Check failed: MaxBottomBlobs() >= bottom.size() (2 vs. 3) L1Loss Layer takes at most 2 bottom blob(s) as input. about unsupervised-adaptation-for-deep-stereo HOT 2 OPEN

Dear sir, in train.prototxt about line 1670, there are three bottom input:

  name: "flow_loss1"
  type: "L1Loss"
  #bottom: "predict_flow1"
  bottom: "blob66"
  bottom: "blob65"
  bottom: "blob65Confidence"
  top: "flow_loss1"
  loss_weight: 1
  l1_loss_param {
    l2_per_location: false
    normalize_by_num_entries: true
  }
}

When bottom: "blob65" was commented, the error about MaxBottomBlobs() >= bottom.size() (2 vs. 3) L1Loss Layer takes at most 2 bottom blob(s) as input. #6is solved.

  name: "flow_loss1"
  type: "L1Loss"
  #bottom: "predict_flow1"
  bottom: "blob66"
  #bottom: "blob65"
  bottom: "blob65Confidence"
  top: "flow_loss1"
  loss_weight: 1
  l1_loss_param {
    l2_per_location: false
    normalize_by_num_entries: true
  }
}

Can you give me some suggestion about how to change flow_loss1 layer? Thanks.

from unsupervised-adaptation-for-deep-stereo.

Are you sure to be using our implementation of L1Loss layer? One of the difference between our code and the original flownet one is indeed the number of bottom blob allowed.

from unsupervised-adaptation-for-deep-stereo.