kingofstu

Results 16 issues of kingofstu

您好,首先很高兴你们能有这样伟大的工作!其次,我想提两个问题: 1、在BevFormer的decoder中: query_pos, query = torch.split( object_query_embed, self.embed_dims, dim=1) # [900,256], [900,256] query_pos = query_pos.unsqueeze(0).expand(bs, -1, -1) query = query.unsqueeze(0).expand(bs, -1, -1) # [B,900,256] reference_points = self.reference_points(query_pos) # linear [B,900,3]...

hi,how can i see the original code of voxel_pooling_train?

很高兴你们作出这样的工作,我在看文章时看到When using the default settings of LSS on the nuScenes dataset, only 50% of the grids can receive valid image features through projection,可否告知这个50%是怎么推算出来的?

作者您好,我有两个疑问希望可以被解答 1、我看到sparsebev_sampling的代码中并未使用valid_mask,也就是说sample_points_cam中是存在投影不到相机平面的3d reference_points的,这样采样的时候不会有影响吗?padding会填充0对吗? 2、使用i_view[..., None].float() / (N - 1)拼接到sample_points_cam是因为each muvl_feats:[B*T*G, N, C, H, W]是5-D tensor,因此要cat相机索引到采样点中然后进行采样吗?那如果将each muvl_feats变为[B*T*G*N, C, H, W]是不是可以直接用4-D tensor了呢? 源码: i_view = torch.argmax(valid_mask, dim=-1)[..., None] # [B, T, Q,...

time_diff = img_metas[0]['time_diff'] # [B, F] if time_diff.shape[1] > 1: time_diff = time_diff.clone() time_diff[time_diff < 1e-5] = 1.0 bbox_pred[..., 8:] = bbox_pred[..., 8:] / time_diff[:, 1:2, None] 您好,可否告知一下/ time_diff[:, 1:2,...

Hi,when I use nuscenes_infos_temporal_test.pkl to run test.py, it occured: AssertionError: Error: You are trying to evaluate on the test set but you do not have the annotations! How can I...

您好,请问将来会公开FB-BEV作3D检测的code和config吗?

您好,我使用bevdet-r50.py训练出来的权重文件有ema版的和不是ema版的: epoch_24_ema.pth、epoch_24.pth 在验证集上test的结果分别是 mAP: 0.2925 NDS: 0.3667 和 mAP: 0.2654 NDS: 0.3381 不过我训练完24轮总loss比您的高1.3578 - 1.3211 = 0.367 我想问您公布的mAP: 0.2828 NDS: 0.3500的结果使用的是训练第几轮的权重文件,是否带ema策略?

query_bbox初始化时xy坐标是做了归一化: grid_size = int(math.sqrt(self.num_query)) # 900 assert grid_size * grid_size == self.num_query x = y = torch.arange(grid_size) # 30,30 xx, yy = torch.meshgrid(x, y, indexing='ij') # [0, grid_size - 1]...

您好,sampling_offset体现在3D sampling_points,而不是像BEVFormer那样体现在ref_2d上,是怎么考虑的呢?