vgg4resnet

``` def infer_facepic(self): ''' faces : list of PIL Image target_embs : [n, 512] computed embeddings of faces in facebank names : recorded names of faces in facebank tta :...

``` def fpnpredictonline(self, img: np.ndarray, mask: Optional[np.ndarray], ignore_mask=True) -> np.ndarray: (img, mask), h, w = self._preprocess(img, mask) with torch.no_grad(): inputs = [img.cuda()] if not ignore_mask: inputs += [mask] import pdb...

adding the loss to net work G'loss ``` def _run_epoch(self, epoch): self.metric_counter.clear() for param_group in self.optimizer_G.param_groups: lr = param_group['lr'] epoch_size = config.get('train_batches_per_epoch') or len(self.train_dataset) tq = tqdm.tqdm(self.train_dataset, total=epoch_size) tq.set_description('Epoch {},...

I want to know how to decrea the self.lossReAutoGrad （the face recognition assuming name is the loss A ），and I wonder my way of adding the lossA to the lossD...

anyone can help me？

@KupynOrest @t-martyniuk can you help me ，or give me some cues？

yes, when the C++ version will be release

I have the same question ! I search in your code and the demo , but I can not find where pose.txt comes from ,can u simply tell us how...

yes ,thank u so much, @kingsman142 @andyzeng I have find some code to obtain pose from the following project,but i dont know which one is better,I also have some questions...

@kingsman142 ok ，anyway ， thanks very much ，the BA I mean the bundle ajustment