How to finetune on wider_face? & VOC fine-tuning colab error

[ArecaNon]

In the finetune example, the dataset name was changed to wider_face, and the label was not defined when proceeding, so the learning was not possible. Is there an example of finetuning with the wider_face dataset?

And even if you use the finetuning example of the given colab as it is `ValueError: in user code:

File "/home/vislab/Human_Pose_Estimation/capstone/pix2seq/data/dataset.py", line 111, in None  *
    lambda x: self.extract(x, training)
File "/home/vislab/Human_Pose_Estimation/capstone/pix2seq/test.py", line 53, in extract  *
    areas = tf.reshape(areas, [tf.shape(label)[0]])

ValueError: slice index 0 of dimension 0 out of bounds. for '{{node strided_slice}} = StridedSlice[Index=DT_INT32, T=DT_INT32, begin_mask=0, ellipsis_mask=0, end_mask=0, new_axis_mask=0, shrink_axis_mask=1](Shape, strided_slice/stack, strided_slice/stack_1, strided_slice/stack_2)' with input shapes: [0], [1], [1], [1] and with computed input tensors: input[1] = <0>, input[2] = <1>, input[3] = <1>.`

The following error does not work.