MCPcopy Create free account
hub / github.com/coperception/star / infer_vae_completion

Method infer_vae_completion

star/utils/CoModule.py:183–190  ·  view source on GitHub ↗
(self, data, batch_size, loss_fn='ce', trainable=False)

Source from the content-addressed store, hash-verified

181 return loss.item(), result, ind_recon, perplexity.detach()
182
183 def infer_vae_completion(self, data, batch_size, loss_fn='ce', trainable=False):
184 bev_seq = data['bev_seq']
185 trans_matrices = data['trans_matrices']
186 num_agent = data['num_agent']
187
188 vq_loss, result, ind_recon = self.model(bev_seq, trans_matrices, num_agent, batch_size=batch_size)
189
190 return result
191
192 # Used by VQ STAR model in scene completion, added by Juexiao
193 def step_vqstar_completion(self, data, batch_size, mask_ratio, loss_fn='mse', trainable = False):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected