triplet_loss = triplet_(ml_real_out,ml_real_out_shuffle,ml_fake_out_shuffle)

g_loss = p_dist + c_dist 

ml_real_out = netML(real_img) # real data
ml_fake_out = netML(fake_img) # generated data 

# shuffle in batch
r1=torch.randperm(batch_size)
r2=torch.randperm(batch_size)
ml_real_out_shuffle = ml_real_out[r1[:, None]].view(ml_real_out.shape[0],ml_real_out.shape[-1])
ml_fake_out_shuffle = ml_fake_out[r2[:, None]].view(ml_fake_out.shape[0],ml_fake_out.shape[-1])

# pairwise distances 
pd_r = pairwise_distances(ml_real_out, ml_real_out) 
pd_f = pairwise_distances(ml_fake_out, ml_fake_out)
 
# matching terms 
p_dist =  torch.dist(pd_r,pd_f,2) # matching 2-diameters             
c_dist = torch.dist(ml_real_out.mean(0),ml_fake_out.mean(0),2) # matching centroids  

python train.py

@misc{daiandhang2021manifold,
      title={Manifold Matching via Deep Metric Learning for Generative Modeling}, 
      author={Mengyu Dai and Haibin Hang},
      year={2021},
      eprint={2106.10777},
      archivePrefix={arXiv}
}