Caffe to coreml coremltool3.0b

[ywang370]

================= Starting Conversion from Caffe to CoreML ======================
Layer 0: Type: 'Python', Name: 'data'. Output(s): 'data', 'mask', 'label'.
WARNING: Skipping training related layer 'data' of type 'Python'.
Layer 1: Type: 'Concat', Name: 'concat'. Input(s): 'data', 'mask'. Output(s): 'data_all'.
Layer 2: Type: 'Convolution', Name: 'conv0'. Input(s): 'data_all'. Output(s): 'conv0'.
python(76428,0x112c4e5c0) malloc: *** error for object 0x7fb46b550228: pointer being freed was not allocated
python(76428,0x112c4e5c0) malloc: *** set a breakpoint in malloc_error_break to debug
Abort trap: 6

Not sure how to get the error:
deploy.prototxt at the first layer:
input: "data"
input_dim: 1
input_dim: 3
input_dim: 512
input_dim: 512

input: "mask"
input_dim: 1
input_dim: 1
input_dim: 512
input_dim: 512

layer {
name: "concat"
bottom: "data"
bottom: "mask"
top: "data_all"
type: "Concat"
concat_param {
axis: 1
}
}

layer {
name: "conv0"
type: "Convolution"
bottom: "data_all"
top: "conv0"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 4
stride: 2
pad: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}

[aseemw]

Is the error specific to coremltools 3.0b3? Does it also happen with coremltools 2.1?

[TobyRoseman]

With the release of coremltools 5.0 the caffe converter has been removed.