def test():
model_to_be_restored = MLP()
checkpoint = tf.train.Checkpoint(
myAwesomeModel=model_to_be_restored
) # 实例化Checkpoint，设置恢复对象为新建立的模型model_to_be_restored
checkpoint.restore(tf.train.latest_checkpoint('./save')) # 从文件恢复模型参数
num_eval_samples = np.shape(data_loader.eval_labels)[0]
y_pred = model_to_be_restored.predict(tf.constant(
data_loader.eval_data)).numpy()
print("test accuracy: %f" %
(sum(y_pred == data_loader.eval_labels) / num_eval_samples))
def test():
model_to_be_restored = MLP()
checkpoint = tf.train.Checkpoint(
myAwesomeModel=model_to_be_restored
) # instantiate a Checkpoint, set newly initialized model `model_to_be_restored` to be the object to be restored
checkpoint.restore(tf.train.latest_checkpoint(
'./save')) # restore parameters of model from file
num_eval_samples = np.shape(data_loader.eval_labels)[0]
y_pred = model_to_be_restored.predict(tf.constant(
data_loader.eval_data)).numpy()
print("test accuracy: %f" %
(sum(y_pred == data_loader.eval_labels) / num_eval_samples))
else:
model = CNN()
data_loader = DataLoader()
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
for batch_index in range(num_batches):
X, y = data_loader.get_batch(batch_size)
with tf.GradientTape() as tape:
y_logit_pred = model(tf.convert_to_tensor(X))
loss = tf.losses.sparse_softmax_cross_entropy(labels=y,
logits=y_logit_pred)
print("batch %d: loss %f" % (batch_index, loss.numpy()))
grads = tape.gradient(loss, model.variables)
optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))
num_eval_samples = np.shape(data_loader.eval_labels)[0]
y_pred = model.predict(data_loader.eval_data).numpy()
print("test accuracy: %f" %
(sum(y_pred == data_loader.eval_labels) / num_eval_samples))
num_correct_pred = 0
for batch_index in range(num_eval_samples // batch_size):
y_pred = model.predict(
data_loader.eval_data[batch_index * batch_size:(batch_index + 1) *
batch_size]).numpy()
num_correct_pred += sum(
y_pred == data_loader.eval_labels[batch_index *
batch_size:(batch_index + 1) *
batch_size])
print("test accuracy: %f" %
(num_correct_pred / np.shape(data_loader.eval_labels)[0]))