Mritula Chandrasekaran

ImportError: cannot import name 'BatchNormalization' from 'keras.layers.normalization'

1

Hi, I kept getting the below error when trying to execute dcgan.py file, when trying to execute in Colab `ImportError: cannot import name 'BatchNormalization' from 'keras.layers.normalization' ` To over come...

Python error 'int' object has no attribute 'shape'

1

I kept getting an error " Python error 'int' object has no attribute 'shape'" reflecting to the following line from def train in the dcgan.py file `g_loss = d_on_g.train_on_batch(noise, [1]...

HI, I am keen to implement ST-GCN for my Dataset. I have 3D keypoints extracted from my dataset. Can you kindly brief me on how can I do it? If...

Hi, As Python 2 cannot be used with COLAB I am getting the following errors: Can someone please let e know how to overcome it? Thanks In advance! `WARNING:tensorflow:Entity could...

Input data

1

Hi, Thanks for the interesting work. I am trying to implement your work and learn. I have got the NTU-RGBD 3D skeleton data downloaded. It's with extension .skeleton. Can you...

Error not able to visualize results

1

Hi, I am getting the following error when I try to run the demo and visualize: Instructions for updating: Use tf.cast instead. train_dir experiments\All\dropout_0.5\epochs_1\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17 Could not find checkpoint. Aborting. Traceback...

ValueError, "Checkpoint {0} does not seem to exist".format( ckpt.model_checkpoint_path ) )

1

Hi, Thanks for the code!! I am trying to reproduce your results and get the hold of 3D reconstruction. I am getting the following error when I tried to first...

Can this work on windows?

1

Hi, Just want to check if I can work on windows and still use ordinal-pose3d. Thanks, Mritula

Hi, Can you kindly add a file of raw data and preprocessed data, please? When I am trying to download from the above-mentioned URL, it errors out. I am trying...

Hi, Can someone clarify why and how the n values are generated? Also, whats the purpose of using windowsize `window=384 n = ((np.where(np.any(dataxy, axis=1))[0][-1] + 1) // window) * window`