I am training my own coco like dataset of only two classes and i am getting this error.
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(0, conf_t.view(-1,1))
RuntimeError: Expected tensor [46480 x 1], src [46480 x 3] and index [46480 x 1] to have the same size apart from dimension 0 at /opt/conda/conda-bld/pytorch_1535491974311/work/aten/src/TH/generic/THTensorMath.cpp:620
I am training my own coco like dataset of only two classes and i am getting this error.
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(0, conf_t.view(-1,1)) RuntimeError: Expected tensor [46480 x 1], src [46480 x 3] and index [46480 x 1] to have the same size apart from dimension 0 at /opt/conda/conda-bld/pytorch_1535491974311/work/aten/src/TH/generic/THTensorMath.cpp:620