Python cntk.element_times() Examples

The following are 7 code examples of cntk.element_times(). 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 cntk , or try the search function .
Example #1
Source File: cntk_smoothL1_loss.py    From cntk-python-web-service-on-azure with MIT License 6 votes vote down vote up 
def SmoothL1Loss(sigma, bbox_pred, bbox_targets, bbox_inside_weights, bbox_outside_weights):
    """
        From https://github.com/smallcorgi/Faster-RCNN_TF/blob/master/lib/fast_rcnn/train.py

        ResultLoss = outside_weights * SmoothL1(inside_weights * (bbox_pred - bbox_targets))
        SmoothL1(x) = 0.5 * (sigma * x)^2,    if |x| < 1 / sigma^2
                        |x| - 0.5 / sigma^2,    otherwise
    """
    sigma2 = sigma * sigma

    inside_mul_abs = C.abs(C.element_times(bbox_inside_weights, C.minus(bbox_pred, bbox_targets)))

    smooth_l1_sign = C.less(inside_mul_abs, 1.0 / sigma2)
    smooth_l1_option1 = C.element_times(C.element_times(inside_mul_abs, inside_mul_abs), 0.5 * sigma2)
    smooth_l1_option2 = C.minus(inside_mul_abs, 0.5 / sigma2)
    smooth_l1_result = C.plus(C.element_times(smooth_l1_option1, smooth_l1_sign),
                              C.element_times(smooth_l1_option2, C.minus(1.0, smooth_l1_sign)))

    return C.element_times(bbox_outside_weights, smooth_l1_result)
Example #2
Source File: cntk_smoothL1_loss.py    From raster-deep-learning with Apache License 2.0 6 votes vote down vote up 
def SmoothL1Loss(sigma, bbox_pred, bbox_targets, bbox_inside_weights, bbox_outside_weights):
    """
        From https://github.com/smallcorgi/Faster-RCNN_TF/blob/master/lib/fast_rcnn/train.py

        ResultLoss = outside_weights * SmoothL1(inside_weights * (bbox_pred - bbox_targets))
        SmoothL1(x) = 0.5 * (sigma * x)^2,    if |x| < 1 / sigma^2
                        |x| - 0.5 / sigma^2,    otherwise
    """
    sigma2 = sigma * sigma

    inside_mul_abs = C.abs(C.element_times(bbox_inside_weights, C.minus(bbox_pred, bbox_targets)))

    smooth_l1_sign = C.less(inside_mul_abs, 1.0 / sigma2)
    smooth_l1_option1 = C.element_times(C.element_times(inside_mul_abs, inside_mul_abs), 0.5 * sigma2)
    smooth_l1_option2 = C.minus(inside_mul_abs, 0.5 / sigma2)
    smooth_l1_result = C.plus(C.element_times(smooth_l1_option1, smooth_l1_sign),
                              C.element_times(smooth_l1_option2, C.minus(1.0, smooth_l1_sign)))

    return C.element_times(bbox_outside_weights, smooth_l1_result)
Example #3
Source File: cntk_smoothL1_loss.py    From cntk-hotel-pictures-classificator with MIT License 6 votes vote down vote up 
def SmoothL1Loss(sigma, bbox_pred, bbox_targets, bbox_inside_weights, bbox_outside_weights):
    """
        From https://github.com/smallcorgi/Faster-RCNN_TF/blob/master/lib/fast_rcnn/train.py

        ResultLoss = outside_weights * SmoothL1(inside_weights * (bbox_pred - bbox_targets))
        SmoothL1(x) = 0.5 * (sigma * x)^2,    if |x| < 1 / sigma^2
                        |x| - 0.5 / sigma^2,    otherwise
    """
    sigma2 = sigma * sigma

    inside_mul_abs = C.abs(C.element_times(bbox_inside_weights, C.minus(bbox_pred, bbox_targets)))

    smooth_l1_sign = C.less(inside_mul_abs, 1.0 / sigma2)
    smooth_l1_option1 = C.element_times(C.element_times(inside_mul_abs, inside_mul_abs), 0.5 * sigma2)
    smooth_l1_option2 = C.minus(inside_mul_abs, 0.5 / sigma2)
    smooth_l1_result = C.plus(C.element_times(smooth_l1_option1, smooth_l1_sign),
                              C.element_times(smooth_l1_option2, C.minus(1.0, smooth_l1_sign)))

    return C.element_times(bbox_outside_weights, smooth_l1_result)
Example #4
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_element_times_1():
    cntk_op = C.element_times([1, 2, 3], [4, 5, 6])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equal(cntk_ret, ng_ret)
Example #5
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_element_times_2():
    cntk_op = C.element_times([[1, 2, 3], [4, 5, 6]], [7, 8, 9])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equal(cntk_ret, ng_ret)
Example #6
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_element_times_3():
    cntk_op = C.element_times([1, 2, 3], [[4, 5, 6], [7, 8, 9]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equal(cntk_ret, ng_ret)
Example #7
Source File: train_end2end.py    From end2end_AU_speech with MIT License 5 votes vote down vote up 
def std_normalized_l2_loss(output, target):
    std_inv = np.array([6.6864805402, 5.2904440280, 3.7165409939, 4.1421640454, 8.1537399389, 7.0312877415, 2.6712380967,
                        2.6372177876, 8.4253649884, 6.7482162880, 9.0849960354, 10.2624412692, 3.1325531319, 3.1091179819,
                        2.7337937590, 2.7336441031, 4.3542467871, 5.4896293687, 6.2003761588, 3.1290341469, 5.7677042738,
                        11.5460919611, 9.9926451700, 5.4259818848, 20.5060642486, 4.7692101480, 3.1681517575, 3.8582905289,
                        3.4222250436, 4.6828286809, 3.0070785113, 2.8936539301, 4.0649030157, 25.3068458731, 6.0030623160,
                        3.1151977458, 7.7773542649, 6.2057372469, 9.9494258692, 4.6865422850, 5.3300697628, 2.7722027974,
                        4.0658663003, 18.1101618617, 3.5390113731, 2.7794520068], dtype=np.float32)
    weights = C.constant(value=std_inv) #.reshape((1, label_dim)))
    dif = output - target
    ret = C.reduce_mean(C.square(C.element_times(dif, weights)))
    return ret