understand_videobased_reid

understand_videobased_reid copied to clipboard

Hi I am trying to understand different methodologies and architecture to train video reid datasets. My question is that can you please tell me what are the best hyperparameters combination,...

FatimaZulfiqar

Some puzzled questions about details in realizing triplet loss

1

``` # Compute pairwise distance, replace by the official when merged dist = torch.pow(inputs, 2).sum(dim=1, keepdim=True).expand(n, n) dist = dist + dist.t() dist.addmm_(1, -2, inputs, inputs.t()) dist = dist.clamp(min=1e-12).sqrt() #...

swg209

sample_method dense mean all ?

8

`` elif self.sample == 'dense': """ Sample all frames in a video into a list of clips, each clip contains seq_len frames, batch_size needs to be set to 1. 将视频中的所有帧采样到一系列的clips，每个clip包含seq_len个帧,批次大小需要设置为1...

swg209

`# compute average precision 计算平均精度 # reference: https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Average_precision num_rel = orig_cmc.sum() # 所有元素求和 tmp_cmc = orig_cmc.cumsum() # 累加和,不改变数据形状 tmp_cmc = [x / (i+1.) for i, x in enumerate(tmp_cmc)] # enumerate()...

swg209