{"cells":[{"cell_type":"markdown","id":"a5-title","metadata":{},"source":"# RSNA Knee — Cross-Series A5 only\n\n元NotebookのStage 2のみで`/kaggle/working/submission.csv`を生成します。\nStage 1のDINOv2予測との重み付き融合（`A5_W = 0.45`）だけを除外しています。"},{"cell_type":"code","execution_count":null,"id":"a5-bootstrap","metadata":{},"outputs":[],"source":"# Exact Kaggle competition-path resolution inherited from the source notebook.\nimport os as _os\nfrom pathlib import Path as _A5Path\n\ndef _comp_root():\n    for _c in (\"/kaggle/input/competitions/rsna-knee-abnormality-detection\",\n               \"/kaggle/input/rsna-knee-abnormality-detection\"):\n        if _os.path.isdir(_c):\n            return _c\n    raise RuntimeError(\"competition data not found under /kaggle/input\")\n\n_COMP_ROOT = _comp_root()\nASSET = _A5Path('/kaggle/input/rsna-knee-bend-dinov3-0917-repro-assets')\n"},{"id":"fbd0db92","cell_type":"markdown","source":"## Stage 2: Cross-Series Spatial Attention Arm A5 (Score: 0.910)\n- Evaluates 5-fold cross-series spatial attention (`vit_small_patch16_dinov3.lvd1689m`) across 16 slices per slot.\n- Blends with Stage 1 using verified rank weighting ($W=0.45$).\n","metadata":{}},{"cell_type":"code","execution_count":null,"id":"a5-code","metadata":{},"outputs":[],"source":"_A5_SAVED = dict(globals())\nimport gc, os, time, warnings\nfrom concurrent.futures import ProcessPoolExecutor, as_completed\nfrom pathlib import Path\nimport cv2\nimport numpy as np\nimport pandas as pd\nimport pydicom\nimport timm\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nwarnings.filterwarnings('ignore')\ncv2.setNumThreads(1)\nCROP_MM = 130.0\nSIZE = 336\nSLICE_BAND = (0.12, 0.88)\nN_SLICE = 16\nINTENSITY = 'slice'\nSLOTS = [('Sagittal', 1), ('Sagittal', 0), ('Coronal', 1), ('Coronal', 0), ('Axial', 1), ('Axial', 0)]\nN_SLOT = len(SLOTS)\nLABELS = ['ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus', 'Medial OA', 'Lateral OA', 'PF OA', 'Effusion', 'Synovitis', \"Baker's\", 'Contusion', 'Fracture']\nCOMP = Path(_COMP_ROOT)\ndef _find_a5_ckpt():\n    candidates = [\n        Path('/kaggle/input/datasets/mattiaangeli/knee-mri-fold-weights'),\n        Path('/kaggle/input/knee-mri-fold-weights'),\n        Path('/kaggle/input/rsna-knee-bend-dinov3-0917-repro-assets/knee-mri-fold-weights'),\n        Path('/kaggle/input/rsna-knee-bend-dinov3-0917-repro-assets'),\n        ASSET / 'knee-mri-fold-weights',\n    ]\n    for c in candidates:\n        if list(c.glob('*_f*.pt')):\n            return c\n    for p in Path('/kaggle/input').glob('**/*_f*.pt'):\n        if 'm_f' in p.name or 'fold' in str(p).lower():\n            return p.parent\n    return candidates[0]\nCKPT = _find_a5_ckpt()\nDEV = 'cuda' if torch.cuda.is_available() else 'cpu'\nprint(f'competition : {COMP}')\nprint(f'checkpoints : {CKPT}')\nprint(f'device      : {DEV}')\nfor i in range(torch.cuda.device_count() if DEV == 'cuda' else 0):\n    cc = torch.cuda.get_device_capability(i)\n    print(f'  gpu{i}       : {torch.cuda.get_device_name(i)} sm_{cc[0]}{cc[1]}, {torch.cuda.get_device_properties(i).total_memory / 2 ** 30:.0f} GiB, native bf16={cc >= (8, 0)}')\nSERIES_ROOT = COMP / 'test_series'\nif not SERIES_ROOT.exists():\n    SERIES_ROOT = COMP / 'train_series'\nprint('series root:', SERIES_ROOT)\n\ndef ordered_files(sdir, cap=64):\n    keyed = []\n    for f in sdir.glob('*.dcm'):\n        try:\n            ds = pydicom.dcmread(str(f), stop_before_pixels=True)\n            keyed.append((int(ds.InstanceNumber), str(f)))\n        except Exception:\n            continue\n        if len(keyed) >= cap * 4:\n            break\n    return [f for _, f in sorted(keyed)]\n\ndef series_side(path):\n    try:\n        return float(pydicom.dcmread(path, stop_before_pixels=True).ImagePositionPatient[0])\n    except Exception:\n        return 0.0\n\ndef read_crop(path):\n    try:\n        ds = pydicom.dcmread(path)\n        arr = ds.pixel_array.astype(np.float32)\n    except Exception:\n        return None\n    try:\n        ps = float(ds.PixelSpacing[0])\n    except Exception:\n        ps = CROP_MM / max(arr.shape)\n    half = int(round(CROP_MM / ps / 2))\n    cy, cx = (arr.shape[0] // 2, arr.shape[1] // 2)\n    y0, y1 = (max(0, cy - half), min(arr.shape[0], cy + half))\n    x0, x1 = (max(0, cx - half), min(arr.shape[1], cx + half))\n    crop = arr[y0:y1, x0:x1]\n    return None if crop.size == 0 else crop\n\ndef window(crop, lo, hi, flip):\n    c = np.clip((crop - lo) / max(hi - lo, 1e-06), 0, 1)\n    img = cv2.resize(c, (SIZE, SIZE), interpolation=cv2.INTER_AREA)\n    return img[:, ::-1].copy() if flip else img\n\ndef render(path, flip):\n    crop = read_crop(path)\n    if crop is None:\n        return None\n    lo, hi = np.percentile(crop[::4, ::4], [1, 99])\n    return window(crop, lo, hi, flip)\n\ndef build_study(args):\n    idx, study, recs = args\n    out = np.zeros((N_SLOT, N_SLICE, SIZE, SIZE), np.uint8)\n    mask = np.zeros(N_SLOT, np.uint8)\n    rows = pd.DataFrame(recs)\n    if len(rows):\n        for s_i, (plane, fs) in enumerate(SLOTS):\n            sub = rows[(rows.Anatomical_Plane == plane) & (rows.Fat_Suppression == fs)]\n            if sub.empty:\n                continue\n            files = ordered_files(SERIES_ROOT / study / sub.iloc[0].SeriesInstanceUID)\n            if not files:\n                continue\n            flip = plane != 'Sagittal' and series_side(files[0]) < 0\n            lo, hi = SLICE_BAND\n            i0 = int(round(lo * (len(files) - 1)))\n            i1 = int(round(hi * (len(files) - 1)))\n            avail = list(range(i0, i1 + 1))\n            if len(avail) >= N_SLICE:\n                picks = [avail[int(round(t))] for t in np.linspace(0, len(avail) - 1, N_SLICE)]\n                off = 0\n            else:\n                picks, off = (avail, (N_SLICE - len(avail)) // 2)\n            if INTENSITY == 'series':\n                crops = [read_crop(files[p]) for p in picks]\n                got = [x for x in crops if x is not None]\n                if got:\n                    samp = np.concatenate([x[::4, ::4].ravel() for x in got])\n                    lo_, hi_ = np.percentile(samp, [1, 99])\n                    for c, x in enumerate(crops):\n                        if x is None:\n                            x = read_crop(files[min(len(files) - 1, picks[c] + 1)])\n                        if x is not None:\n                            out[s_i, off + c] = (window(x, lo_, hi_, flip) * 255).astype(np.uint8)\n            else:\n                for c, p in enumerate(picks):\n                    img = render(files[p], flip)\n                    if img is None:\n                        img = render(files[min(len(files) - 1, p + 1)], flip)\n                    if img is not None:\n                        out[s_i, off + c] = (img * 255).astype(np.uint8)\n            mask[s_i] = len(picks)\n    return (idx, out, mask)\nsub_df = pd.read_csv(COMP / 'sample_submission.csv')\nser_csv = pd.read_csv(COMP / 'test_series.csv')\nif not (COMP / 'test_series').exists():\n    ser_csv = pd.read_csv(COMP / 'train_series.csv')\nser_csv = ser_csv.loc[:, ~ser_csv.columns.duplicated()]\nstudies = sub_df.StudyInstanceUID.tolist()\nby = {s: g.to_dict('records') for s, g in ser_csv[ser_csv.StudyInstanceUID.isin(set(studies))].groupby('StudyInstanceUID')}\nprint(f'{len(studies):,} test studies, {len(by):,} with series metadata')\nN_SLOT_TYPES, MASK_IDX = (6, 0)\n\ndef segment_softmax(scores, sidx, B):\n    T, K = scores.shape\n    idx = sidx.unsqueeze(1).expand(-1, K)\n    m = torch.full((B, K), float('-inf'), device=scores.device, dtype=scores.dtype)\n    m = m.scatter_reduce(0, idx, scores, reduce='amax', include_self=True)\n    e = (scores - m[sidx]).exp()\n    s = torch.zeros(B, K, device=scores.device, dtype=scores.dtype).index_add_(0, sidx, e)\n    return e / s[sidx].clamp(min=1e-06)\n\nclass MeanMaxPool(nn.Module):\n\n    def forward(self, f, sidx, B, slot=None, return_attn=False):\n        D = f.shape[1]\n        cnt = torch.zeros(B, device=f.device, dtype=f.dtype).index_add_(0, sidx, torch.ones(f.shape[0], device=f.device, dtype=f.dtype))\n        mean = torch.zeros(B, D, device=f.device, dtype=f.dtype).index_add_(0, sidx, f)\n        mean = mean / cnt.clamp(min=1).unsqueeze(1)\n        mx = torch.full((B, D), -10000.0, device=f.device, dtype=f.dtype)\n        mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), f, reduce='amax', include_self=True)\n        return (torch.cat([mean, mx], 1), None)\n\nclass LabelAttentionPool(nn.Module):\n\n    def __init__(self, d, n_labels=12, n_heads=4, slot_bias=True):\n        super().__init__()\n        self.d, self.k, self.h = (d, n_labels, n_heads)\n        self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n        self.key, self.val = (nn.Linear(d, d), nn.Linear(d, d))\n        self.slot_bias = nn.Parameter(torch.zeros(n_labels, N_SLOT_TYPES + 1)) if slot_bias else None\n\n    def forward(self, f, sidx, B, slot=None, return_attn=False):\n        scores = self.key(f) @ self.q.t() / self.d ** 0.5\n        if self.slot_bias is not None and slot is not None:\n            scores = scores + self.slot_bias.t()[slot]\n        a = segment_softmax(scores, sidx, B)\n        out = torch.zeros(B, self.k, self.d, device=f.device, dtype=f.dtype)\n        out = out.index_add_(0, sidx, a.unsqueeze(-1) * self.val(f).unsqueeze(1))\n        return (out, a)\n\nclass TokenXAttnPool(nn.Module):\n\n    def __init__(self, d, n_labels=12, n_heads=6, dropout=0.2):\n        super().__init__()\n        self.d, self.k = (d, n_labels)\n        self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n        self.slot_emb = nn.Embedding(N_SLOT_TYPES + 1, d, padding_idx=0)\n        self.kv_norm = nn.LayerNorm(d)\n        self.attn = nn.MultiheadAttention(d, n_heads, dropout=dropout, batch_first=True)\n\n    def forward(self, tok, sidx, B, slot=None, return_attn=False):\n        T, N, D = tok.shape\n        cnt = torch.bincount(sidx, minlength=B)\n        S = int(cnt.max().item())\n        starts = torch.cumsum(cnt, 0) - cnt\n        pos = torch.arange(T, device=tok.device) - starts[sidx]\n        kv = tok + self.slot_emb(slot).unsqueeze(1)\n        pad = tok.new_zeros(B, S, N, D)\n        pad[sidx, pos] = kv\n        keep = torch.zeros(B, S, dtype=torch.bool, device=tok.device)\n        keep[sidx, pos] = True\n        kpm = ~keep.repeat_interleave(N, dim=1)\n        pad = self.kv_norm(pad.reshape(B, S * N, D))\n        q = self.q.unsqueeze(0).expand(B, -1, -1)\n        att, w = self.attn(q, pad, pad, key_padding_mask=kpm, need_weights=return_attn, average_attn_weights=True)\n        cls = tok[:, 0]\n        mean = torch.zeros(B, D, device=tok.device, dtype=tok.dtype).index_add_(0, sidx, cls) / cnt.clamp(min=1).unsqueeze(1)\n        mx = torch.full((B, D), -10000.0, device=tok.device, dtype=tok.dtype)\n        mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), cls, reduce='amax', include_self=True)\n        base = torch.cat([mean, mx], 1).unsqueeze(1).expand(-1, self.k, -1)\n        return (torch.cat([att, base], -1), w)\n\nclass ViTSlotToken(nn.Module):\n\n    def __init__(self, vit, n_cat, dim=None):\n        super().__init__()\n        self.vit = vit\n        d = dim or vit.embed_dim\n        self.tok = nn.Embedding(n_cat + 1, d, padding_idx=MASK_IDX)\n        self.num_features = vit.num_features\n        self._orig_prefix = getattr(vit, 'num_prefix_tokens', 1)\n        vit.num_prefix_tokens = self._orig_prefix + 1\n        for blk in vit.blocks:\n            a = getattr(blk, 'attn', None)\n            if a is not None and hasattr(a, 'num_prefix_tokens'):\n                a.num_prefix_tokens = a.num_prefix_tokens + 1\n\n    @staticmethod\n    def _maybe(mod, x):\n        return x if mod is None else mod(x)\n\n    def forward_features(self, x, cat):\n        v = self.vit\n        x = v.patch_embed(x)\n        pos = v._pos_embed(x)\n        rope = None\n        if isinstance(pos, tuple):\n            x, rope = pos\n        else:\n            x = pos\n        x = self._maybe(getattr(v, 'patch_drop', None), x)\n        x = self._maybe(getattr(v, 'norm_pre', None), x)\n        npt = self._orig_prefix\n        tok = self.tok(cat).unsqueeze(1)\n        x = torch.cat([x[:, :npt], tok, x[:, npt:]], dim=1)\n        if rope is not None:\n            if getattr(v, 'rope_mixed', False):\n                for i, blk in enumerate(v.blocks):\n                    x = blk(x, rope=rope[i])\n            else:\n                for blk in v.blocks:\n                    x = blk(x, rope=rope)\n        else:\n            x = v.blocks(x)\n        return v.norm(x)\n\n    def forward_head(self, x, pre_logits=True):\n        return self.vit.forward_head(x, pre_logits=pre_logits)\nIMAGENET_MEAN = (0.485, 0.456, 0.406)\nIMAGENET_STD = (0.229, 0.224, 0.225)\n\nclass _GatedDepthBlock(nn.Module):\n\n    def __init__(self, n_slice, dropout=0.0, ls_init=0.1):\n        super().__init__()\n        self.norm = nn.GroupNorm(1, n_slice)\n        self.v = nn.Conv2d(n_slice, n_slice, 1)\n        self.g = nn.Conv2d(n_slice, n_slice, 1)\n        self.out = nn.Conv2d(n_slice, n_slice, 1)\n        self.gamma = nn.Parameter(torch.full((n_slice, 1, 1), ls_init))\n        self.drop = nn.Dropout2d(dropout) if dropout else nn.Identity()\n\n    def forward(self, x):\n        z = self.norm(x)\n        return x + self.gamma * self.drop(self.out(self.v(z) * F.silu(self.g(z))))\n\nclass DepthCompress(nn.Module):\n\n    def __init__(self, n_slice=16, out_ch=3, depth=1, dropout=0.0, ls_init=0.1, imagenet=True, proj_noise=0.25):\n        super().__init__()\n        self.imagenet = imagenet\n        self.blocks = nn.ModuleList([_GatedDepthBlock(n_slice, dropout, ls_init) for _ in range(depth)])\n        self.proj = nn.Conv2d(n_slice, out_ch, 1, bias=True)\n        if imagenet:\n            self.register_buffer('mu', torch.tensor(IMAGENET_MEAN).view(1, -1, 1, 1))\n            self.register_buffer('sd', torch.tensor(IMAGENET_STD).view(1, -1, 1, 1))\n\n    def forward(self, x):\n        keep = (x.amax(dim=1, keepdim=True) > 0).to(x.dtype)\n        z = x\n        for b in self.blocks:\n            z = b(z)\n        z = self.proj(z)\n        if self.imagenet:\n            z = (z - self.mu.to(z.dtype)) / self.sd.to(z.dtype)\n        return z * keep\nN_PLANE, N_CONTRAST = (3, 2)\n_PLANE_OF = lambda s: torch.clamp(s - 1, 0, 5) // 2\n_CONTRAST_OF = lambda s: torch.clamp(s - 1, 0, 5) % 2\n\nclass SlotDepthMixer(nn.Module):\n\n    def __init__(self, n_slice=16, ksize=5, alpha_max=0.25):\n        super().__init__()\n        self.n_slice, self.ksize, self.r = (n_slice, ksize, ksize // 2)\n        self.alpha_max = alpha_max\n        b = torch.tensor([1.0, 4.0, 6.0, 4.0, 1.0])\n        self.register_buffer('base', b.log()[self.r:])\n        n_u = self.r + 1\n        self.shared = nn.Parameter(torch.zeros(n_u))\n        self.plane_k = nn.Parameter(torch.zeros(N_PLANE, n_u))\n        self.contrast_k = nn.Parameter(torch.zeros(N_CONTRAST, n_u))\n        self.g0 = nn.Parameter(torch.zeros(()))\n        self.gate_p = nn.Parameter(torch.zeros(N_PLANE))\n        self.gate_c = nn.Parameter(torch.zeros(N_CONTRAST))\n        idx = torch.arange(n_slice)\n        self.register_buffer('off', idx[None, :] - idx[:, None])\n\n    def kernel(self, slot):\n        p, c = (_PLANE_OF(slot), _CONTRAST_OF(slot))\n        half = self.base + self.shared + self.plane_k[p] + self.contrast_k[c]\n        full = torch.cat([half.flip(-1)[..., :self.r], half], dim=-1)\n        return F.softmax(full, dim=-1)\n\n    def alpha(self, slot):\n        p, c = (_PLANE_OF(slot), _CONTRAST_OF(slot))\n        return self.alpha_max * torch.tanh(self.g0 + self.gate_p[p] + self.gate_c[c])\n\n    def forward(self, x, slot, vmask):\n        T, S, H, W = x.shape\n        if vmask is None:\n            raise ValueError('stem=mixer requires the padding mask')\n        k = self.kernel(slot)\n        v = vmask.to(k.dtype)\n        d = self.off + self.r\n        inb = (d >= 0) & (d < self.ksize)\n        kk = k[:, d.clamp(0, self.ksize - 1)] * inb\n        M = kk * v[:, None, :]\n        den = M.sum(-1, keepdim=True)\n        eye = torch.eye(S, device=x.device, dtype=M.dtype).expand(T, S, S)\n        ok = (den > 1e-06) & v[:, :, None].bool()\n        M = torch.where(ok, M / den.clamp(min=1e-06), eye)\n        a = self.alpha(slot)[:, None, None]\n        Aop = ((1.0 - a) * eye + a * M).to(x.dtype)\n        if x.is_contiguous(memory_format=torch.channels_last) and (not x.is_contiguous()):\n            y = torch.bmm(x.permute(0, 2, 3, 1).reshape(T, H * W, S), Aop.transpose(1, 2))\n            return y.reshape(T, H, W, S).permute(0, 3, 1, 2)\n        return torch.bmm(Aop, x.reshape(T, S, H * W)).reshape(T, S, H, W)\n\ndef _seg_mean_max(v, sidx, B):\n    D = v.shape[1]\n    cnt = torch.zeros(B, device=v.device, dtype=v.dtype).index_add_(0, sidx, torch.ones(v.shape[0], device=v.device, dtype=v.dtype))\n    mean = torch.zeros(B, D, device=v.device, dtype=v.dtype).index_add_(0, sidx, v)\n    mean = mean / cnt.clamp(min=1).unsqueeze(1)\n    mx = torch.full((B, D), -10000.0, device=v.device, dtype=v.dtype)\n    mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), v, reduce='amax', include_self=True)\n    return torch.cat([mean, mx], 1)\n\ndef _pad_kv(x, sidx, B, norm):\n    T, P, D = x.shape\n    cnt = torch.bincount(sidx, minlength=B)\n    S = int(cnt.max().item())\n    starts = torch.cumsum(cnt, 0) - cnt\n    pos = torch.arange(T, device=x.device) - starts[sidx]\n    pad = x.new_zeros(B, S, P, D)\n    pad[sidx, pos] = x\n    keep = torch.zeros(B, S, dtype=torch.bool, device=x.device)\n    keep[sidx, pos] = True\n    return (norm(pad.reshape(B, S * P, D)), ~keep.repeat_interleave(P, dim=1))\n\nclass _GatedDelta(nn.Module):\n\n    def __init__(self, d, n_labels, n_heads, dropout):\n        super().__init__()\n        self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n        self.kv_norm = nn.LayerNorm(d)\n        self.attn = nn.MultiheadAttention(d, n_heads, dropout=dropout, batch_first=True)\n        self.d_norm = nn.LayerNorm(d)\n        self.dw = nn.Parameter(torch.randn(n_labels, d) * (1.0 / d ** 0.5))\n        self.db = nn.Parameter(torch.zeros(n_labels))\n        self.gate = nn.Parameter(torch.zeros(n_labels))\n\n    def delta(self, pat, sidx, B, return_attn):\n        kv, kpm = _pad_kv(pat, sidx, B, self.kv_norm)\n        q = self.q.unsqueeze(0).expand(B, -1, -1)\n        att, w = self.attn(q, kv, kv, key_padding_mask=kpm, need_weights=return_attn, average_attn_weights=True)\n        return ((self.d_norm(att) * self.dw).sum(-1) + self.db, w)\n\nclass TokenResidualPool(_GatedDelta):\n\n    def __init__(self, d, n_labels=12, n_heads=6, pe=64, dropout=0.2):\n        super().__init__(d, n_labels, n_heads, dropout)\n        self.base = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(dropout), nn.Linear(2 * d + pe, n_labels))\n\n    def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n        base = self.base(torch.cat([_seg_mean_max(tok[:, 1:].mean(1), sidx, B), pres], 1))\n        d_, w = self.delta(tok[:, 1:], sidx, B, return_attn)\n        return (base + self.gate * d_, w)\n\nclass CodexResidualPool(_GatedDelta):\n\n    def __init__(self, d, n_labels=12, n_heads=6, pe=64, dropout=0.2):\n        super().__init__(d, n_labels, n_heads, dropout)\n        self.base = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(dropout), nn.Linear(2 * d + pe, n_labels))\n\n    def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n        base = self.base(torch.cat([_seg_mean_max(tok[:, 0], sidx, B), pres], 1))\n        d_, w = self.delta(tok[:, 1:], sidx, B, return_attn)\n        return (base + self.gate * d_, w)\n\nclass ClsAddPool(nn.Module):\n\n    def __init__(self, d, n_labels=12, pe=64, dropout=0.2):\n        super().__init__()\n        self.net = nn.Sequential(nn.LayerNorm(4 * d + pe), nn.Dropout(dropout), nn.Linear(4 * d + pe, n_labels))\n\n    def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n        return (self.net(torch.cat([_seg_mean_max(tok[:, 1:].mean(1), sidx, B), _seg_mean_max(tok[:, 0], sidx, B), pres], 1)), None)\n\nclass Readout(nn.Module):\n\n    def __init__(self, pool, d, n_labels=12, pe=64):\n        super().__init__()\n        self.pool_kind, self.k = (pool, n_labels)\n        self.pres_emb = nn.Embedding(N_SLOT_TYPES + 1, pe, padding_idx=0)\n        if pool in ('xres', 'clsadd', 'xcodex'):\n            self.pool = {'xres': TokenResidualPool, 'clsadd': ClsAddPool, 'xcodex': CodexResidualPool}[pool](d, n_labels, pe=pe)\n        elif pool in ('attn', 'xattn'):\n            if pool == 'xattn':\n                self.pool = TokenXAttnPool(d, n_labels)\n                wd = 3 * d + pe\n            else:\n                self.pool = LabelAttentionPool(d, n_labels)\n                wd = d + pe\n            self.norm = nn.LayerNorm(wd)\n            self.w = nn.Parameter(torch.randn(n_labels, wd) * (1.0 / wd ** 0.5))\n            self.b = nn.Parameter(torch.zeros(n_labels))\n        else:\n            self.pool = MeanMaxPool()\n            self.net = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(0.2), nn.Linear(2 * d + pe, n_labels))\n        self.drop = nn.Dropout(0.2)\n\n    def forward(self, f, slot, sidx, B, return_attn=False):\n        pe = self.pres_emb(slot)\n        pres = torch.zeros(B, pe.shape[1], device=f.device, dtype=f.dtype).index_add_(0, sidx, pe)\n        if self.pool_kind in ('xres', 'clsadd', 'xcodex'):\n            return self.pool(f, slot, sidx, B, pres)[0]\n        pooled, attn = self.pool(f, sidx, B, slot=slot, return_attn=return_attn)\n        if self.pool_kind in ('attn', 'xattn'):\n            x = torch.cat([pooled, pres.unsqueeze(1).expand(-1, self.k, -1)], -1)\n            x = self.drop(self.norm(x))\n            return (x * self.w).sum(-1) + self.b\n        return self.net(torch.cat([pooled, pres], 1))\n\nclass Net(nn.Module):\n\n    def __init__(self, enc, cond, n_meta=0, pool='mean_max', stem='native', n_slice=16):\n        super().__init__()\n        self.enc, self.cond = (enc, cond)\n        self.compress = DepthCompress(n_slice, 3) if stem == 'compress' else None\n        self.mixer = SlotDepthMixer(n_slice) if stem == 'mixer' else None\n        self.tokens = pool in ('xattn', 'xres', 'clsadd', 'xcodex')\n        D = enc.num_features\n        self.meta_mlp = nn.Sequential(nn.LayerNorm(n_meta), nn.Linear(n_meta, 128), nn.GELU(), nn.Linear(128, D)) if n_meta > 0 else None\n        self.readout = Readout(pool, D)\n        if cond == 'post':\n            self.slot_emb = nn.Embedding(N_SLOT_TYPES + 1, D, padding_idx=MASK_IDX)\n\n    def forward(self, im, slot, smeta, sidx, B, vm=None):\n        if self.mixer is not None:\n            im = self.mixer(im, slot, vm)\n        if self.compress is not None:\n            im = self.compress(im)\n        f = self.enc.forward_features(im, slot) if self.cond == 'token' else self.enc.forward_features(im)\n        if self.tokens:\n            inner = getattr(self.enc, 'vit', self.enc)\n            orig = getattr(self.enc, '_orig_prefix', getattr(inner, 'num_prefix_tokens', 1))\n            f = torch.cat([f[:, :1], f[:, orig:]], 1)\n        else:\n            f = self.enc.forward_head(f, pre_logits=True)\n            if f.dim() > 2:\n                f = f.flatten(1)\n        ex = (lambda v: v.unsqueeze(1)) if self.tokens else lambda v: v\n        if self.cond == 'post':\n            f = f + ex(self.slot_emb(slot))\n        if self.meta_mlp is not None and smeta.shape[1] > 0:\n            mt = self.meta_mlp(smeta)\n            f = torch.cat([f, mt.unsqueeze(1)], 1) if self.tokens else f + mt\n        return self.readout(f, slot, sidx, B)\nmodels = []\nfor ckpt_path in sorted(CKPT.glob('*_f*.pt')):\n    z = torch.load(ckpt_path, map_location='cpu', weights_only=False)\n    cfg = z['cfg']\n    _stem = cfg.get('stem', 'native')\n    _in = 3 if _stem == 'compress' else cfg.get('n_slice', 16)\n    enc = timm.create_model(cfg['backbone'], pretrained=False, num_classes=0, in_chans=_in, **{'img_size': cfg['img']} if 'vit_' in cfg['backbone'] else {})\n    if cfg['cond'] == 'token':\n        enc = ViTSlotToken(enc, N_SLOT_TYPES)\n    m = Net(enc, cfg['cond'], cfg.get('n_meta', 0), cfg['pool'], stem=_stem, n_slice=cfg.get('n_slice', 16))\n    missing, unexpected = m.load_state_dict(z['state_dict'], strict=False)\n    assert not missing, f'missing {missing[:5]}'\n    assert not unexpected, f'unexpected {unexpected[:5]}'\n    models.append(m.eval())\n    print(f\"loaded {ckpt_path.name}  fold {z['fold']}  {cfg['backbone']} pool={cfg['pool']} meta={cfg['meta']}\")\nCFG = cfg if 'cfg' in locals() else {'norm': 'none', 'n_meta': 0}\nif len(models) > 0:\n    assert CFG.get('n_meta', 0) == 0, f\"checkpoint expects {CFG['n_meta']} metadata features -- build slot_meta for the TEST studies and pass it to predict() before submitting\"\nprint(f\"\\n{len(models)} fold models ready | input norm: {CFG.get('norm', 'none')}\")\nAMP_PREF = 'bf16'\n\ndef amp_for(dev):\n    if not str(dev).startswith('cuda'):\n        return (torch.float32, False)\n    cc = torch.cuda.get_device_capability(dev)\n    if AMP_PREF == 'bf16':\n        return (torch.bfloat16, True)\n    if AMP_PREF == 'fp16':\n        return (torch.float16, True)\n    if AMP_PREF == 'fp32':\n        return (torch.float32, False)\n    return (torch.bfloat16 if cc >= (8, 0) else torch.float16, True)\nAMP_DT, AMP_ON = amp_for(DEV)\nWORKERS = max(1, min(4, os.cpu_count() or 4))\nCHUNK = 48\nMICRO = 8\nmodels = [m.to(DEV).eval() for m in models]\nprint(f\"device {DEV} | amp {str(AMP_DT).split('.')[-1]} (on={AMP_ON}) | workers {WORKERS} | chunk {CHUNK} | micro {MICRO}\")\n\ndef _norm_(im):\n    k = CFG.get('norm', 'none')\n    if k == 'zscore':\n        m = (im > 0).float()\n        n = m.sum(dim=(1, 2, 3), keepdim=True).clamp(min=1.0)\n        mu = (im * m).sum(dim=(1, 2, 3), keepdim=True) / n\n        var = (((im - mu) * m) ** 2).sum(dim=(1, 2, 3), keepdim=True) / n\n        return (im - mu) / (var.sqrt() + 1e-06) * m\n    if k == 'imagenet':\n        m = (im > 0).float()\n        return (im - 0.485) / 0.229 * m\n    return im\n\n@torch.no_grad()\ndef _micro(images, masks):\n    dev = DEV\n    ims, slots, sidx, vms = ([], [], [], [])\n    for b in range(len(masks)):\n        present = np.nonzero(masks[b] > 0)[0]\n        if len(present) == 0:\n            continue\n        blk = images[b][present]\n        ims.append(torch.from_numpy(blk))\n        vms.append(torch.from_numpy(blk.reshape(blk.shape[0], blk.shape[1], -1).max(2) > 0))\n        slots.append(torch.from_numpy(present + 1).long())\n        sidx.append(torch.full((len(present),), b, dtype=torch.long))\n    out = np.full((len(models), len(masks), len(LABELS)), np.nan, np.float32)\n    if not ims:\n        return out\n    im = _norm_(torch.cat(ims).to(dev, non_blocking=True).float().div_(255.0))\n    sl = torch.cat(slots).to(dev)\n    si = torch.cat(sidx).to(dev)\n    vm = torch.cat(vms).to(dev)\n    sm = torch.zeros(len(sl), CFG.get('n_meta', 0), device=dev)\n    per = torch.zeros(len(models), len(masks), len(LABELS), device=dev, dtype=torch.float32)\n    with torch.autocast('cuda' if str(dev).startswith('cuda') else 'cpu', dtype=AMP_DT, enabled=AMP_ON):\n        for fold_index, model in enumerate(models):\n            per[fold_index] = torch.sigmoid(model(im, sl, sm, si, len(masks), vm=vm).float())\n    got = per.cpu().numpy()\n    keep = np.array([(masks[b] > 0).any() for b in range(len(masks))])\n    out[:, keep] = got[:, keep]\n    return out\n\ndef predict(images, masks):\n    out = np.full((len(models), len(masks), len(LABELS)), np.nan, np.float32)\n    for a in range(0, len(masks), MICRO):\n        b = min(a + MICRO, len(masks))\n        out[:, a:b] = _micro(images[a:b], masks[a:b])\n    return out\npreds = np.full((len(models), len(studies), len(LABELS)), np.nan, np.float32)\nt0, done = (time.time(), 0)\nwith ProcessPoolExecutor(max_workers=WORKERS) as ex:\n    for c0 in range(0, len(studies), CHUNK):\n        block = studies[c0:c0 + CHUNK]\n        imgs = np.zeros((len(block), N_SLOT, N_SLICE, SIZE, SIZE), np.uint8)\n        msks = np.zeros((len(block), N_SLOT), np.uint8)\n        futs = [ex.submit(build_study, (i, s, by.get(s, []))) for i, s in enumerate(block)]\n        for f in as_completed(futs):\n            try:\n                i, a, k = f.result()\n                imgs[i], msks[i] = (a, k)\n            except Exception as e:\n                print(f'  study failed: {type(e).__name__}: {e}')\n        preds[:, c0:c0 + len(block)] = predict(imgs, msks)\n        done += len(block)\n        el = time.time() - t0\n        print(f'  {done:,}/{len(studies):,}  {el / 60:.1f}m  eta {el / done * (len(studies) - done) / 60:.1f}m', flush=True)\n        del imgs, msks\n        gc.collect()\nprint(f'\\ninference done in {(time.time() - t0) / 60:.1f} min')\n# Standalone output: retain the original five-fold A5 aggregation, but do not\n# blend it with the DINOv2 submission produced by Stage 1.\n_a5_ok = np.isfinite(preds).all(axis=(0, 2))\n_a5_rank_mean = np.zeros((len(studies), len(LABELS)), np.float64)\nfor fold_index in range(preds.shape[0]):\n    fold = preds[fold_index][_a5_ok]\n    ordinal = fold.argsort(0).argsort(0).astype(np.float64)\n    _a5_rank_mean[_a5_ok] += ordinal / max(len(fold) - 1, 1)\n_a5_rank_mean /= preds.shape[0]\n_a5_rank_mean[~_a5_ok] = np.nan\n\n_a5_sub = sub_df[['StudyInstanceUID']].copy()\n_a5_sub[LABELS] = _a5_rank_mean\n_a5_sub[LABELS] = _a5_sub[LABELS].fillna(0.5)\nassert _a5_sub.columns.tolist() == ['StudyInstanceUID'] + LABELS\nassert np.isfinite(_a5_sub[LABELS].to_numpy()).all()\n_a5_sub.to_csv('/kaggle/working/submission.csv', index=False)\nprint(f'wrote /kaggle/working/submission.csv from Cross-Series A5 only; {_a5_sub.shape}')\n"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.10.12"}},"nbformat":4,"nbformat_minor":5}