Why to compute depth predict resultt is different from your paper ablation experiment?

`def safe_log10(x, eps=1e-10):
result = np.where(x > eps, x, -10)
np.log10(result, out=result, where=result > 0)
return result

def safe_log(x, eps=1e-5):
return np.log(x+eps)

def calculate(gt, pred):
if gt.shape[0] == 0:
return np.nan, np.nan, np.nan, np.nan, np.nan, np.nan

#thresh = np.maximum((gt / pred), (pred / gt))
#a1 = (thresh < 1.25).mean()
#a2 = (thresh < 1.25 ** 2).mean()
#a3 = (thresh < 1.25 ** 3).mean()

# abs_rel absolute relative error
abs_rel = np.mean(np.divide(np.abs(gt - pred),  gt, out=np.zeros_like(pred), where=gt!=0))
sq_rel = np.mean(np.divide(((gt - pred) ** 2), gt, out=np.zeros_like(pred), where=gt!=0))

rmse = (gt - pred) ** 2
rmse = np.sqrt(rmse.mean())

rmse_log = (safe_log(gt) - safe_log(pred)) ** 2
rmse_log = np.sqrt(rmse_log.mean())

# to compute SILog metric
err = safe_log(pred) - safe_log(gt)

silog = np.sqrt(np.mean(err ** 2) - np.mean(err) ** 2) * 100
if np.isnan(silog):
    silog = 0

log_10 = (np.abs(safe_log10(gt) - safe_log10(pred))).mean()
logger.info('abs_rel: {}\t rmse: {}\t log_10: {}\t rmse_log: {}\t silog: {}\t sq_rel: {}\t'.format(abs_rel, rmse, log_10, rmse_log, silog, sq_rel))
return [abs_rel, rmse, log_10, rmse_log, silog, sq_rel]

`

` def eval_step(self, batch, batch_idx, prefix: str):
(sweep_imgs, mats, _, img_metas, _, gt_labels, depth_labels) = batch
#(sweep_imgs, mats, _, img_metas, _, _) = batch
if torch.cuda.is_available():
for key, value in mats.items():
mats[key] = value.cuda()
sweep_imgs = sweep_imgs.cuda()
gt_labels = [gt_label.cuda() for gt_label in gt_labels]
preds, depth_preds = self.model(sweep_imgs, mats)
if len(depth_labels.shape) == 5:
depth_labels = depth_labels[:, 0, ...]

    depth_labels = self.get_downsampled_gt_depth(depth_labels.cuda())
    depth_preds = depth_preds.permute(0, 2, 3, 1).contiguous().view(-1, self.depth_channels)
    fg_mask = torch.max(depth_labels, dim=1).values > 0.0
    depth_result = calculate(depth_labels[fg_mask].cpu().numpy(), np.round(depth_preds[fg_mask].cpu().numpy(), 2))
    if isinstance(self.model, torch.nn.parallel.DistributedDataParallel):
        results = self.model.module.get_bboxes(preds, img_metas)
    else:
        results = self.model.get_bboxes(preds, img_metas)
    for i in range(len(results)):
        results[i][0] = results[i][0].tensor.detach().cpu().numpy()
        results[i][1] = results[i][1].detach().cpu().numpy()
        results[i][2] = results[i][2].detach().cpu().numpy()
        results[i].append(img_metas[i])
    return results`

The following result is different from your paper ablation experiment with your pretrained bev_depth_lss_r50_256x704_128x128_20e_cbgs_2key_da.pth weight.

Start with the calculate function and eval_step shown in the issue, then reproduce the evaluation using bev_depth_lss_r50_256x704_128x128_20e_cbgs_2key_da.pth. Compare the computed depth metrics with the paper's ablation result and identify the reproducible source of the discrepancy; done means the difference is explained and the evaluation result is consistent or documented.