l2_reg = 1e-3
learning_rate = 25
epochs = 5000
epoch0 = 10
epoch1 = 1000
target = 76
MEAN = np.float32([0.485, 0.456, 0.406])
STD = np.float32([0.229, 0.224, 0.225])
SAVE_PATH = "cs231n/datasets/squeezenet.ckpt"
if not os.path.exists(SAVE_PATH + ".index"):
raise ValueError("You need to download SqueezeNet!")
model = SqueezeNet()
model.load_weights(SAVE_PATH)
model.trainable = False
X = 255 * np.random.rand(224, 224, 3)
X = process(X)
X = X[None]
X = tf.Variable(X)
for _ in range(epochs):
with tf.GradientTape() as tape:
tape.watch(X)
loss = model(X)[0, target] - l2_reg * tf.nn.l2_loss(X)
dX = tape.gradient(loss, X)
X.assign_add(dX[0] * learning_rate)
X.assign(clip(X))
if _ % epoch0 == 0:
# for auto-reloading external modules
# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython
#%load_ext autoreload
#%autoreload 2
#%% Load the pretrained model.
# this model is downloaded from here "http://cs231n.stanford.edu/squeezenet_tf2.zip"
SAVE_PATH = 'cs231n/datasets/squeezenet.ckpt'
if not os.path.exists(SAVE_PATH + ".index"):
raise ValueError("You need to download SqueezeNet!")
model = SqueezeNet()
status = model.load_weights(SAVE_PATH)
model.trainable = False
#%% Load some ImageNet images
from cs231n.data_utils import load_imagenet_val
X_raw, y, class_names = load_imagenet_val(num=5)
plt.figure(figsize=(12, 6))
for i in range(5):
plt.subplot(1, 5, i + 1)
plt.imshow(X_raw[i])
plt.title(class_names[y[i]])
plt.axis('off')
plt.gcf().tight_layout()