8f74f45d3a17b6f53d11516df43062f5a69381b4,examples/basic_tutorials/4_mnist_mlp_eager_mode_dynamic.py,,,#,48

Before Change

        train_loss, train_acc, n_iter = 0, 0, 0
        for X_batch, y_batch in tl.iterate.minibatches(X_train, y_train, batch_size, shuffle=False):
            _logits = MLP(X_batch, foo=1).outputs
            train_loss += tl.cost.cross_entropy(_logits, y_batch, name="eval_loss")
            train_acc += np.mean(np.equal(np.argmax(_logits, 1), y_batch))
            n_iter += 1
        print("   train foo=1 loss: {}".format(train_loss / n_iter))
        print("   train foo=1 acc:  {}".format(train_acc / n_iter))

After Change

        train_loss, train_acc, n_iter = 0, 0, 0
        for X_batch, y_batch in tl.iterate.minibatches(X_train, y_train, batch_size, shuffle=False):
            _logits = MLP(X_batch, foo=1)
            train_loss += tl.cost.cross_entropy(_logits, y_batch, name="eval_loss")
            train_acc += np.mean(np.equal(np.argmax(_logits, 1), y_batch))
            n_iter += 1
        print("   train foo=1 loss: {}".format(train_loss / n_iter))
        print("   train foo=1 acc:  {}".format(train_acc / n_iter))

Instances