问题:我正在从保存的检查点加载一个简单的 VGG16。我想在推理过程中为图像生成显着性。当我计算为此所需的梯度(损失输入图像)时,我将所有梯度恢复为零。非常感谢我在这里缺少的任何想法!
tf版本: tensorflow-2.0alpha-gpu
该模型:
import tensorflow as tf
from tensorflow.keras.applications.vgg16 import VGG16 as KerasVGG16
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Flatten, Dense
class VGG16(Model):
def __init__(self, num_classes, use_pretrained=True):
super(VGG16, self).__init__()
self.num_classes = num_classes
self.use_pretrained = use_pretrained
if use_pretrained:
self.base_model = KerasVGG16(weights='imagenet', include_top=False)
for layer in self.base_model.layers:
layer.trainable = False
else:
self.base_model = KerasVGG16(include_top=False)
self.flatten1 = Flatten(name='flatten')
self.dense1 = Dense(4096, activation='relu', name='fc1')
self.dense2 = Dense(100, activation='relu', name='fc2')
self.dense3 = Dense(self.num_classes, activation='softmax', name='predictions')
def call(self, inputs):
x = self.base_model(tf.cast(inputs, tf.float32))
x = self.flatten1(x)
x = self.dense1(x)
x = self.dense2(x)
x = self.dense3(x)
return x
我训练这个模型并将其保存到一个检查点并通过以下方式加载它:
model = VGG16(num_classes=2, use_pretrained=False)
checkpoint = tf.train.Checkpoint(net=model)
status = checkpoint.restore(tf.train.latest_checkpoint('./my_checkpoint'))
status.assert_consumed()
我验证重量是否正确加载。
获取测试图像
# load my image and make sure its float
img = tf.convert_to_tensor(image, dtype=tf.float64)
support_class = tf.convert_to_tensor(support_class, dtype=tf.float64)
获取渐变:
with tf.GradientTape(persistent=True) as g_tape:
g_tape.watch(img)
#g_tape.watch(model.base_model.trainable_variables)
#g_tape.watch(model.trainable_variables)
loss = tf.losses.CategoricalCrossentropy()(support_class, model(img))
gradients_wrt_image = g_tape.gradient(loss,
img, unconnected_gradients=tf.UnconnectedGradients.NONE)
当我检查我的渐变时,它们都为零!知道我错过了什么吗?提前致谢!