AICS-Course icon indicating copy to clipboard operation
AICS-Course copied to clipboard

《智能计算系统 AI Computing Systems》习题答案、实验答案、课程笔记

Results 3 AICS-Course issues
Sort by recently updated
recently updated
newest added

一个是您确实写了保存最优参数,但是似乎没有用起来,修改一下main_exp_2_1.py就可以(参数保存名字改为best.npy) ``` if __name__ == '__main__': mlp = build_mnist_mlp() evaluate(mlp) mlp.load_model('best.npy') evaluate(mlp) ``` 另外一个是我对main_exp_2_1.py里面的evaluate的检测剩余批次的代码有些疑惑 其中的 last_batch = mlp.test_data.shape[0]/mlp.batch_size*mlp.batch_size 是否应该改为 last_batch = mlp.test_data.shape[0] % mlp.batch_size ``` def evaluate(mlp): pred_results = np.zeros([mlp.test_data.shape[0]])...