def create_pb_model_of_pretrained(Net):
K.set_learning_phase(0)
#if not(Net=='VGG'):
tf.reset_default_graph()
with K.get_session().as_default():
if Net == 'InceptionV1_slim':
model = InceptionV1_slim(include_top=True, weights='imagenet')
name = "tf_inception_v1_slim.pb"
elif Net == 'InceptionV1':
model = inception_v1_oldTF(weights='imagenet', include_top=True)
name = "tf_inception_v1.pb"
elif Net == 'VGG':
model = tf.keras.applications.vgg19.VGG19(include_top=False, weights='imagenet',\
input_shape=(224,224,3))
name = "tf_vgg19.pb"
elif Net == 'ResNet50':
model = tf.keras.applications.resnet50.ResNet50(include_top=True, weights='imagenet',\
input_shape= (224, 224, 3))
name = "tf_resnet50.pb"
else:
raise (ValueError(Net + ' is unknown'))
os.makedirs('./model', exist_ok=True)
frozen_graph = freeze_session(
K.get_session(),
output_names=[out.op.name for out in model.outputs],
clear_devices=True)
# Save the pb model
tf.io.write_graph(frozen_graph,
logdir="model",
name=name,
as_text=False)
def get_pretrained_model(Net, include_top=True):
if Net == 'InceptionV1_slim':
model = InceptionV1_slim(include_top=include_top, weights='imagenet')
elif Net == 'InceptionV1':
model = inception_v1_oldTF(weights='imagenet', include_top=include_top)
elif Net == 'VGG':
model = tf.keras.applications.vgg19.VGG19(include_top=include_top,
weights='imagenet',
input_shape=(224, 224, 3))
elif Net == 'ResNet50':
model = tf.keras.applications.resnet50.ResNet50(include_top=include_top, weights='imagenet',\
input_shape= (224, 224, 3))
else:
raise (ValueError(Net + ' is unknown'))
return (model)
def get_dico_layers_type_all_layers(Net):
if Net == 'InceptionV1_slim':
model = InceptionV1_slim(include_top=True, weights='imagenet')
elif Net == 'InceptionV1':
model = inception_v1_oldTF(weights='imagenet', include_top=True)
elif Net == 'VGG':
model = tf.keras.applications.vgg19.VGG19(include_top=False,
weights='imagenet',
input_shape=(224, 224, 3))
elif Net == 'ResNet50':
model = tf.keras.applications.resnet50.ResNet50(include_top=True, weights='imagenet',\
input_shape= (224, 224, 3))
else:
raise (ValueError(Net + ' is unknown'))
dico = get_dico_layers_type_all_layers_fromNet(model)
return (dico)
def test_autocorr_render_Inception_v1():
tf.reset_default_graph()
K.set_learning_phase(0)
if not (os.path.isfile("model/tf_inception_v1.pb")):
with K.get_session().as_default():
model = inception_v1_oldTF(
weights='imagenet',
include_top=True) #include_top=True, weights='imagenet')
print(model.input)
os.makedirs('./model', exist_ok=True)
frozen_graph = freeze_session(
K.get_session(),
output_names=[out.op.name for out in model.outputs],
clear_devices=True)
# Save the pb model
tf.io.write_graph(frozen_graph,
logdir="model",
name="tf_inception_v1.pb",
as_text=False)
nodes_tab = [
n.name for n in tf.get_default_graph().as_graph_def().node
]
print(nodes_tab)
#with tf.Graph().as_default() as graph, tf.Session() as sess:
with gradient_override_map({
'Relu': redirected_relu_grad,
'ReLU': redirected_relu_grad
}):
lucid_inception_v1 = Lucid_InceptionV1()
lucid_inception_v1.load_graphdef()
out = render.render_vis(lucid_inception_v1, 'mixed4a_1x1_pre_relu/Conv2D:0',\
relu_gradient_override=True,use_fixed_seed=True)
plt.figure()
plt.imshow(out[0][0])
out = render.render_vis(lucid_inception_v1, 'mixed4b_pre_relu/concat:452',\
relu_gradient_override=True,use_fixed_seed=True)
plt.figure()
plt.imshow(out[0][0])
JITTER = 1
ROTATE = 5
SCALE = 1.1
transforms = [
transform.pad(2 * JITTER),
transform.jitter(JITTER),
transform.random_scale([SCALE**(n / 10.) for n in range(-10, 11)]),
transform.random_rotate(range(-ROTATE, ROTATE + 1))
]
imgs = render.render_vis(lucid_inception_v1,
'mixed4b_pre_relu/concat:452',
transforms=transforms,
param_f=lambda: param.image(64),
thresholds=[2048],
verbose=False,
relu_gradient_override=True,
use_fixed_seed=True)
plt.figure()
plt.imshow(imgs[0][0])