#!/usr/bin/env python
# coding: utf-8

# # Lucid Modelzoo
# 
# If you want to study techniques for visualizing and understanding neural networks, it's important to be able to try your experiments on multiple models.
# 
#  [Lucid](https://github.com/tensorflow/lucid) is a library for visualizing neural networks.
#  As of lucid v0.3, we provide a consistent API for interacting with 27 different vision models.
# 
# 

# ## General Setup

# In[ ]:


# Expanded modelzoo is only available as of lucid v0.3
get_ipython().system('pip install --quiet lucid==0.3')

import numpy as np
import tensorflow as tf

from lucid.misc.io import show, load
import lucid.optvis.objectives as objectives
import lucid.optvis.param as param
import lucid.optvis.render as render
import lucid.optvis.transform as transform


# ## Import Modelzoo

# In[ ]:


# Lucid's modelzoo can be accessed as classes in vision_models
import lucid.modelzoo.vision_models as models

# ... or throguh a more systematic factory API
import lucid.modelzoo.nets_factory as nets


# ## List Models
# 
# As of lucid v0.3

# In[3]:


print ""
print "Model".ljust(27), " ", "Dataset"
print ""
for name, Model in nets.models_map.iteritems():
  print name.ljust(27), " ", Model.dataset


# ## List Model Layers

# In[4]:


models.InceptionV4_slim.layers


# ## Show Model Graph

# In[5]:


model = models.InceptionV4_slim()
model.load_graphdef()

model.show_graph()


# ## Visualize Neuron
# 
# See the [lucid tutorial](https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/tutorial.ipynb) to learn more.
# 
# We pick `InceptionV4/InceptionV4/Mixed_6b/concat` from above, and chose to focus on unit 0.

# In[9]:


model = models.InceptionV4_slim()
model.load_graphdef()

_ = render.render_vis(model, "InceptionV4/InceptionV4/Mixed_6b/concat:0")


# ## Caricature
# 
# See the [inversion and caricature notebook](https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/misc/feature_inversion_caricatures.ipynb) to learn more.

# In[8]:


from lucid.recipes.caricature import feature_inversion

img = load("https://storage.googleapis.com/lucid-static/building-blocks/examples/dog_cat.png")

model = models.InceptionV4_slim()
model.load_graphdef()

result = feature_inversion(img, model, "InceptionV4/InceptionV4/Mixed_6b/concat", n_steps=512, cossim_pow=0.0)
show(result)