我正在尝试创建一个图像分类器,它利用纤薄文档中提供的预先训练的ResNet V2模型。
以下是目前的代码:
import tensorflow as tf
slim = tf.contrib.slim
from PIL import Image
from inception_resnet_v2 import *
import numpy as np
checkpoint_file = 'inception_resnet_v2_2016_08_30.ckpt'
sample_images = ['carrot.jpg']
input_tensor = tf.placeholder(tf.float32, shape=(None,299,299,3), name='input_image')
scaled_input_tensor = tf.scalar_mul((1.0/255), input_tensor)
scaled_input_tensor = tf.subtract(scaled_input_tensor, 0.5)
scaled_input_tensor = tf.multiply(scaled_input_tensor, 2.0)
variables_to_restore = slim.get_model_variables()
print(variables_to_restore)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_file,
slim.get_model_variables('InceptionResnetV2'))
sess = tf.Session()
init_fn(sess)
arg_scope = inception_resnet_v2_arg_scope()
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
for image in sample_images:
im = Image.open(image).resize((299,299))
im = np.array(im)
im = im.reshape(-1,299,299,3)
predict_values, logit_values = sess.run([end_points['Predictions'], logits], feed_dict={input_tensor: im})
print (np.max(predict_values), np.max(logit_values))
print (np.argmax(predict_values), np.argmax(logit_values))
问题是我一直收到这个错误:
Traceback (most recent call last):
File "./classify.py", line 21, in <module>
slim.get_model_variables('InceptionResnetV2'))
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 584, in assign_from_checkpoint_fn
saver = tf_saver.Saver(var_list, reshape=reshape_variables)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1040, in __init__
self.build()
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1061, in build
raise ValueError("No variables to save")
ValueError: No variables to save
所以似乎TF / Slim无法找到任何变量,当我打电话时这是明确的:
variables_to_restore = slim.get_model_variables()
print(variables_to_restore)
因为它输出一个空数组。
如何使用预先训练过的模型?
答案 0 :(得分:1)
这是因为您还没有在图表中构建模型,但是还没有以名称&#34; InceptionResnetV2&#34;开头的任何变量。由保护者捕捉和恢复。
我相信你应该在使用slim.get_variables_to_restore()
之前放置模型结构。
例如:
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
variables_to_restore = slim.get_model_variables()
这样,将构造Tensor变量,您应该看到variables_to_restore不再为空。
答案 1 :(得分:0)
您需要手动添加模型变量。
试试这个
with slim.arg_scope(arg_scope):
logits, end_points = inception_resnet_v2(scaled_input_tensor, is_training=False)
# Add model variables
for var in tf.global_variables(scope='inception_resnet_v2'):
slim.add_model_variable(var)