水木清扬

摘要： total_num = sum(p.numel() for p in model.parameters()) trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad) print('Total ',to 阅读全文

摘要： #统计caffe算模型的参数量 from numpy import prod, sum flops = 0 typenames = ['Convolution', 'BatchNorm'] for layer_name, blob in net.blobs.iteritems(): if layer 阅读全文