tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [1,8732,4] vs. [1,10,0]
[[node compute/sub_1 (defined at /losses/smooth_l1_loss.py:22) ]] [Op:__inference_train_function_6041]
Errors may have originated from an input operation.
Input Source operations connected to node compute/sub_1:
compute/strided_slice_2 (defined at /losses/ssd_loss.py:43)
compute/strided_slice_3 (defined at /losses/ssd_loss.py:44)
当我在一个类上使用 vgg16 火车和来自这个 github（https://github.com/Socret360/object-detection-in-keras）的 SSD 编译代码时，我遇到了 SSD 损失函数的问题。问题来自这两行：
bbox_true = y_true[:, :, -12:-8]
bbox_pred = y_pred[:, :, -12:-8]
因此，如果有人对问题有所了解，那将非常有帮助