Python decomposition.MiniBatchDictionaryLearning类代码示例

def dictionay_learning_MHOF_online(training_samples_num=400):
    from MHOF_Extraction import MHOF_Extraction
    from MHOF_histogram_block import MHOF_histogram_block
    from sklearn.decomposition import MiniBatchDictionaryLearning
    import numpy as np
    import cv2
    import video
    cam=video.create_capture('Crowd-Activity-All.avi')
    height_block_num=4
    width_block_num=5
    bin_num=16
    ret,prev=cam.read()
    ret,img=cam.read()
    flow_H=MHOF_Extraction(prev,img)
    flow_hist_H=MHOF_histogram_block(flow_H,height_block_num,width_block_num,bin_num)
    flow_hist_H=np.reshape(flow_hist_H,[1,flow_hist_H.size])
    #  error!!!!
    dico=MiniBatchDictionaryLearning(1,alpha=1,n_iter=500)
    dic=dico.fit(flow_hist_H).components_
    for i in range(training_samples_num):
        ret,img=cam.read()
        flow_H=MHOF_Extraction(prev,img)
        flow_hist_H=MHOF_histogram_block(flow_H,height_block_num,width_block_num,bin_num)
        dico=MiniBatchDictionaryLearing(i+1,alpha=1,n_iter=500,dict_init=dic)
        dic=dico.fit(flow_hist_H).components
    return dic

        

def test_dict_learning_online_positivity(transform_algorithm,
                                         positive_code,
                                         positive_dict):
    rng = np.random.RandomState(0)
    n_components = 8

    dico = MiniBatchDictionaryLearning(
        n_components, transform_algorithm=transform_algorithm, random_state=0,
        positive_code=positive_code, positive_dict=positive_dict).fit(X)
    code = dico.transform(X)
    if positive_dict:
        assert_true((dico.components_ >= 0).all())
    else:
        assert_true((dico.components_ < 0).any())
    if positive_code:
        assert_true((code >= 0).all())
    else:
        assert_true((code < 0).any())

    code, dictionary = dict_learning_online(X, n_components=n_components,
                                            alpha=1, random_state=rng,
                                            positive_dict=positive_dict,
                                            positive_code=positive_code)
    if positive_dict:
        assert_true((dictionary >= 0).all())
    else:
        assert_true((dictionary < 0).any())
    if positive_code:
        assert_true((code >= 0).all())
    else:
        assert_true((code < 0).any())

def main(games_path = None):
    
    if games_path == None:
        games_path = 'specmine/data/go_games/2010-01.pickle.gz'

    with specmine.util.openz(games_path) as games_file:
        games = pickle.load(games_file)

    boards = None # numpy array nx9x9 
    for game in games:
        if boards == None: 
            boards = games[game].grids
        else:
            boards = numpy.vstack((boards,games[game].grids))

    print 'boards shape: ', boards.shape

    boards = boards.reshape((boards.shape[0],-1))

    print 'boards reshaped: ', boards.shape

    print 'Learning the dictionary... '
    t0 = time()
    dico = MiniBatchDictionaryLearning(n_atoms=100, alpha=1, n_iter=500)
    V = dico.fit(boards).components_
    dt = time() - t0
    print 'done in %.2fs.' % dt

    #pl.figure(figsize=(4.2, 4))
    for i, comp in enumerate(V[:100]):
        pl.subplot(10, 10, i + 1)
        pl.imshow(comp, cmap=pl.cm.gray_r) # interpolation='nearest')
        pl.xticks(())
        pl.yticks(())

def scskl_dico_learning(list_pickled_array,n_atoms,maxepoch=5,maxiter=100):
  D = None
  for e in range(maxepoch):
    for a in list_pickled_array:
      data = joblib.load(a)
      dico = MiniBatchDictionaryLearning(n_components=n_atoms, n_iter=maxiter, dict_init=D)
      D = dico.fit(data).components_.astype(np.float32)
  return D      

def sklearn_check(img, patch_size, dic_size, T=1000):
    patch_shape = (patch_size, patch_size)
    patches = extract_patches_2d(img, patch_shape)
    patches = patches.reshape(patches.shape[0], -1)
    patches = center(patches)
    dl = MiniBatchDictionaryLearning(dic_size, n_iter=T)
    dl.fit(patches)
    D = dl.components_.T
    return D

def to_sparse(X,dim):

	sparse_dict = MiniBatchDictionaryLearning(dim)
	sparse_dict.fit(X)
	sparse_vectors = sparse_encode(X, sparse_dict.components_)

	for i in sparse_vectors:
		print i

	return sparse_vectors

def create_dictionaries(n_codewords=20):
	dataset_features = np.load('MSR_Features_hog-hof-skel1360423760.27.dat')
	hogs = []
	hofs = []
	skels = []
	for n in dataset_features.keys():
		hogs +=	dataset_features[n]['hog']
		hofs +=	dataset_features[n]['hof']
		skels += [normalize_skeleton(dataset_features[n]['skel_world'])]

	''' Input should be features[n_samples, n_features] '''
	hogs = np.vstack(hogs)
	hofs = np.vstack(hofs)
	skels = np.vstack(skels)

	hog_dict = MiniBatchDictionaryLearning(n_codewords, n_jobs=-1, verbose=True, transform_algorithm='lasso_lars')
	hog_dict.fit(hogs)
	hof_dict = MiniBatchDictionaryLearning(n_codewords, n_jobs=-1, verbose=True, transform_algorithm='lasso_lars')
	hof_dict.fit(hofs)
	skels_dict = MiniBatchDictionaryLearning(n_codewords, n_jobs=-1, verbose=True, transform_algorithm='lasso_lars')
	skels_dict.fit(skels)

	feature_dictionaries = {'hog':hog_dict, 'hof':hof_dict, 'skel':skels_dict}

	with open('MSR_Dictionaries_hog-hof-skel_%f.dat'%time.time(), 'wb') as outfile:
	    pickle.dump(feature_dictionaries, outfile, protocol=pickle.HIGHEST_PROTOCOL)

class BOW_sparsecoding(BOW):

	def codebook(self):
		self.mbdl =  MiniBatchDictionaryLearning(self.N_codebook)
		self.mbdl.fit(self.raw_features)
		

	def bow_feature_extract(self, path):
		des = self.raw_feature_extract(path)
		out = sum(sparse_encode(des, self.mbdl.components_))
		out = np.array([out])
		return out

def buildmodel2():
    "生成有眼镜-无眼镜pair模型"
    modelrec = np.load('cut_rec.npy')
    modelglass = np.load('glassline.npy')[:modelrec.shape[0]]

    linkedmodel = np.empty((modelrec.shape[0],modelrec.shape[1]+modelglass.shape[1]),'f')
    linkedmodel[:,:modelrec.shape[1]]=modelrec
    linkedmodel[:,modelrec.shape[1]:]=modelglass

    #Train
    from sklearn.decomposition import MiniBatchDictionaryLearning
    learning = MiniBatchDictionaryLearning(500,verbose=True)
    learning.fit(linkedmodel)
    import cPickle
    cPickle.dump(learning,file('sparselinked','wb'),-1)

def learning_sparse_coding(X, components=None):
    """
    http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.DictionaryLearning.html
    http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.sparse_encode.html
    """
    if components is None:
        print('Learning the dictionary...')
        t0 = time()
        diclearner = MiniBatchDictionaryLearning(n_components=100, verbose=True)
        components = diclearner.fit(X).components_
        np.savetxt('components_of_convfeat.txt', components)
        dt = time() - t0
        print('done in %.2fs.' % dt)

    codes = sparse_encode(X, components)
    np.savetxt('sparse_codes_of_convfeat.txt', codes)

 def extract_codes(self, X, standardize=False):
     self.standardize=standardize
     self._extract_data_patches(X)
     self.dico = MiniBatchDictionaryLearning(n_components=self.n_components, alpha=1, n_iter=500)
     print "Dictionary learning from data..."
     self.D = self.dico.fit(self.data)
     return self

 def fit(self, X, y=None):
     # compute the codes
     print 'Extracting patchs...'
     patchs = []
     num = self.patch_num // X.size
     for x in X:
         img = imread(str(x[0]))
         tmp = extract_patches_2d(img, (self.patch_size,self.patch_size), \
                                  max_patches=num, random_state=np.random.RandomState())
         patchs.append(tmp)
     data = np.vstack(patchs)
     data = data.reshape(data.shape[0], -1)
     
     data -= np.mean(data, axis=0)
     data = data/np.std(data, axis=0)
     
     print 'Learning codebook...'
     if self.method == 'sc':
         self.dico = MiniBatchDictionaryLearning(n_components=self.codebook_size, \
                                            alpha=1, n_iter=100, batch_size =100, verbose=True)
         self.dico.fit(data)
     elif self.method=='km':
         # self.dico = MiniBatchKMeans(n_clusters=self.codebook_size)
         pass
     
     return self

def test_dict_learning_online_partial_fit():
    # this test was not actually passing before!
    raise SkipTest
    n_components = 12
    rng = np.random.RandomState(0)
    V = rng.randn(n_components, n_features)  # random init
    V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
    dico1 = MiniBatchDictionaryLearning(n_components, n_iter=10, batch_size=1,
                                        shuffle=False, dict_init=V,
                                        random_state=0).fit(X)
    dico2 = MiniBatchDictionaryLearning(n_components, n_iter=1, dict_init=V,
                                        random_state=0)
    for ii, sample in enumerate(X):
        dico2.partial_fit(sample, iter_offset=ii * dico2.n_iter)
        # if ii == 1: break
    assert_true(not np.all(sparse_encode(X, dico1.components_, alpha=100) ==
                           0))
    assert_array_equal(dico1.components_, dico2.components_)

def train_sparse_coding(feature_list, patch_list, dict_size=256, transform_alpha=0.5, n_iter=50):
    """
    使用mini batch训练稀疏编码
    #feature_list 表示要训练的特征的列表
    #patch_list 表示结果patch的列表

    :return sc_list
    """
    sc_list = []
    i = 0
    for feature, patch in zip(feature_list, patch_list):
        i = i + 1
        '''
        由于组合数值大小比例的问题，稀疏编码可能忽略较小的特征,下面的×10需要用别的特征归一化方法代替
        相关性越大，则每个向量都是有用的，所以需要更长的时间进行训练。
        '''
        dico = None
        X = np.concatenate((feature, patch), axis=1)

        if len(X) > 100000:
            np.random.shuffle(X)
            X = X[:90000]

        if len(X) < 5000:
            print "进入DictionaryLearning状态"
            dico = MiniBatchDictionaryLearning(batch_size=1000, transform_algorithm='lasso_lars', fit_algorithm='lars',
                                               transform_n_nonzero_coefs=5, n_components=len(X)/50,
                                               dict_init=X[:len(X)/50],
                                               n_iter=n_iter, transform_alpha=transform_alpha, verbose=10, n_jobs=-1)
        else:
            print "进入MiniBatchDictionaryLearning状态"
            dico = MiniBatchDictionaryLearning(batch_size=1000, transform_algorithm='lasso_lars', fit_algorithm='lars',
                                               transform_n_nonzero_coefs=5, n_components=len(X)/50,
                                               dict_init=X[:len(X)/50],
                                               n_iter=n_iter, transform_alpha=transform_alpha, verbose=10, n_jobs=-1)
        V = dico.fit(X).components_
        sc_list.append(V)

        file_name = "./tmp_file/_tmp_sc_list_new_clsd_raw_%d.pickle" % (i)
        sc_file = open(file_name, 'wb')
        cPickle.dump(sc_list, sc_file, 1)
        sc_file.close()

    return sc_list

def test_dict_learning_online_partial_fit():
    n_components = 12
    rng = np.random.RandomState(0)
    V = rng.randn(n_components, n_features)  # random init
    V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
    dict1 = MiniBatchDictionaryLearning(n_components, n_iter=10 * len(X),
                                        batch_size=1,
                                        alpha=1, shuffle=False, dict_init=V,
                                        random_state=0).fit(X)
    dict2 = MiniBatchDictionaryLearning(n_components, alpha=1,
                                        n_iter=1, dict_init=V,
                                        random_state=0)
    for i in range(10):
        for sample in X:
            dict2.partial_fit(sample[np.newaxis, :])

    assert not np.all(sparse_encode(X, dict1.components_, alpha=1) == 0)
    assert_array_almost_equal(dict1.components_, dict2.components_,
                              decimal=2)