def build_paddle_model(): # * backbone backbone = 'resnet50' dilation = False position_embedding = 'sine' # * Transformer enc_layers = 6 dec_layers = 6 dim_feedforward = 2048 hidden_dim = 256 dropout = 0 nheads = 8 num_queries = 100 pre_norm = False num_classes = 91 position_embedding = PositionEmbeddingSine(hidden_dim // 2, normalize=True) backbone = Backbone(backbone, False, True, dilation) backbone = Joiner(backbone, position_embedding) backbone.num_channels = 2048 transformer = Transformer( d_model=hidden_dim, dropout=dropout, nhead=nheads, dim_feedforward=dim_feedforward, num_encoder_layers=enc_layers, num_decoder_layers=dec_layers, normalize_before=pre_norm, return_intermediate_dec=True) model = DETR(backbone, transformer, num_classes=num_classes, num_queries=num_queries, aux_loss=True) return model
def build_backbone(lr_backbone, masks, backbone, dilation, hidden_dim, position_embedding): position_embedding = build_position_encoding(hidden_dim, position_embedding) train_backbone = lr_backbone > 0 return_interm_layers = masks backbone = Backbone(backbone, train_backbone, return_interm_layers, dilation) model = Joiner(backbone, position_embedding) model.num_channels = backbone.num_channels return model
def test_transformer_forward(self): backbone = Backbone('resnet50', True, True, False) x = nested_tensor_from_tensor_list( [torch.rand(3, 200, 200), torch.rand(3, 200, 250)]) out = backbone(x) for key, value in out.items(): print('{} {}'.format(key, value.tensors.shape))
def build_backbone(): N_steps = 256 // 2 position_embedding = PositionEmbeddingSine(N_steps, normalize=True) train_backbone = True return_interm_layers = False backbone = Backbone('resnet50', train_backbone, return_interm_layers, False) model = Joiner(backbone, position_embedding) model.num_channels = backbone.num_channels return model
def build_backbone(): position_embedding = PositionEmbeddingSine(num_pos_feats=128, normalize=True) backbone = Backbone('resnet50', train_backbone=True, return_interm_layers=False, dilation=False) model = Joiner(backbone, position_embedding) model.num_channels = backbone.num_channels return model
def _make_detr(backbone_name: str, dilation=False, num_classes=91, mask=False): hidden_dim = 256 backbone = Backbone(backbone_name, train_backbone=True, return_interm_layers=mask, dilation=dilation) pos_enc = PositionEmbeddingSine(hidden_dim // 2, normalize=True) backbone_with_pos_enc = Joiner(backbone, pos_enc) backbone_with_pos_enc.num_channels = backbone.num_channels transformer = Transformer(d_model=hidden_dim, return_intermediate_dec=True) detr = DETR(backbone_with_pos_enc, transformer, num_classes=num_classes, num_queries=100) if mask: return DETRsegm(detr) return detr
def build_backbone(lr_backbone, masks, backbone, dilation, hidden_dim, position_embedding): position_embedding = build_position_encoding(hidden_dim, position_embedding) train_backbone = lr_backbone > 0 return_interm_layers = masks if 'resnet' in backbone: backbone = Backbone(backbone, train_backbone, return_interm_layers, dilation) elif 'mobilenet' in backbone: backbone = MNetBackbone(train_backbone, return_interm_layers) model = Joiner(backbone, position_embedding) model.num_channels = backbone.num_channels return model
def _make_backbone(backbone_name: str, mask: bool = False): if backbone_name[:len("timm_")] == "timm_": backbone = TimmBackbone( backbone_name[len("timm_"):], mask, main_layer=-1, group_norm=True, ) else: backbone = Backbone(backbone_name, train_backbone=True, return_interm_layers=mask, dilation=False) hidden_dim = 256 pos_enc = PositionEmbeddingSine(hidden_dim // 2, normalize=True) backbone_with_pos_enc = Joiner(backbone, pos_enc) backbone_with_pos_enc.num_channels = backbone.num_channels return backbone_with_pos_enc
def __init__(self, input_image_shape, num_classes, pos_threshold=0.5, neg_threshold=0.1, predict_conf_threshold=0.75, **kwargs): super(ObjectDetection, self).__init__(**kwargs) self.pos_threshold = pos_threshold self.neg_threshold = neg_threshold self.predict_conf_threshold = predict_conf_threshold self.num_classes = num_classes self.input_image_shape = input_image_shape # The feature counts / depth for each feature map considered # for the class regression head self.FEATURE_COUNTS = (64, ) # Anchor sizes (per layer) # The anchors sizes need to scale to cover the sizes of possible objects # in the dataset. # You can either set an absolute pixel value, or set based off size of image. width = input_image_shape[-1] self.ANCHOR_SIZES = ((width // 8, width // 4, width // 2, width), ) # These ratios are for all anchors self.ANCHOR_RATIOS = (1.0, 0.5, 2.0) self.backbone = Backbone() self.anchor_generator = AnchorGenerator( sizes=self.ANCHOR_SIZES, aspect_ratios=self.ANCHOR_RATIOS) self.box_prediction = BoxPrediction( num_features=self.FEATURE_COUNTS, num_class=num_classes, batch_norm=True, num_anchors=[ len(anchors) * len(self.ANCHOR_RATIOS) for anchors in self.ANCHOR_SIZES ]) self.loss = torch.nn.BCEWithLogitsLoss(reduce=False)
def test_backbone_script(self): backbone = Backbone('resnet50', True, False, False) torch.jit.script(backbone) # noqa
def __init__(self): super(Solo, self).__init__() self.backbone = Backbone() self.fpn = FPN() self.ins_head = InsHead() self.mask_head = MaskHead()
data_loader_train = DataLoader(dataset_train, batch_sampler=batch_sampler_train, collate_fn=utils.collate_fn_os, num_workers=args.num_workers) data_loader_val = DataLoader(dataset_train, args.batch_size, sampler=sampler_val, collate_fn=utils.collate_fn_os, drop_last=False, num_workers=args.num_workers) # %% BUILD MODEL position_embedding = build_position_encoding(args) train_backbone = args.lr_backbone > 0 base_backbone = Backbone(args.backbone, train_backbone, False, args.dilation) backbone = Joiner(base_backbone, position_embedding) backbone.num_channels = base_backbone.num_channels transformer = Transformer( d_model=args.hidden_dim, dropout=args.dropout, nhead=args.nheads, dim_feedforward=args.dim_feedforward, num_encoder_layers=args.enc_layers, num_decoder_layers=args.dec_layers, normalize_before=args.pre_norm, return_intermediate_dec=True, ) model = OSDETR( backbone,
def __init__(self, args): super(my_DETR, self).__init__() N_steps = args.hidden_dim // 2 if args.position_embedding in ('v2', 'sine'): # TODO find a better way of exposing other arguments position_embedding = PositionEmbeddingSine(N_steps, normalize=True) elif args.position_embedding in ('v3', 'learned'): position_embedding = PositionEmbeddingLearned(N_steps) else: raise ValueError(f"not supported {args.position_embedding}") train_backbone = args.lr_backbone > 0 return_interm_layers = args.masks backbone = Backbone(args.backbone, train_backbone, return_interm_layers, args.dilation) joiner = Joiner(backbone, position_embedding) joiner.num_channels = backbone.num_channels transformer = Transformer( d_model=args.hidden_dim, dropout=args.dropout, nhead=args.nheads, dim_feedforward=args.dim_feedforward, num_encoder_layers=args.enc_layers, num_decoder_layers=args.dec_layers, normalize_before=args.pre_norm, return_intermediate_dec=True, ) num_classes = 20 if args.dataset_file != 'coco' else 91 if args.dataset_file == "coco_panoptic": num_classes = 250 matcher = build_matcher(args) weight_dict = {'loss_ce': 1, 'loss_bbox': args.bbox_loss_coef} weight_dict['loss_giou'] = args.giou_loss_coef # if args.masks: # weight_dict["loss_mask"] = args.mask_loss_coef # weight_dict["loss_dice"] = args.dice_loss_coef # TODO this is a hack if args.aux_loss: aux_weight_dict = {} for i in range(args.dec_layers - 1): aux_weight_dict.update( {k + f'_{i}': v for k, v in weight_dict.items()}) weight_dict.update(aux_weight_dict) losses = ['labels', 'boxes', 'cardinality'] if args.masks: losses += ["masks"] self.criterion = SetCriterion(num_classes, matcher=matcher, weight_dict=weight_dict, eos_coef=args.eos_coef, losses=losses) self.num_queries = args.num_queries self.transformer = transformer hidden_dim = transformer.d_model self.class_embed = nn.Linear(hidden_dim, num_classes + 1) self.bbox_embed = MLP(hidden_dim, hidden_dim, 4, 3) self.query_embed = nn.Embedding(args.num_queries, hidden_dim) self.input_proj = nn.Conv2d(joiner.num_channels, hidden_dim, kernel_size=1) self.backbone = joiner self.aux_loss = args.aux_loss