im able to complete training,but at last epoch I'm getting below error, also for doing inference I'm again getting error, how can we fix this error
fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)
im able to complete training,but at last epoch I'm getting below error, also for doing inference I'm again getting error, how can we fix this error