def evaluate(self):
efficientdetPredict = EfficientdetPredict(os.path.join(self.OUTPUT_PATH,self.DATASET_NAME,"models","efficientdet" + str(self.model) + '_' + self.DATASET_NAME,'pascalCustom_30.h5'),
os.path.join(self.OUTPUT_PATH,self.DATASET_NAME, self.DATASET_NAME + "_classes.csv"),
self.model)
map = Map(efficientdetPredict, self.DATASET_NAME, os.path.join(self.OUTPUT_PATH, self.DATASET_NAME), self.model)
map.evaluate()
def evaluate(self):
tensorflowPredict = TensorflowPredict(os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "models",
self.model + "_" + self.DATASET_NAME + "_final.params"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "annotations", "label_map.pbtxt"),
self.model)
map = Map(tensorflowPredict, self.DATASET_NAME, os.path.join(self.OUTPUT_PATH, self.DATASET_NAME), self.model)
map.evaluate()
def evaluate(self):
# yoloPredict = DarknetPredict(imagePaths,modelWeights,classesFile,modelConfiguration)
yoloPredict = DarknetPredict(
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "models", self.DATASET_NAME+"_"+self.model +"train_final.weights"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "classes.names"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME,self.DATASET_NAME+"_"+self.model + "train.cfg"))
map = Map(yoloPredict, self.DATASET_NAME,os.path.join(self.OUTPUT_PATH, self.DATASET_NAME), self.model)
map.evaluate()
def evaluate(self):
rcnnPredict = RCNNPredict(
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "models",
"mask_rcnn_" + self.DATASET_NAME.lower() +
"_0005.h5"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "classes.names"))
map = Map(rcnnPredict, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()
def evaluate(self):
# yoloPredict = DarknetPredict(imagePaths,modelWeights,classesFile,modelConfiguration)
retinanetPredict = RetinanetPredictor(
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "models",
"output.h5"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "classes.names"))
map = Map(retinanetPredict, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()
def evaluate(self):
predictor = mmdetectionPredict(
os.path.join('./work_dirs/' + self.model + '/latest.pth'),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME,
self.DATASET_NAME + "_classes.csv"), self.model,
self.model + self.DATASET_NAME)
map = Map(predictor, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()
def evaluate(self):
mxnetPredict = MxNetPredict(
os.path.join(
self.OUTPUT_PATH, self.DATASET_NAME, "models",
self.model + "_" + self.DATASET_NAME + "_final.params"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "classes.names"),
self.model)
map = Map(mxnetPredict, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()
def evaluate(self):
fcosPredict = FcosPredict(
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "models",
"fcos_" + str(self.model) + '_' + self.DATASET_NAME,
str(self.model) + '_pascalCustom_25.h5'),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME,
self.DATASET_NAME + "_classes.csv"), self.model)
map = Map(fcosPredict, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()
def evaluate(self):
tinyyoloPredict = DarknetPredict(
os.path.join(
self.OUTPUT_PATH, self.DATASET_NAME, "models",
self.DATASET_NAME + "_" + self.model + "_final.weights"),
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME, "classes.names"),
os.path.join(self.OUTPUT_PATH,
self.DATASET_NAME + "_" + self.model,
self.DATASET_NAME + "_" + self.model + ".cfg"))
map = Map(tinyyoloPredict, self.DATASET_NAME,
os.path.join(self.OUTPUT_PATH, self.DATASET_NAME),
self.model)
map.evaluate()