def inference(filename):
layers = 50
img = load_image(filename)
print(img.shape)
sess = tf.Session()
new_saver = tf.train.import_meta_graph(meta_fn(layers))
new_saver.restore(sess, checkpoint_fn(layers))
graph = tf.get_default_graph()
prob_tensor = graph.get_tensor_by_name("prob:0")
images = graph.get_tensor_by_name("images:0")
for op in graph.get_operations():
print op.name
#init = tf.initialize_all_variables()
#sess.run(init)
print "graph restored"
batch = img.reshape((1, 224, 224, 3))
feed_dict = {images: batch}
prob = sess.run(prob_tensor, feed_dict=feed_dict)
return print_prob(prob[0])
def test_image():
img = load_image("data/cat.jpg")
batch = img.reshape((1, 224, 224, 3))
feed_dict = {images: batch}
prob = sess.run(prob_tensor, feed_dict=feed_dict)
print_prob(prob[0])
vl = ['scale5/block3/Relu:0']
# vl = ['scale1/Relu:0', 'scale1/Conv2D:0', 'sub:0']
for v in vl:
vten = sess.run(graph.get_tensor_by_name(v), feed_dict=feed_dict)
print v
print vten
print vten.shape
# print sess.run(graph.get_tensor_by_name("scale1/Relu:0"),
# feed_dict=feed_dict)
# print sess.run(graph.get_tensor_by_name("scale1/Conv2D:0"),
# feed_dict=feed_dict)
# print sess.run(graph.get_tensor_by_name("sub:0"), feed_dict=feed_dict)
pass
def test_image():
img = load_image("data/cat.jpg")
batch = img.reshape((1, 224, 224, 3))
feed_dict = {images: batch}
prob = sess.run(prob_tensor, feed_dict=feed_dict)
print_prob(prob[0])
vl = ['scale5/block3/Relu:0']
# vl = ['scale1/Relu:0', 'scale1/Conv2D:0', 'sub:0']
for v in vl:
vten = sess.run(graph.get_tensor_by_name(v), feed_dict=feed_dict)
print v
print vten
print vten.shape
# print sess.run(graph.get_tensor_by_name("scale1/Relu:0"),
# feed_dict=feed_dict)
# print sess.run(graph.get_tensor_by_name("scale1/Conv2D:0"),
# feed_dict=feed_dict)
# print sess.run(graph.get_tensor_by_name("sub:0"), feed_dict=feed_dict)
pass
tf.app.flags.DEFINE_string('resnet_model_name', 'ResNet-',
"""Model name.""")
layers = 20
img = load_image("data/cat.jpg")
sess = tf.Session()
saver = tf.train.import_meta_graph(meta_fn(layers))
saver.restore(sess, checkpoint_fn(layers))
graph = tf.get_default_graph()
prob_tensor = graph.get_tensor_by_name("prob:0")
images = graph.get_tensor_by_name("images:0")
for op in graph.get_operations():
print op.name
#init = tf.initialize_all_variables()
#sess.run(init)
print "graph restored"
batch = img.reshape((1, 224, 224, 3))
feed_dict = {images: batch}
prob = sess.run(prob_tensor, feed_dict=feed_dict)
print_prob(prob[0])
from convert import print_prob, load_image, checkpoint_fn, meta_fn
import tensorflow as tf
layers = 50
img = load_image("data/cat.jpg")
sess = tf.Session()
new_saver = tf.train.import_meta_graph(meta_fn(layers))
new_saver.restore(sess, checkpoint_fn(layers))
graph = tf.get_default_graph()
prob_tensor = graph.get_tensor_by_name("prob:0")
images = graph.get_tensor_by_name("images:0")
for op in graph.get_operations():
print op.name
#init = tf.initialize_all_variables()
#sess.run(init)
print "graph restored"
batch = img.reshape((1, 224, 224, 3))
feed_dict = {images: batch}
prob = sess.run(prob_tensor, feed_dict=feed_dict)
print_prob(prob[0])