Dena Bazazian

In the recent version of TensorFlow, you should replace these lines: > `summary = tf.Summary()` >`summary_value = summary.value.add()` >`summary_value.simple_value = value` >`summary_value.tag = graph_name` with: >`with self.writer.as_default():` >              ...

Thanks for your quick reply @hfawaz . I have installed the same tensorflow version (1.12.0) as you mentioned in [requirements](https://github.com/hfawaz/InceptionTime/blob/c9a323c789984e3fb56e82ebb4eea6438611e59c/requirements.txt). I don't think if the problem is related to the...

@bryandlee Many thanks for your reply. I have tried to use the [projector](https://github.com/rosinality/stylegan2-pytorch/blob/master/projector.py) code from StyleGAN2. But, the `latent_in` from that [code](https://github.com/rosinality/stylegan2-pytorch/blob/master/projector.py) is aligned with the generated projected image of...

Yes, the projector code generates the closest projection of a given input image, and the problem is that in most of the cases the view-point and some features of the...

`k_n` stands for the number of neighbors, so you should define this parameter based on the density of your point cloud. If your point cloud is very dense, then your...

@Harsha-Musunuri could you resolve this issue? I face the same problem, tensorflow1.14 is not compatible with CUDA10.2. Also, pytorch1.3 is not compatible with gcc>5 and CUDA10.2. But, the `convert_weight.py` code...

> I have used pytorch 1.3.1, CUDA 10.2. It seems like that pytorch version is crucial. (See #1) @rosinality pytorch 1.3 is not compatible with CUDA 10.2, did you install...

I have the same problem. I've tried to run the `convert_weight.py` several times with `pytorch 1.3`, `pytorch 1.4`, `pytorch 1.7`, and also `gcc 5.2`, and `gcc 4.8`, `gcc 7.3`, but...

It's weird, because I always get: `Test :: test acc: 0.926661, test **avg acc: 0.889669**` Since I am using exactly the same hyper-parameters and the same model, I am just...