def create_classifer(in_path,out_path,built_classifer,flat=True):
dataset=load.get_images(in_path)
cls=built_classifer(dataset.shape())
print(flat)
if(flat):
cls=learning_iter(dataset,cls)
else:
cls=learning_conv(dataset,cls)
utils.save_object(out_path,cls)
return cls
return T.maximum(X, 0.)
def dropout(X, p=0.):
if p > 0:
retain_prob = 1 - p
X *= srng.binomial(X.shape, p=retain_prob, dtype=theano.config.floatX)
X /= retain_prob
return X
def softmax(X):
e_x = T.exp(X - X.max(axis=1).dimshuffle(0, 'x'))
return e_x / e_x.sum(axis=1).dimshuffle(0, 'x')
def get_hyper_params(learning_rate=0.10):
kern_one=8#32
kern_two=12#64
kern_third=16#128
n_hidden=400
kern_params=[(kern_one, 1, 3, 3),(kern_two, kern_one, 3, 3),(kern_third, kern_two, 3, 3),
(kern_third * 6 * 6, n_hidden),(n_hidden, 7)]
params={'learning_rate': learning_rate,
'kern_params':kern_params}
return params
if __name__ == '__main__':
dataset_path="/home/user/cf/conv_frames/cls/images/"
dataset=load.get_images(dataset_path)
out_path="/home/user/cf/exp1/conv_net"
cls=learning.create_classifer(dataset_path,out_path,built_conv_cls,flat=False)
learning.evaluate_cls(dataset_path,out_path,flat=False)
def evaluate_cls(dataset_path,cls_path,flat=True):
dataset=load.get_images(dataset_path)
cls=utils.read_object(cls_path) #learning_iter(dataset,cls)
correct=check_prediction(dataset,cls,flat)
print(correct)