def __init__(self, modelText):
# store the layer number and initialize the Overfeat transformer
#self.layerNum = layerNum
self.modelText = modelText
print("[INFO] loading {}...".format(modelText))
if modelText in ("inception", "xception", "vgg16", "vgg19", "resnet"):
Network = MODELS[modelText]
self.model = Network(include_top=False)
if modelText == "googlenet":
self.model = GoogLeNetTransformer()
if modelText == "overfeat":
self.model = OverfeatTransformer(output_layers=[-3])
if modelText == "lab888":
self.model = LABModel()
if modelText == "lab444":
self.model = HSVModel(bins=[4, 4, 4])
if modelText == "hsv888":
self.model = LABModel()
if modelText == "hsv444":
self.model = HSVModel(bins=[4, 4, 4])
if modelText == "haralick":
self.model = Haralick()
if modelText == "lbp":
self.model = LBP()
if modelText == "hog":
self.model = HOG()
if modelText == "haarhog":
self.model = HaarHOG()
if modelText == "densenet":
self.model = DenseNet()
if "annulus" in modelText:
bags = int(modelText[modelText.find('_') + 1:modelText.rfind('_')])
p_segments = int(modelText[modelText.rfind('_') + 1])
self.model = HistogramsSeveralMasksAnnulusLabSegments(
plainImagePath=
"/home/joheras/Escritorio/Research/Fungi/FungiImages/plain.jpg",
bags=[bags, bags, bags],
p_segments=p_segments)
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(']')
print 'y>x', crop.shape
else:
h = 231
w = sz[1] * h / sz[0]
mid = w / 2
rimg = cv2.resize(img, (w, h))
crop = rimg[:, mid - h / 2:mid + h / 2 + 1]
print 'y<x', crop.shape
return crop
if __name__ == '__main__':
catlists = json.load(file('catimagelist.json'))
#print catlists
tranformer = OverfeatTransformer(output_layers=[-2])
features = None
ctype = []
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
from sklearn_theano.feature_extraction import OverfeatTransformer
from sklearn_theano.utils import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.metrics import classification_report, accuracy_score
import matplotlib.pyplot as plt
import time
asirra = fetch_asirra(image_count=20)
X = asirra.images.astype('float32')
y = asirra.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=.6,
random_state=1999)
tf = OverfeatTransformer(output_layers=[-3])
clf = LogisticRegression()
pipe = make_pipeline(tf, clf)
t0 = time.time()
pipe.fit(X_train, y_train)
print("Total transform time")
print("====================")
print(time.time() - t0)
print()
y_pred = pipe.predict(X_test)
print(classification_report(y_test, y_pred))
print()
print("Accuracy score")
print("==============")
print(accuracy_score(y_test, y_pred))
f, axarr = plt.subplots(1, 2)
# Show the original image
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)
def __init__(self, layerNum):
# store the layer number and initialize the Overfeat transformer
self.layerNum = layerNum
self.of = OverfeatTransformer(output_layers=[layerNum])
shape=(len(imagePaths), ),
dtype=h5py.special_dtype(vlen=unicode))
featuresDB = db.create_dataset("features",
shape=(len(imagePaths), output_size),
dtype="float")
#just to reproduce the results
random.seed(42)
random.shuffle(imagePaths)
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]
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 __init__(self, layerNum):
self.layerNum = layerNum
self.of = OverfeatTransformer(output_layers=[layerNum])
