def __init__(self, master, bg, width, height, scale=30.0, varDict=dict()):
Canvas.__init__(self, master, width=width, height=height, bg=bg)
self.varDict = varDict # Dictionary of variables
self.evaluator = Evaluation.Eval(
varDict=varDict
) # Creation of evaluator object, sending variable dictionary as reference
self.evaluate = self.evaluator.evaluate # Obtaining the function
self.fnList = [] # List of functions to be plotted
self.fnColors = {}
self.xrange = width #Range of x axis
self.yrange = height #Range of y axis
# Initializing Origin and Scale
self.x_offset = width / 2.0
self.y_offset = height / 2.0
self.scale = scale
# Storing a backup
self.default_x_offset = self.x_offset
self.default_y_offset = self.y_offset
self.default_scale = self.scale
#Plotting axis
self.plotAxis()
'-dt',
type=str,
help='Exact datetime of model used for inference')
args = parser.parse_args()
##### Set specified GPU to be active
if args.GPU != -1:
os.environ['CUDA_VISIBLE_DEVICES'] = str(args.GPU)
##### Load Training/Testing Data
Loader = IO.ShapeNetIO('./Dataset/ShapeNet', batchsize=args.batchsize)
Loader.LoadTestFiles()
##### Evaluation Object
Eval = Evaluation.Eval()
## Number of categories
PartNum = Loader.NUM_PART_CATS
output_dim = PartNum
ShapeCatNum = Loader.NUM_CATEGORIES
#### Save Directories
#dt='2020-06-17_07-45-44'
dt = args.Datetime
BASE_PATH = os.path.expanduser('./Results/ShapeNet/{}_sty-{}_m-{}_{}'.format(
args.Network, args.Style, args.m, dt))
SUMMARY_PATH = os.path.join(BASE_PATH, 'Summary')
PRED_PATH = os.path.join(BASE_PATH, 'Prediction')
CHECKPOINT_PATH = os.path.join(BASE_PATH, 'Checkpoint')
summary_filepath = os.path.join(SUMMARY_PATH, 'Summary.txt')
def __init__(self, varDict=dict(pi=3.14159265359, e=2.718281)):
self.varDict = varDict #Variable Mapping
self.evaluator = Evaluation.Eval(varDict=varDict) #Evaluator object
self.evaluate = self.evaluator.evaluate #Evauator Function\
