class OverfeatExtractor:
def __init__(self, layerNum):
self.layerNum = layerNum
self.of = OverfeatTransformer(output_layers=[layerNum])
def describe(self, data):
return self.of.transform(data)
def getFeatureDim(self):
return SMALL_NETWORK_FILTER_SHAPES[self.layerNum][0]
class OverfeatExtractor:
def __init__(self, layerNum):
# store the layer number and initialize the Overfeat transformer
self.layerNum = layerNum
self.of = OverfeatTransformer(output_layers=[layerNum])
def describe(self, data):
# apply the Overfeat transform to the images
return self.of.transform(data)
def getFeatureDim(self):
# return the feature dimensionality from the supplied layer
return SMALL_NETWORK_FILTER_SHAPES[self, layerNum][0]
class ConvQAgent(PacmanQAgent):
def __init__(self, epsilon=0.05,gamma=0.8,alpha=0.2, numTraining=0, **args):
"""
These default parameters can be changed from the pacman.py command line.
For example, to change the exploration rate, try:
python pacman.py -p PacmanQLearningAgent -a epsilon=0.1
alpha - learning rate
epsilon - exploration rate
gamma - discount factor
numTraining - number of training episodes, i.e. no learning after these many episodes
"""
args['epsilon'] = epsilon
args['gamma'] = gamma
args['alpha'] = alpha
args['numTraining'] = numTraining
self.index = 0 # This is always Pacman
QLearningAgent.__init__(self, **args)
self.tf = OverfeatTransformer(output_layers = [-1], force_reshape = False)
self.weights = util.Counter()
def featureExtractor(self):
screen = np.array(ImageGrab.grab(bbox = (50, 120, 1250, 650)))
small_screen = block_reduce(screen, (530/224, 1200/224, 1), np.max)
features = np.array(self.tf.transform(small_screen[:,:,0:3])).flatten()
feat = dict(zip(range(2000), features))
return feat
def getQValue(self, state, action):
features = self.featureExtractor()
total = 0
for feat in features:
total += feat * self.weights[feat]
return total
def update(self, state, action, nextState, reward):
candidateQ = reward + self.discount * \
self.computeValueFromQValues(nextState)
currentQ = self.getQValue(state, action)
features = self.featureExtractor()
difference = candidateQ - currentQ
for feat in features:
self.weights[feat] += self.alpha * difference * feat
class Classifier(object):
def __init__(self, configPath):
self.config = json.load(open(configPath))
self.model = cPickle.load(open(self.config["classifier_path"]))
self.le = cPickle.load(open(self.config["label_encoder_path"]))
self.overfeat = OverfeatTransformer(output_layers=self.config["layer_num"])
def _preprocess(self, image):
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, tuple(self.config["image_size"]))
return image
def _extract_overfeat_features(self, image):
image = self._preprocess(image)
features = self.overfeat.transform([image])
return features
def predict(self, imagePath):
image = cv2.imread(imagePath)
features = self._extract_overfeat_features(image)[0]
prediction = self.model.predict([features])[0]
return self.le.inverse_transform(prediction)
import cv2
import decimal
import json
import ijson.backends.yajl2_cffi as ijson
from sklearn_theano.feature_extraction import OverfeatTransformer
tr = OverfeatTransformer(output_layers=[8])
class DecimalEncoder(json.JSONEncoder):
def default(self, o):
if isinstance(o, decimal.Decimal):
return float(o)
return super(DecimalEncoder, self).default(o)
with open('../workspace/ds.json') as inh:
with open('../workspace/ds_deep.json', 'w') as outh:
ds = ijson.items(inh, 'item')
outh.write('[')
for i, item in enumerate(ds):
print 'running', i + 1
if i > 0:
outh.write(',')
img = cv2.imread('set1/' + item['file'])
img = cv2.resize(img, (231, 231))
item['deep'] = tr.transform(img)[0].tolist()
json.dump(item, outh, cls=DecimalEncoder)
outh.write(']')
cmap = {}
ct = 0
for k, v in catlists.iteritems():
print v['name']
cnt = 0
cmap[ct] = {'id': k, 'name': v['name']}
for fn in v['images']:
img = cv2.imread(fn)
if img is None:
continue
crop = simpleProcessImage(img)
csz = crop.shape
if csz[0] == 231 and csz[1] == 231:
res = tranformer.transform(crop)
else:
continue
#print res.shape
#print res[res>0.0]
if features is None:
features = res
else:
features = np.vstack((features, res))
ctype.append(ct)
#cv2.imshow('X', crop)
#cv2.waitKey()
cnt += 1
if cnt > 500:
break
import cv2
import decimal
import json
import ijson.backends.yajl2_cffi as ijson
from sklearn_theano.feature_extraction import OverfeatTransformer
tr = OverfeatTransformer(output_layers=[8])
class DecimalEncoder(json.JSONEncoder):
def default(self, o):
if isinstance(o, decimal.Decimal):
return float(o)
return super(DecimalEncoder, self).default(o)
with open('../workspace/ds.json') as inh:
with open('../workspace/ds_deep.json', 'w') as outh:
ds = ijson.items(inh, 'item')
outh.write('[')
for i, item in enumerate(ds):
print 'running', i+1
if i > 0:
outh.write(',')
img = cv2.imread('set1/' + item['file'])
img = cv2.resize(img, (231, 231))
item['deep'] = tr.transform(img)[0].tolist()
json.dump(item, outh, cls=DecimalEncoder)
outh.write(']')
f, axarr = plt.subplots(2, 3)
X = load_sample_image("sloth.jpg")
axarr[0, 0].imshow(X)
axarr[0, 0].axis('off')
# Show a single box
axarr[0, 1].imshow(X)
axarr[0, 1].axis('off')
r = Rectangle((0, 0), 231, 231, fc='yellow', ec='black', alpha=.8)
axarr[0, 1].add_patch(r)
# Show all the boxes being processed
axarr[0, 2].imshow(X)
axarr[0, 2].axis('off')
clf = OverfeatTransformer(force_reshape=False)
X_tf = clf.transform(X)
x_points = np.linspace(0, X.shape[1] - 231, X_tf[0].shape[3])
y_points = np.linspace(0, X.shape[0] - 231, X_tf[0].shape[2])
xx, yy = np.meshgrid(x_points, y_points)
for x, y in zip(xx.flat, yy.flat):
axarr[0, 2].add_patch(Rectangle((x, y), 231, 231, fc='yellow', ec='black',
alpha=.4))
# Get all points with sloth in the top 5 labels
sloth_label = "three-toed sloth, ai, Bradypus tridactylus"
clf = OverfeatLocalizer(match_strings=[sloth_label])
sloth_points = clf.predict(X)[0]
axarr[1, 0].imshow(X)
axarr[1, 0].axis('off')
axarr[1, 0].autoscale(enable=False)
axarr[1, 0].scatter(sloth_points[:, 0], sloth_points[:, 1], color='orange',
f, axarr = plt.subplots(2, 3)
X = load_sample_image("sloth.jpg")
axarr[0, 0].imshow(X)
axarr[0, 0].axis('off')
# Show a single box
axarr[0, 1].imshow(X)
axarr[0, 1].axis('off')
r = Rectangle((0, 0), 231, 231, fc='yellow', ec='black', alpha=.8)
axarr[0, 1].add_patch(r)
# Show all the boxes being processed
axarr[0, 2].imshow(X)
axarr[0, 2].axis('off')
clf = OverfeatTransformer(force_reshape=False)
X_tf = clf.transform(X)
x_points = np.linspace(0, X.shape[1] - 231, X_tf[0].shape[3])
y_points = np.linspace(0, X.shape[0] - 231, X_tf[0].shape[2])
xx, yy = np.meshgrid(x_points, y_points)
for x, y in zip(xx.flat, yy.flat):
axarr[0, 2].add_patch(
Rectangle((x, y), 231, 231, fc='yellow', ec='black', alpha=.4))
# Get all points with sloth in the top 5 labels
sloth_label = "three-toed sloth, ai, Bradypus tridactylus"
clf = OverfeatLocalizer(match_strings=[sloth_label])
sloth_points = clf.predict(X)[0]
axarr[1, 0].imshow(X)
axarr[1, 0].axis('off')
axarr[1, 0].autoscale(enable=False)
axarr[1, 0].scatter(sloth_points[:, 0],
from sklearn_theano.datasets import fetch_asirra
from sklearn_theano.feature_extraction import OverfeatTransformer
import matplotlib.pyplot as plt
import time
asirra = fetch_asirra()
X = asirra.images.astype("float32")
X = X[0:5]
y = asirra.target
all_times = []
for i in range(0, 15):
tf = OverfeatTransformer(output_layers=[i])
t0 = time.time()
X_tf = tf.transform(X)
print("Shape of layer %i output" % i)
print(X_tf.shape)
t_o = time.time() - t0
all_times.append(t_o)
print("Time for layer %i" % i, t_o)
print()
plt.plot(all_times, marker="o")
plt.title("Runtime for input to layer X")
plt.xlabel("Layer number")
plt.ylabel("Time (seconds)")
plt.show()
cmap = {}
ct = 0
for k,v in catlists.iteritems():
print v['name']
cnt=0
cmap[ct] = {'id':k, 'name':v['name']}
for fn in v['images']:
img = cv2.imread(fn)
if img is None:
continue
crop = simpleProcessImage(img)
csz = crop.shape
if csz[0]==231 and csz[1]==231:
res = tranformer.transform(crop)
else:
continue
#print res.shape
#print res[res>0.0]
if features is None:
features = res
else:
features = np.vstack((features, res))
ctype.append(ct)
#cv2.imshow('X', crop)
#cv2.waitKey()
cnt+=1
if cnt>500:
break
print("[INFO] encoding labels...")
le = LabelEncoder()
le.fit([p.split("/")[-2] for p in imagePaths])
print("[INFO] initializing network...")
overfeat = OverfeatTransformer(output_layers=config["layer_num"])
print("[INFO] extracting features...")
for start in xrange(0, len(imagePaths), batch_size):
end = start + batch_size
#read and resize the images
images = [cv2.imread(impath) for impath in imagePaths[start:end]]
images = [cv2.cvtColor(image, cv2.COLOR_BGR2RGB) for image in images]
images = np.array(
[cv2.resize(image, tuple(config["image_size"])) for image in images],
dtype="float")
#dump the image ID and features to the hdf5 database
imageIDDB[start:end] = [
":".join(impath.split("/")[-2:]) for impath in imagePaths[start:end]
]
features = overfeat.transform(np.array(images))
featuresDB[start:end] = overfeat.transform(np.array(images))
print("[INFO] processed {} images".format(end))
db.close()
f = open(config["label_encoder_path"], "w")
cPickle.dump(le, f)
f.close()
from sklearn_theano.datasets import fetch_asirra
from sklearn_theano.feature_extraction import OverfeatTransformer
import matplotlib.pyplot as plt
import time
asirra = fetch_asirra()
X = asirra.images.astype('float32')
X = X[0:5]
y = asirra.target
all_times = []
for i in range(0, 15):
tf = OverfeatTransformer(output_layers=[i])
t0 = time.time()
X_tf = tf.transform(X)
print("Shape of layer %i output" % i)
print(X_tf.shape)
t_o = time.time() - t0
all_times.append(t_o)
print("Time for layer %i" % i, t_o)
print()
plt.plot(all_times, marker='o')
plt.title("Runtime for input to layer X")
plt.xlabel("Layer number")
plt.ylabel("Time (seconds)")
plt.show()
f, axarr = plt.subplots(2, 3)
X = load_sample_image("sloth.jpg")
axarr[0, 0].imshow(X)
axarr[0, 0].axis('off')
# Show a single box
axarr[0, 1].imshow(X)
axarr[0, 1].axis('off')
r = Rectangle((0, 0), 231, 231, fc='yellow', ec='black', alpha=.8)
axarr[0, 1].add_patch(r)
# Show all the boxes being processed
axarr[0, 2].imshow(X)
axarr[0, 2].axis('off')
clf = OverfeatTransformer(force_reshape=False)
X_tf = clf.transform(X[None].astype('float32'))
x_points = np.linspace(0, X.shape[1] - 231, X_tf[0].shape[3])
y_points = np.linspace(0, X.shape[0] - 231, X_tf[0].shape[2])
xx, yy = np.meshgrid(x_points, y_points)
for x, y in zip(xx.flat, yy.flat):
axarr[0, 2].add_patch(Rectangle((x, y), 231, 231, fc='yellow', ec='black',
alpha=.4))
# Get all points with sloth in the top 5 labels
sloth_label = [label for label in get_all_overfeat_labels()
if 'three-toed sloth' in label][0]
clf = OverfeatLocalizer(match_strings=[sloth_label])
sloth_points = clf.predict(X.astype('float32'))[0]
axarr[1, 0].imshow(X)
axarr[1, 0].axis('off')
axarr[1, 0].autoscale(enable=False)
f, axarr = plt.subplots(2, 3)
X = load_sample_image("sloth.jpg")
axarr[0, 0].imshow(X)
axarr[0, 0].axis("off")
# Show a single box
axarr[0, 1].imshow(X)
axarr[0, 1].axis("off")
r = Rectangle((0, 0), 231, 231, fc="yellow", ec="black", alpha=0.8)
axarr[0, 1].add_patch(r)
# Show all the boxes being processed
axarr[0, 2].imshow(X)
axarr[0, 2].axis("off")
clf = OverfeatTransformer(force_reshape=False)
X_tf = clf.transform(X[None].astype("float32"))
x_points = np.linspace(0, X.shape[1] - 231, X_tf[0].shape[3])
y_points = np.linspace(0, X.shape[0] - 231, X_tf[0].shape[2])
xx, yy = np.meshgrid(x_points, y_points)
for x, y in zip(xx.flat, yy.flat):
axarr[0, 2].add_patch(Rectangle((x, y), 231, 231, fc="yellow", ec="black", alpha=0.4))
# Get all points with sloth in the top 5 labels
sloth_label = "three-toed sloth, ai, Bradypus tridactylus"
clf = OverfeatLocalizer(match_strings=[sloth_label])
sloth_points = clf.predict(X.astype("float32"))[0]
axarr[1, 0].imshow(X)
axarr[1, 0].axis("off")
axarr[1, 0].autoscale(enable=False)
axarr[1, 0].scatter(sloth_points[:, 0], sloth_points[:, 1], color="orange", s=50)
