def build(self): """ Build Retina Net architecture. """ # Image size must be dividable by 2 multiple times. h, w = self.cf.patch_size[:2] if h / 2**5 != int(h / 2**5) or w / 2**5 != int(w / 2**5): raise Exception( "Image size must be dividable by 2 at least 5 times " "to avoid fractions when downscaling and upscaling." "For example, use 256, 320, 384, 448, 512, ... etc. ") # instanciate abstract multi dimensional conv class and backbone model. conv = mutils.NDConvGenerator(self.cf.dim) backbone = utils.import_module('bbone', self.cf.backbone_path) # build Anchors, FPN, Classifier / Bbox-Regressor -head self.np_anchors = mutils.generate_pyramid_anchors(self.logger, self.cf) self.anchors = torch.from_numpy(self.np_anchors).float().cuda() self.Fpn = backbone.FPN(self.cf, conv, operate_stride1=self.cf.operate_stride1) self.Classifier = Classifier(self.cf, conv) self.BBRegressor = BBRegressor(self.cf, conv) self.final_conv = conv(self.cf.end_filts, self.cf.num_seg_classes, ks=1, pad=0, norm=self.cf.norm, relu=None)
def build(self): """ Build Retina Net architecture. """ # Image size must be dividable by 2 multiple times. h, w = self.cf.patch_size[:2] if h / 2 ** 5 != int(h / 2 ** 5) or w / 2 ** 5 != int(w / 2 ** 5): raise Exception("Image size must be dividable by 2 at least 5 times " "to avoid fractions when downscaling and upscaling." "For example, use 256, 320, 384, 448, 512, ... etc. ") # instanciate abstract multi dimensional conv class and backbone model. conv = mutils.NDConvGenerator(self.cf.dim) backbone = utils.import_module('bbone', self.cf.backbone_path) # build Anchors, FPN, Classifier / Bbox-Regressor -head self.np_anchors = mutils.generate_pyramid_anchors(self.logger, self.cf) self.anchors = torch.from_numpy(self.np_anchors).float().cuda() # self.Fpn = backbone.FPN(self.cf, conv, operate_stride1=self.cf.operate_stride1) self.num_classes=self.cf.head_classes # i3d_rgb = backbone.I3D(num_classes=self.num_classes) ######## HEART OF I3D RGB Weight Transfer # print("Transferring weight from i3d_rgb model...........") # i3d_rgb = backbone.I3D(num_classes=self.num_classes) # i3d_rgb.load_state_dict(torch.load('weight/model_rgb.pth'), strict=False) # print('Success..........') # self.Fpn = i3d_rgb self.Fpn = backbone.I3D(num_classes=self.num_classes) self.Classifier = Classifier(self.cf, conv) self.BBRegressor = BBRegressor(self.cf, conv)
def build(self): """Build Retina Net architecture.""" # Image size must be dividable by 2 multiple times. h, w = self.cf.patch_size[:2] if h / 2 ** 5 != int(h / 2 ** 5) or w / 2 ** 5 != int(w / 2 ** 5): raise Exception("Image size must be divisible by 2 at least 5 times " "to avoid fractions when downscaling and upscaling." "For example, use 256, 320, 384, 448, 512, ... etc. ") backbone = utils.import_module('bbone', self.cf.backbone_path) self.logger.info("loaded backbone from {}".format(self.cf.backbone_path)) conv = backbone.ConvGenerator(self.cf.dim) # build Anchors, FPN, Classifier / Bbox-Regressor -head self.np_anchors = mutils.generate_pyramid_anchors(self.logger, self.cf) self.anchors = torch.from_numpy(self.np_anchors).float().cuda() self.fpn = backbone.FPN(self.cf, conv, operate_stride1=self.cf.operate_stride1).cuda() self.classifier = Classifier(self.cf, conv).cuda() self.bb_regressor = BBRegressor(self.cf, conv).cuda() if 'regression' in self.cf.prediction_tasks: self.roi_regressor = RoIRegressor(self.cf, conv, self.cf.regression_n_features).cuda() elif 'regression_bin' in self.cf.prediction_tasks: # classify into bins of regression values self.roi_regressor = RoIRegressor(self.cf, conv, len(self.cf.bin_labels)).cuda() else: self.roi_regressor = lambda x: [torch.tensor([]).cuda()] if self.cf.model == 'retina_unet': self.final_conv = conv(self.cf.end_filts, self.cf.num_seg_classes, ks=1, pad=0, norm=None, relu=None)
def build(self): """Build Mask R-CNN architecture.""" # Image size must be dividable by 2 multiple times. h, w = self.cf.patch_size[:2] if h / 2**5 != int(h / 2**5) or w / 2**5 != int(w / 2**5): raise Exception( "Image size must be divisible by 2 at least 5 times " "to avoid fractions when downscaling and upscaling." "For example, use 256, 288, 320, 384, 448, 512, ... etc.,i.e.," "any number x*32 will do!") # instantiate abstract multi-dimensional conv generator and load backbone module. backbone = utils.import_module('bbone', self.cf.backbone_path) self.logger.info("loaded backbone from {}".format( self.cf.backbone_path)) conv = backbone.ConvGenerator(self.cf.dim) # build Anchors, FPN, RPN, Classifier / Bbox-Regressor -head, Mask-head self.np_anchors = mutils.generate_pyramid_anchors(self.logger, self.cf) self.anchors = torch.from_numpy(self.np_anchors).float().cuda() self.fpn = backbone.FPN(self.cf, conv, relu_enc=self.cf.relu, operate_stride1=False).cuda() self.rpn = RPN(self.cf, conv) self.classifier = Classifier(self.cf, conv) self.mask = Mask(self.cf, conv)
def build(self): # build Anchors, FPN, Classifier / Bbox-Regressor -head self.np_anchors = mutils.generate_pyramid_anchors(self.logger, self.cf) self.anchors = torch.from_numpy(self.np_anchors).float().cuda() self.Fpn = backbone.FPN( input_channels= 7, # (3*2+1)feed +/- 3 neighbouring slices into channel dimension. start_filts=48, out_channels=192, res_architecture='resnet50', dropout=self.mc_var) self.Classifier = Classifier(n_input_channels=192, n_features=256, n_classes=2, pred_var=self.pred_var) self.BBRegressor = BBRegressor(n_input_channels=192, n_features=256, anchor_stride=1)