Python numpy.repeate() Examples

The following are 23 code examples of numpy.repeate(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module numpy , or try the search function .
Example #1
Source File: model.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #2
Source File: model.py    From SketchyScene with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #3
Source File: model.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #4
Source File: model_resnet_v2.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #5
Source File: model_resnext.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #6
Source File: model_resnext_v2.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #7
Source File: model_seresnext.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #8
Source File: model.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #9
Source File: model.py    From PyTorch-Luna16 with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #10
Source File: MaskRCNN.py    From PyTorch-Luna16 with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #11
Source File: model.py    From latte with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #12
Source File: Model.py    From Keras-RFCN with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #13
Source File: model_utils.py    From medicaldetectiontoolkit with Apache License 2.0 5 votes vote down vote up 
def bbox_overlaps_2D(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)
    return overlaps
Example #14
Source File: model_mod_mpan.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #15
Source File: model_mod_rgb.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #16
Source File: model.py    From decentralized_AI with GNU General Public License v2.0 5 votes vote down vote up 
def bbox_overlaps(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)

    return overlaps
Example #17
Source File: model.py    From deep-learning-explorer with Apache License 2.0 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #18
Source File: model.py    From DeepTL-Lane-Change-Classification with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #19
Source File: model_utils.py    From RegRCNN with Apache License 2.0 5 votes vote down vote up 
def bbox_overlaps_3D(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2, z1, z2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,6)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2, b1_z1, b1_z2 = boxes1.chunk(6, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2, b2_z1, b2_z2 = boxes2.chunk(6, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    z1 = torch.max(b1_z1, b2_z1)[:, 0]
    z2 = torch.min(b1_z2, b2_z2)[:, 0]
    zeros = torch.zeros(y1.size()[0], requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros) * torch.max(z2 - z1, zeros)

    # 3. Compute unions
    b1_volume = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)  * (b1_z2 - b1_z1)
    b2_volume = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)  * (b2_z2 - b2_z1)
    union = b1_volume[:,0] + b2_volume[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)
    return overlaps
Example #20
Source File: model_utils.py    From RegRCNN with Apache License 2.0 5 votes vote down vote up 
def bbox_overlaps_2D(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.

    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]

    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,4)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = boxes1.chunk(4, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = boxes2.chunk(4, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    #--> expects x1<x2 & y1<y2
    zeros = torch.zeros(y1.size()[0], requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros)

    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area[:,0] + b2_area[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    assert torch.all(iou<=1), "iou score>1 produced in bbox_overlaps_2D"
    overlaps = iou.view(boxes2_repeat, boxes1_repeat) #--> per gt box: ious of all proposal boxes with that gt box

    return overlaps
Example #21
Source File: model.py    From Mask-RCNN-Pedestrian-Detection with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #22
Source File: model.py    From segmentation-unet-maskrcnn with MIT License 5 votes vote down vote up 
def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps
Example #23
Source File: model_utils.py    From medicaldetectiontoolkit with Apache License 2.0 5 votes vote down vote up 
def bbox_overlaps_3D(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2, z1, z2)].
    """
    # 1. Tile boxes2 and repeate boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeate() so simulate it
    # using tf.tile() and tf.reshape.
    boxes1_repeat = boxes2.size()[0]
    boxes2_repeat = boxes1.size()[0]
    boxes1 = boxes1.repeat(1,boxes1_repeat).view(-1,6)
    boxes2 = boxes2.repeat(boxes2_repeat,1)

    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2, b1_z1, b1_z2 = boxes1.chunk(6, dim=1)
    b2_y1, b2_x1, b2_y2, b2_x2, b2_z1, b2_z2 = boxes2.chunk(6, dim=1)
    y1 = torch.max(b1_y1, b2_y1)[:, 0]
    x1 = torch.max(b1_x1, b2_x1)[:, 0]
    y2 = torch.min(b1_y2, b2_y2)[:, 0]
    x2 = torch.min(b1_x2, b2_x2)[:, 0]
    z1 = torch.max(b1_z1, b2_z1)[:, 0]
    z2 = torch.min(b1_z2, b2_z2)[:, 0]
    zeros = Variable(torch.zeros(y1.size()[0]), requires_grad=False)
    if y1.is_cuda:
        zeros = zeros.cuda()
    intersection = torch.max(x2 - x1, zeros) * torch.max(y2 - y1, zeros) * torch.max(z2 - z1, zeros)

    # 3. Compute unions
    b1_volume = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)  * (b1_z2 - b1_z1)
    b2_volume = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)  * (b2_z2 - b2_z1)
    union = b1_volume[:,0] + b2_volume[:,0] - intersection

    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = iou.view(boxes2_repeat, boxes1_repeat)
    return overlaps