcount operation is now supported by tensorflow(TF Issue Binary ops #1592)