def learn1():
num_epochs = 1
batch_size = 50
learning_rate = 0.001
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(100, activation=tf.nn.relu),
tf.keras.layers.Dense(10),
tf.keras.layers.Softmax()
])
data_loader = MNISTLoader()
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=[tf.keras.metrics.sparse_categorical_accuracy])
model.fit(data_loader.train_data,
data_loader.train_label,
epochs=num_epochs,
batch_size=batch_size)
tf.saved_model.save(model, "saved/1")
import json
import numpy as np
import requests
from zh.model.utils import MNISTLoader
data_loader = MNISTLoader()
data = json.dumps({"instances": data_loader.test_data[0:3].tolist()})
headers = {"content-type": "application/json"}
json_response = requests.post('http://localhost:8501/v1/models/MLP:predict',
data=data,
headers=headers)
predictions = np.array(json.loads(json_response.text)['predictions'])
print(np.argmax(predictions, axis=-1))
print(data_loader.test_label[0:10])
x = tf.keras.layers.MaxPool2D(pool_size=[2, 2], strides=2)(x)
x = tf.keras.layers.Conv2D(filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)(x)
x = tf.keras.layers.MaxPool2D(pool_size=[2, 2], strides=2)(x)
x = tf.keras.layers.Reshape(target_shape=(7 * 7 * 64, ))(x)
x = tf.keras.layers.Dense(units=1024, activation=tf.nn.relu)(x)
x = tf.keras.layers.Dense(units=10)(x)
outputs = tf.keras.layers.Softmax()(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
if mode == 'subclassing':
from zh.model.mnist.cnn import CNN
model = CNN()
data_loader = MNISTLoader()
if training_loop == 'keras':
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=[tf.keras.metrics.sparse_categorical_accuracy])
model.fit(data_loader.train_data,
data_loader.train_label,
epochs=num_epochs,
batch_size=batch_size)
print(model.evaluate(data_loader.test_data, data_loader.test_label))
if training_loop == 'custom':
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
num_batches = int(data_loader.num_train_data // batch_size * num_epochs)
for batch_index in range(num_batches):
X, y = data_loader.get_batch(batch_size)
with tf.GradientTape() as tape: