def __init__(self): Dataset.__init__(self) self.data_dir = VOC2007_TF_DATADIR self.file_pattern = 'voc2007_%s.tfrecord' self.num_classes = 20 self.name = 'VOC2007' self.is_multilabel = True
def __init__(self, class_name): Dataset.__init__(self) self.data_dir = OBJECTNET3D_TF_DATADIR self.class_name = class_name self.num_classes = 100 self.name = 'ObjectNet3D' self.is_multilabel = True
def __init__(self): Dataset.__init__(self) self.data_dir = IMAGENET_TF_DATADIR self.file_pattern = '%s-*' self.num_classes = 1000 self.label_offset = 1 self.name = 'imagenet'
def __init__(self): subjects = range(1, 5) Dataset.__init__(self, name='OPP', num_classes=4, segment_length=150, num_channels=3, num_loc=5, subjects=subjects) self.XR, self.YR, self.SR = self.read_data(mode=1)
def __init__(self): subjects = np.setdiff1d(range(1, 22), [1, 2, 10, 12, 13, 14, 15, 17, 20, 22]) Dataset.__init__(self, name='IRH', num_classes=24, segment_length=100, num_channels=3, num_loc=5, subjects=subjects) self.XR, self.YR, self.SR = self.read_data()
def __init__(self, args): Dataset.__init__(self, args) #pdb.set_trace() self.user_items_dct = self.get_user_items_dict(self.user_lists_dct, self.list_items_dct) self.user_item_matrix_sp = self.get_sparse_matrix_from_dict( self.user_items_dct, self.num_user, self.num_item) self.list_item_matrix_sp = self.get_sparse_matrix_from_dict( self.list_items_dct, self.num_list, self.num_item) self.item_list_matrix_sp = self.get_sparse_matrix_from_dict( self.list_items_dct, self.num_item, self.num_list, reverse=True) t1 = time() self.user_user_comm_mat_sp = self.mat_mult_sp( self.user_item_matrix_sp, self.user_item_matrix_sp.T) #.astype(bool).astype(int)#todok() self.item_item_comm_mat_sp = self.mat_mult_sp( self.item_list_matrix_sp, self.item_list_matrix_sp.T) #.astype(bool).astype(int) self.list_list_comm_mat_sp = self.mat_mult_sp( self.list_item_matrix_sp, self.list_item_matrix_sp.T ) ##.astype(bool).astype(int) ##real values print("""[%.2f s] """ % (time() - t1)) #pdb.set_trace() # ============================== #self.list_item_train_seq = self.get_dct_mat_seq(dct=self.list_items_dct, num_row=self.num_list, num_col=self.num_item, padding_value=0) ##self.train_matrix_item_seq = self.get_dct_mat_seq_remove_test(dct=self.list_items_dct, num_row=self.num_list, num_col=self.max_item_seq_length+1, padding_value=0) ##last_index :] for all, :-1] for remove test item, :-2] for removing test and valid #pdb.set_trace() ## ''' binarize = True print("hello") if binarize == True: self.user_user_comm_mat_sp = sp.csr_matrix(sp.csr_matrix((self.user_user_comm_mat_sp),dtype=bool),dtype=int) self.item_item_comm_mat_sp = sp.csr_matrix(sp.csr_matrix((self.item_item_comm_mat_sp),dtype=bool),dtype=int) self.list_list_comm_mat_sp = sp.csr_matrix(sp.csr_matrix((self.list_list_comm_mat_sp),dtype=bool),dtype=int) #self.user_user_comm_mat_sp = self.binarize_sparse_matrix(self.user_user_comm_mat_sp) #self.item_item_comm_mat_sp = self.binarize_sparse_matrix(self.item_item_comm_mat_sp) #self.list_list_comm_mat_sp = self.binarize_sparse_matrix(self.list_list_comm_mat_sp) print("hello 2") ''' # adj =========== self.user_adj_mat = self.user_user_comm_mat_sp self.list_adj_mat = self.list_list_comm_mat_sp self.item_adj_mat = self.item_item_comm_mat_sp print("hello")
def __init__(self, args): Dataset.__init__(self, args) self.user_item_embed_mat = self.get_user_item_embed_mat( self.user_attr_mat, self.attr_mat) #self.adjacency_mat = self.get_adjacency_matrix(self.train_matrix,self.train_matrix.T) self.adjacency_mat = self.get_adjacency_matrix_sparse( self.train_matrix, self.train_matrix.T) assert self.adjacency_mat.shape[0] == self.adjacency_mat.shape[1] self.num_nodes = self.adjacency_mat.shape[0] self.feature_dim = self.attr_dim print("num nodes: ", self.num_nodes)
def __init__(self, id=None, drawing=None, posX=0, posY=0, x1=0, y1=0, x2=0, y2=0, pen=None, brush=None): Dataset.__init__(self, id) self.drawing = drawing self.posX = posX self.posY = posY self.x1 = x1 self.y1 = y1 self.x2 = x2 self.y2 = y2 self.pen = pen self.brush = brush
def __init__(self, data_path, train_val_test=(0.8, 0.1, 0.1)): """ Initialises a ImSeg_Dataset object by calling the superclass initialiser. The difference between an ImSeg_Dataset object and a Dataset object is the annotation. This object will therefore override the self.annotations_path and self.annotation_list attributes. """ assert (train_val_test[0] + train_val_test[1] + train_val_test[2] ) == 1, 'Train, val and test percentages should add to 1' assert train_val_test[0] > 0 and train_val_test[ 1] > 0 and train_val_test[ 2] > 0, 'Train, val and test percentages should be non-negative' Dataset.__init__(self, data_path) self.train_val_test = train_val_test self.train_path = self.data_path + '/im_seg/train' self.val_path = self.data_path + '/im_seg/val' self.test_path = self.data_path + '/im_seg/test' self.out_path = self.data_path + '/im_seg/out' self.data_sizes = [] # [train_size, val_size, test_size, out_size] if not os.path.isdir(self.data_path + '/im_seg'): print( f"Creating directory to store semantic segmentation formatted dataset." ) os.mkdir(self.data_path + '/im_seg') # Create train, validation, test directories, each with an images and # annotations sub-directories for directory in [ self.train_path, self.val_path, self.test_path, self.out_path ]: if not os.path.isdir(directory): os.mkdir(directory) if not os.path.isdir(directory + '/images'): os.mkdir(directory + '/images') if not os.path.isdir(directory + '/annotations'): os.mkdir(directory + '/annotations') # Size of each training, val and test directories num_samples = len([ name for name in os.listdir(f'{directory}/images') if name.endswith('.jpg') ]) self.data_sizes.append(num_samples)
def __init__(self, data_path, train_val_test=(0.8, 0.1, 0.1), is_plot=False): """ Initialises a 'PIXOR_Dataset' object by calling the superclass initialiser. The difference between a PIXOR_Dataset object and a Dataset object is the annotation. The PIXOR_Dataset object will therefore override the self.annotations_path and self.annotation_list attributes such that the building labels are in XML format. """ assert (train_val_test[0] + train_val_test[1] + train_val_test[2] ) == 1, 'Train, val and test percentages should add to 1' assert train_val_test[0] > 0 and train_val_test[ 1] > 0 and train_val_test[ 2] > 0, 'Train, val and test percentages should be non-negative' Dataset.__init__(self, data_path) self.train_val_test = train_val_test self.train_path = self.data_path + '/pixor/train' self.val_path = self.data_path + '/pixor/val' self.test_path = self.data_path + '/pixor/test' self.is_plot = is_plot if not os.path.isdir(self.data_path + '/pixor'): print(f"Creating directory to store PIXOR formatted dataset.") os.mkdir(self.data_path + '/pixor') # Create train, validation, test directories, each with an images and annotations # sub-directory for directory in [self.train_path, self.val_path, self.test_path]: if not os.path.isdir(directory): os.mkdir(directory) if not os.path.isdir(directory + '/images'): os.mkdir(directory + '/images') if not os.path.isdir(directory + '/class_annotations'): os.mkdir(directory + '/class_annotations') if not os.path.isdir(directory + '/box_annotations'): os.mkdir(directory + '/box_annotations')
def __init__(self): subjects = range(1, 9) Dataset.__init__(self, name='SAD', num_classes=19, segment_length=125, num_channels=3, num_loc=5, subjects=subjects) if not os.path.exists(self.data_folder): os.makedirs(self.data_folder) self.write_to_file() x1 = np.genfromtxt(self.name + '_allX1.csv', delimiter=',') x2 = np.genfromtxt(self.name + '_allX2.csv', delimiter=',') x3 = np.genfromtxt(self.name + '_allX3.csv', delimiter=',') self.YR = np.genfromtxt(self.name + '_allY.csv', delimiter=',') self.SR = np.genfromtxt(self.name + '_allS.csv', delimiter=',') a, b = x1.shape self.XR = np.empty(shape=(a, 3, b)) self.XR[:, 0, :] = x1 self.XR[:, 1, :] = x2 self.XR[:, 2, :] = x3
def __init__(self, args): Dataset.__init__(self, args) self.same_entity_list = eval(args.same_entity) assert len( self.same_entity_list ) == args.num_views, 'length of same_entity and num_views should be same.' self.item_view_matrix,self.num_row,self.num_col,self.adjacency_view_matrix = [],[],[],[] for view in range(args.num_views): num_row, num_col = self.get_row_column_count(self.embed_path + ".view_matrix" + str(view + 1)) self.num_row.append( num_row ) # this is only for test purpose. self.num_item is used instead self.num_col.append(num_col) if self.same_entity_list[ view] == -1: #-1 means entities are different self.item_view_matrix.append( self.load_rating_file_as_matrix_for_views( self.embed_path + ".view_matrix" + str(view + 1), self.num_row[view], self.num_col[view])) self.adjacency_view_matrix.append( self.get_adjacency_matrix_sparse( self.item_view_matrix[view], self. item_view_matrix[view].T)) # Note num_items is used else: # 1 or other number means it is same entity both side self.item_view_matrix.append( self.load_rating_file_as_matrix_for_views( self.embed_path + ".view_matrix" + str(view + 1), max(self.num_row[view], self.num_col[view]), max(self.num_row[view], self.num_col[view]))) _A_obs = self.item_view_matrix[view] + self.item_view_matrix[ view].T # Note num_items is used _A_obs[_A_obs > 1] = 1 self.adjacency_view_matrix.append( _A_obs) # Note num_items is used
def __init__(self): Dataset.__init__(self) self.data_dir = STL10_TF_DATADIR self.file_pattern = 'stl10_%s.tfrecord' self.num_classes = 10 self.name = 'STL10'
def __init__(self, id=None, x=0, y=0): Dataset.__init__(self, id) self.x = x self.y = y