core::tester Namespace Reference

Classes
class	Predictor
Functions
def	draw_all_detection
def	generate_proposals
def	im_detect
def	im_proposal
def	pred_eval
def	vis_all_detection

---

Function Documentation

def core.tester.draw_all_detection	(		im_array,
			detections,
			class_names,
			scale,
			cfg,
			threshold = 1e-1
	)

visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:

Definition at line 278 of file tester.py.

def core.tester.generate_proposals	(		predictor,
			test_data,
			imdb,
			cfg,
			vis = False,
			thresh = 0.
	)

Generate detections results using RPN.
:param predictor: Predictor
:param test_data: data iterator, must be non-shuffled
:param imdb: image database
:param vis: controls visualization
:param thresh: thresh for valid detections
:return: list of detected boxes

Definition at line 58 of file tester.py.

def core.tester.im_detect	(		predictor,
			data_batch,
			data_names,
			scales,
			cfg
	)

Definition at line 124 of file tester.py.

def core.tester.im_proposal	(		predictor,
			data_batch,
			data_names,
			scales
	)

Definition at line 38 of file tester.py.

def core.tester.pred_eval	(		predictor,
			test_data,
			imdb,
			cfg,
			vis = False,
			thresh = 1e-3,
			logger = None,
			ignore_cache = True
	)

wrapper for calculating offline validation for faster data analysis
in this example, all threshold are set by hand
:param predictor: Predictor
:param test_data: data iterator, must be non-shuffle
:param imdb: image database
:param vis: controls visualization
:param thresh: valid detection threshold
:return:

Definition at line 153 of file tester.py.

def core.tester.vis_all_detection	(		im_array,
			detections,
			class_names,
			scale,
			cfg,
			threshold = 1e-3
	)

visualize all detections in one image
:param im_array: [b=1 c h w] in rgb
:param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
:param class_names: list of names in imdb
:param scale: visualize the scaled image
:return:

Definition at line 244 of file tester.py.