src/region_layer.c
@@ -409,6 +409,7 @@ cuda_pull_array(state.truth, truth_cpu, num_truth); } cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs); cudaStreamSynchronize(get_cuda_stream()); network_state cpu_state = state; cpu_state.train = state.train; cpu_state.truth = truth_cpu; @@ -418,6 +419,7 @@ free(cpu_state.input); if(!state.train) return; cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs); cudaStreamSynchronize(get_cuda_stream()); if(cpu_state.truth) free(cpu_state.truth); }