scripts/train_detection.py [108:157]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    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_panoptic.py [121:170]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    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)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -