scripts/train_detection.py [62:157]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - log_debug("\n%s", config_to_string(conf)) return conf def make_dataloader(args, config, rank, world_size): config = config["dataloader"] log_debug("Creating dataloaders for dataset in %s", args.data) # Training dataloader train_tf = ISSTransform(config.getint("shortest_size"), config.getint("longest_max_size"), config.getstruct("rgb_mean"), config.getstruct("rgb_std"), config.getboolean("random_flip"), config.getstruct("random_scale")) train_db = ISSDataset(args.data, config["train_set"], train_tf) train_sampler = DistributedARBatchSampler( train_db, config.getint("train_batch_size"), world_size, rank, True) train_dl = data.DataLoader(train_db, batch_sampler=train_sampler, collate_fn=iss_collate_fn, pin_memory=True, num_workers=config.getint("num_workers")) # Validation dataloader val_tf = ISSTransform(config.getint("shortest_size"), config.getint("longest_max_size"), config.getstruct("rgb_mean"), config.getstruct("rgb_std")) val_db = ISSDataset(args.data, config["val_set"], val_tf) val_sampler = DistributedARBatchSampler( val_db, config.getint("val_batch_size"), world_size, rank, False) val_dl = data.DataLoader(val_db, batch_sampler=val_sampler, collate_fn=iss_collate_fn, pin_memory=True, num_workers=config.getint("num_workers")) return train_dl, val_dl def make_model(config, num_thing, num_stuff): body_config = config["body"] fpn_config = config["fpn"] rpn_config = config["rpn"] roi_config = config["roi"] classes = {"total": num_thing + num_stuff, "stuff": num_stuff, "thing": num_thing} # BN + activation norm_act_static, norm_act_dynamic = norm_act_from_config(body_config) # Create backbone log_debug("Creating backbone model %s", body_config["body"]) body_fn = models.__dict__["net_" + body_config["body"]] body_params = body_config.getstruct("body_params") if body_config.get("body_params") else {} body = body_fn(norm_act=norm_act_static, **body_params) if body_config.get("weights"): body.load_state_dict(torch.load(body_config["weights"], map_location="cpu")) # Freeze parameters for n, m in body.named_modules(): for mod_id in range(1, body_config.getint("num_frozen") + 1): if ("mod%d" % mod_id) in n: freeze_params(m) body_channels = body_config.getstruct("out_channels") # Create FPN fpn_inputs = fpn_config.getstruct("inputs") fpn = FPN([body_channels[inp] for inp in fpn_inputs], fpn_config.getint("out_channels"), fpn_config.getint("extra_scales"), norm_act_static, fpn_config["interpolation"]) body = FPNBody(body, fpn, fpn_inputs) # Create RPN proposal_generator = ProposalGenerator(rpn_config.getfloat("nms_threshold"), rpn_config.getint("num_pre_nms_train"), rpn_config.getint("num_post_nms_train"), rpn_config.getint("num_pre_nms_val"), rpn_config.getint("num_post_nms_val"), rpn_config.getint("min_size")) anchor_matcher = AnchorMatcher(rpn_config.getint("num_samples"), rpn_config.getfloat("pos_ratio"), rpn_config.getfloat("pos_threshold"), rpn_config.getfloat("neg_threshold"), rpn_config.getfloat("void_threshold")) rpn_loss = RPNLoss(rpn_config.getfloat("sigma")) rpn_algo = RPNAlgoFPN( proposal_generator, anchor_matcher, rpn_loss, rpn_config.getint("anchor_scale"), rpn_config.getstruct("anchor_ratios"), fpn_config.getstruct("out_strides"), rpn_config.getint("fpn_min_level"), rpn_config.getint("fpn_levels")) rpn_head = RPNHead( fpn_config.getint("out_channels"), len(rpn_config.getstruct("anchor_ratios")), 1, rpn_config.getint("hidden_channels"), norm_act_dynamic) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - scripts/train_instance_seg.py [64:159]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - log_debug("\n%s", config_to_string(conf)) return conf def make_dataloader(args, config, rank, world_size): config = config["dataloader"] log_debug("Creating dataloaders for dataset in %s", args.data) # Training dataloader train_tf = ISSTransform(config.getint("shortest_size"), config.getint("longest_max_size"), config.getstruct("rgb_mean"), config.getstruct("rgb_std"), config.getboolean("random_flip"), config.getstruct("random_scale")) train_db = ISSDataset(args.data, config["train_set"], train_tf) train_sampler = DistributedARBatchSampler( train_db, config.getint("train_batch_size"), world_size, rank, True) train_dl = data.DataLoader(train_db, batch_sampler=train_sampler, collate_fn=iss_collate_fn, pin_memory=True, num_workers=config.getint("num_workers")) # Validation dataloader val_tf = ISSTransform(config.getint("shortest_size"), config.getint("longest_max_size"), config.getstruct("rgb_mean"), config.getstruct("rgb_std")) val_db = ISSDataset(args.data, config["val_set"], val_tf) val_sampler = DistributedARBatchSampler( val_db, config.getint("val_batch_size"), world_size, rank, False) val_dl = data.DataLoader(val_db, batch_sampler=val_sampler, collate_fn=iss_collate_fn, pin_memory=True, num_workers=config.getint("num_workers")) return train_dl, val_dl def make_model(config, num_thing, num_stuff): body_config = config["body"] fpn_config = config["fpn"] rpn_config = config["rpn"] roi_config = config["roi"] classes = {"total": num_thing + num_stuff, "stuff": num_stuff, "thing": num_thing} # BN + activation norm_act_static, norm_act_dynamic = norm_act_from_config(body_config) # Create backbone log_debug("Creating backbone model %s", body_config["body"]) body_fn = models.__dict__["net_" + body_config["body"]] body_params = body_config.getstruct("body_params") if body_config.get("body_params") else {} body = body_fn(norm_act=norm_act_static, **body_params) if body_config.get("weights"): body.load_state_dict(torch.load(body_config["weights"], map_location="cpu")) # Freeze parameters for n, m in body.named_modules(): for mod_id in range(1, body_config.getint("num_frozen") + 1): if ("mod%d" % mod_id) in n: freeze_params(m) body_channels = body_config.getstruct("out_channels") # Create FPN fpn_inputs = fpn_config.getstruct("inputs") fpn = FPN([body_channels[inp] for inp in fpn_inputs], fpn_config.getint("out_channels"), fpn_config.getint("extra_scales"), norm_act_static, fpn_config["interpolation"]) body = FPNBody(body, fpn, fpn_inputs) # Create RPN proposal_generator = ProposalGenerator(rpn_config.getfloat("nms_threshold"), rpn_config.getint("num_pre_nms_train"), rpn_config.getint("num_post_nms_train"), rpn_config.getint("num_pre_nms_val"), rpn_config.getint("num_post_nms_val"), rpn_config.getint("min_size")) anchor_matcher = AnchorMatcher(rpn_config.getint("num_samples"), rpn_config.getfloat("pos_ratio"), rpn_config.getfloat("pos_threshold"), rpn_config.getfloat("neg_threshold"), rpn_config.getfloat("void_threshold")) rpn_loss = RPNLoss(rpn_config.getfloat("sigma")) rpn_algo = RPNAlgoFPN( proposal_generator, anchor_matcher, rpn_loss, rpn_config.getint("anchor_scale"), rpn_config.getstruct("anchor_ratios"), fpn_config.getstruct("out_strides"), rpn_config.getint("fpn_min_level"), rpn_config.getint("fpn_levels")) rpn_head = RPNHead( fpn_config.getint("out_channels"), len(rpn_config.getstruct("anchor_ratios")), 1, rpn_config.getint("hidden_channels"), norm_act_dynamic) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -