import json, random, collections, urllib.request, os
d = json.load(open("instances_val2017.json"))
cats = {c["id"]: c["name"] for c in d["categories"]}
imgs = {i["id"]: i for i in d["images"]}
by = collections.defaultdict(list)
for a in d["annotations"]:
    if a["iscrowd"]: continue
    by[a["image_id"]].append(a)
rng = random.Random(0); cand = []
for iid, anns in sorted(by.items()):
    W, H = imgs[iid]["width"], imgs[iid]["height"]
    cnt = collections.Counter(a["category_id"] for a in anns)
    cid, n = cnt.most_common(1)[0]
    g = [a for a in anns if a["category_id"] == cid]
    if not (1 <= n <= 8): continue
    if any(a["bbox"][2] * a["bbox"][3] < 32 * 32 for a in g): continue
    boxes = [[a["bbox"][0]/W*1000, a["bbox"][1]/H*1000, (a["bbox"][0]+a["bbox"][2])/W*1000, (a["bbox"][1]+a["bbox"][3])/H*1000] for a in g]
    cand.append({"id": iid, "file": "img/%012d.jpg" % iid, "cat": cats[cid], "n_gt": n, "boxes": boxes, "w": W, "h": H})
rng.shuffle(cand); sel = cand[:100]
for s in sel:
    if not os.path.exists(s["file"]):
        urllib.request.urlretrieve("http://images.cocodataset.org/val2017/%012d.jpg" % s["id"], s["file"])
json.dump(sel, open("eval_set.json", "w"))
print("candidates", len(cand), "selected", len(sel), "mean GT/img", sum(s["n_gt"] for s in sel)/len(sel))
print(collections.Counter(s["cat"] for s in sel).most_common(8))