File size: 1,934 Bytes
0966b6c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
import os
import torch
import argparse
import glob
parser = argparse.ArgumentParser(description='Pruning')
parser.add_argument('--ckpt', type=str, default=None, help='path to model ckpt')
args = parser.parse_args()
ckpt = args.ckpt
def prune_it(p, keep_only_ema=False):
print(f"prunin' in path: {p}")
size_initial = os.path.getsize(p)
nsd = dict()
sd = torch.load(p, map_location="cpu")
print(sd.keys())
for k in sd.keys():
if k != "optimizer_states":
nsd[k] = sd[k]
else:
print(f"removing optimizer states for path {p}")
if "global_step" in sd:
print(f"This is global step {sd['global_step']}.")
if keep_only_ema:
sd = nsd["state_dict"].copy()
# infer ema keys
ema_keys = {k: "model_ema." + k[6:].replace(".", ".") for k in sd.keys() if k.startswith("model.")}
new_sd = dict()
for k in sd:
if k in ema_keys:
new_sd[k] = sd[ema_keys[k]].half()
elif not k.startswith("model_ema.") or k in ["model_ema.num_updates", "model_ema.decay"]:
new_sd[k] = sd[k].half()
assert len(new_sd) == len(sd) - len(ema_keys)
nsd["state_dict"] = new_sd
else:
sd = nsd['state_dict'].copy()
new_sd = dict()
for k in sd:
new_sd[k] = sd[k].half()
nsd['state_dict'] = new_sd
fn = f"{os.path.splitext(p)[0]}-pruned.ckpt" if not keep_only_ema else f"{os.path.splitext(p)[0]}-ema-pruned.ckpt"
print(f"saving pruned checkpoint at: {fn}")
torch.save(nsd, fn)
newsize = os.path.getsize(fn)
MSG = f"New ckpt size: {newsize*1e-9:.2f} GB. " + \
f"Saved {(size_initial - newsize)*1e-9:.2f} GB by removing optimizer states"
if keep_only_ema:
MSG += " and non-EMA weights"
print(MSG)
if __name__ == "__main__":
prune_it(ckpt) |