def get_hypercolumn_prediction(net, img, boxes, categids): boxes = boxes.copy() #clip boxes to image boxes = clip_boxes(boxes-1, img.shape) im_new, spp_boxes, normalized_boxes, categids = get_blobs(img, boxes, categids) #reshape the network net.blobs['image'].reshape(*(im_new.shape)) net.blobs['normalizedboxes'].reshape(*(normalized_boxes.shape)) net.blobs['sppboxes'].reshape(*(spp_boxes.shape)) net.blobs['categids'].reshape(*(categids.shape)) #forward output_blobs = net.forward(image=im_new, normalizedboxes=normalized_boxes,sppboxes=spp_boxes, categids=categids) output =output_blobs['loss'] return output
def reshape(self, bottom, top):
#sample a category
categid = np.random.choice(self.numclasses)
#sample an image for this category
imid = self.data_percateg[categid]['imids'][np.random.choice(
len(self.data_percateg[categid]['imids']))]
img = cv2.imread(self._params.imgpath.format(self.names[imid]))
#get all possibilities for this category
start = self.data_percateg[categid]['im_end_index'][imid] + 1
stop = self.data_percateg[categid]['im_end_index'][imid + 1]
#pick a box
idx = np.random.choice(np.arange(start, stop + 1),
cfg.TRAIN_SAMPLES_PER_IMG)
boxid = self.data_percateg[categid]['boxids'][idx]
boxes = self.boxes[imid][boxid, :] - 1
instid = self.data_percateg[categid]['instids'][idx]
#load the gt
[inst, categories] = sbd.load_gt(self.names[imid])
masks = np.zeros((idx.size, 1, inst.shape[0], inst.shape[1]))
for k in range(idx.size):
masks[k, 0, :, :] = (inst == instid[k] + 1).astype(np.float32)
categids = categid * np.ones(idx.size)
#get the blobs
im_new, spp_boxes, normalized_boxes, categids, masksblob, instance_wts = get_blobs(
img, boxes.astype(np.float32), categids, masks)
#save blobs in private dict
self.myblobs['image'] = im_new.astype(np.float32)
self.myblobs['normalizedboxes'] = normalized_boxes.astype(np.float32)
self.myblobs['sppboxes'] = spp_boxes.astype(np.float32)
self.myblobs['categids'] = categids.astype(np.float32)
self.myblobs['labels'] = masksblob.astype(np.float32)
self.myblobs['instance_wts'] = instance_wts.astype(np.float32)
#and reshape
for i in range(len(top)):
top[i].reshape(*(self.myblobs[self.blob_names[i]].shape))
def reshape(self, bottom, top):
#sample a category
categid = np.random.choice(self.numclasses)
#sample an image for this category
imid = self.data_percateg[categid]['imids'][np.random.choice(len(self.data_percateg[categid]['imids']))]
img = cv2.imread(self._params.imgpath.format(self.names[imid]))
#get all possibilities for this category
start = self.data_percateg[categid]['im_end_index'][imid]+1
stop = self.data_percateg[categid]['im_end_index'][imid+1]
#pick a box
idx = np.random.choice(np.arange(start,stop+1), cfg.TRAIN_SAMPLES_PER_IMG)
boxid = self.data_percateg[categid]['boxids'][idx]
boxes = self.boxes[imid][boxid,:]-1
instid = self.data_percateg[categid]['instids'][idx]
#load the gt
[inst, categories] = sbd.load_gt(self.names[imid])
masks = np.zeros((idx.size, 1,inst.shape[0],inst.shape[1]))
for k in range(idx.size):
masks[k,0,:,:] = (inst==instid[k]+1).astype(np.float32)
categids = categid*np.ones(idx.size)
#get the blobs
im_new, spp_boxes, normalized_boxes, categids, masksblob, instance_wts = get_blobs(img, boxes.astype(np.float32), categids, masks)
#save blobs in private dict
self.myblobs['image']=im_new.astype(np.float32)
self.myblobs['normalizedboxes']=normalized_boxes.astype(np.float32)
self.myblobs['sppboxes']=spp_boxes.astype(np.float32)
self.myblobs['categids']=categids.astype(np.float32)
self.myblobs['labels']=masksblob.astype(np.float32)
self.myblobs['instance_wts']=instance_wts.astype(np.float32)
#and reshape
for i in range(len(top)):
top[i].reshape(*(self.myblobs[self.blob_names[i]].shape))
