"""Eval conv deep head from checkpoint."""
import os, sys, time, torch
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from train_conv_deep import DeepConvHead, cofiber_decompose, make_locations

DEVICE = "cuda"
COCO_ROOT = os.environ["ARENA_COCO_ROOT"]
VAL_CACHE = os.environ["ARENA_VAL_CACHE"]

head = DeepConvHead(hidden=256, n_blocks=10).to(DEVICE)
ckpt = torch.load(os.path.join(os.path.dirname(__file__), "heads", "cofiber_threshold", "conv_deep", "conv_deep_256h_10b_step12000.pth"), map_location=DEVICE, weights_only=False)
head.load_state_dict(ckpt["head"])
head.eval()
print(f"Loaded step {ckpt['step']}, {sum(p.numel() for p in head.parameters()):,} params")

val = torch.load(VAL_CACHE, map_location="cpu", weights_only=False)
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
coco_gt = COCO(os.path.join(COCO_ROOT, "annotations", "instances_val2017.json"))
cat_ids = sorted(coco_gt.getCatIds())
idx_to_cat = {i: c for i, c in enumerate(cat_ids)}
strides = [16, 32, 64]; H = 640 // 16
all_locs = torch.cat(make_locations([(H,H),(H//2,H//2),(H//4,H//4)], strides, torch.device(DEVICE)))

all_results = []
t0 = time.time()
with torch.no_grad():
    for idx in range(len(val)):
        item = val[idx]
        spatial = item["spatial"].unsqueeze(0).float().to(DEVICE)
        img_id = int(item["img_id"]); scale = item["scale"]
        cls_l, reg_l, ctr_l = head(spatial)
        cls_s = torch.cat([c.permute(0,2,3,1).reshape(-1, 80) for c in cls_l]).sigmoid()
        reg_s = torch.cat([r.permute(0,2,3,1).reshape(-1, 4) for r in reg_l])
        ctr_s = torch.cat([c.permute(0,2,3,1).reshape(-1) for c in ctr_l]).sigmoid()
        scores = cls_s * ctr_s.unsqueeze(1)
        max_s, max_c = scores.max(1)
        topk = min(100, max_s.shape[0])
        top_s, top_i = max_s.topk(topk)
        tc=max_c[top_i]; tr=reg_s[top_i]; tl=all_locs[top_i]
        x1=(tl[:,0]-tr[:,0])/scale; y1=(tl[:,1]-tr[:,1])/scale
        x2=(tl[:,0]+tr[:,2])/scale; y2=(tl[:,1]+tr[:,3])/scale
        w=(x2-x1).clamp(min=0); h=(y2-y1).clamp(min=0)
        for i in range(topk):
            s = top_s[i].item()
            if s < 0.01: continue
            all_results.append({"image_id": img_id, "category_id": idx_to_cat[tc[i].item()],
                                "bbox": [x1[i].item(), y1[i].item(), w[i].item(), h[i].item()],
                                "score": s})
        if (idx+1) % 1000 == 0:
            print(f"  {idx+1}/{len(val)} ({time.time()-t0:.0f}s)", flush=True)

print(f"\n{len(all_results)} detections")
coco_dt = coco_gt.loadRes(all_results)
ev = COCOeval(coco_gt, coco_dt, "bbox")
ev.params.imgIds = sorted(coco_gt.getImgIds())[:len(val)]
ev.evaluate(); ev.accumulate(); ev.summarize()
print(f"\nConv Deep 256h 10b (step 12000): mAP={ev.stats[0]:.4f} mAP50={ev.stats[1]:.4f} mAP75={ev.stats[2]:.4f}")