|
import importlib |
|
|
|
import torch |
|
import numpy as np |
|
from tqdm import tqdm |
|
from inspect import isfunction |
|
from PIL import Image, ImageDraw, ImageFont |
|
import hashlib |
|
import requests |
|
import os |
|
|
|
URL_MAP = { |
|
'vggishish_lpaps': 'https://a3s.fi/swift/v1/AUTH_a235c0f452d648828f745589cde1219a/specvqgan_public/vggishish16.pt', |
|
'vggishish_mean_std_melspec_10s_22050hz': 'https://a3s.fi/swift/v1/AUTH_a235c0f452d648828f745589cde1219a/specvqgan_public/train_means_stds_melspec_10s_22050hz.txt', |
|
'melception': 'https://a3s.fi/swift/v1/AUTH_a235c0f452d648828f745589cde1219a/specvqgan_public/melception-21-05-10T09-28-40.pt', |
|
} |
|
|
|
CKPT_MAP = { |
|
'vggishish_lpaps': 'vggishish16.pt', |
|
'vggishish_mean_std_melspec_10s_22050hz': 'train_means_stds_melspec_10s_22050hz.txt', |
|
'melception': 'melception-21-05-10T09-28-40.pt', |
|
} |
|
|
|
MD5_MAP = { |
|
'vggishish_lpaps': '197040c524a07ccacf7715d7080a80bd', |
|
'vggishish_mean_std_melspec_10s_22050hz': 'f449c6fd0e248936c16f6d22492bb625', |
|
'melception': 'a71a41041e945b457c7d3d814bbcf72d', |
|
} |
|
|
|
|
|
def download(url, local_path, chunk_size=1024): |
|
os.makedirs(os.path.split(local_path)[0], exist_ok=True) |
|
with requests.get(url, stream=True) as r: |
|
total_size = int(r.headers.get("content-length", 0)) |
|
with tqdm(total=total_size, unit="B", unit_scale=True) as pbar: |
|
with open(local_path, "wb") as f: |
|
for data in r.iter_content(chunk_size=chunk_size): |
|
if data: |
|
f.write(data) |
|
pbar.update(chunk_size) |
|
|
|
|
|
def md5_hash(path): |
|
with open(path, "rb") as f: |
|
content = f.read() |
|
return hashlib.md5(content).hexdigest() |
|
|
|
|
|
|
|
def log_txt_as_img(wh, xc, size=10): |
|
|
|
|
|
b = len(xc) |
|
txts = list() |
|
for bi in range(b): |
|
txt = Image.new("RGB", wh, color="white") |
|
draw = ImageDraw.Draw(txt) |
|
font = ImageFont.truetype('data/DejaVuSans.ttf', size=size) |
|
nc = int(40 * (wh[0] / 256)) |
|
lines = "\n".join(xc[bi][start:start + nc] for start in range(0, len(xc[bi]), nc)) |
|
|
|
try: |
|
draw.text((0, 0), lines, fill="black", font=font) |
|
except UnicodeEncodeError: |
|
print("Cant encode string for logging. Skipping.") |
|
|
|
txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0 |
|
txts.append(txt) |
|
txts = np.stack(txts) |
|
txts = torch.tensor(txts) |
|
return txts |
|
|
|
|
|
def ismap(x): |
|
if not isinstance(x, torch.Tensor): |
|
return False |
|
return (len(x.shape) == 4) and (x.shape[1] > 3) |
|
|
|
|
|
def isimage(x): |
|
if not isinstance(x,torch.Tensor): |
|
return False |
|
return (len(x.shape) == 4) and (x.shape[1] == 3 or x.shape[1] == 1) |
|
|
|
|
|
def exists(x): |
|
return x is not None |
|
|
|
|
|
def default(val, d): |
|
if exists(val): |
|
return val |
|
return d() if isfunction(d) else d |
|
|
|
|
|
def mean_flat(tensor): |
|
""" |
|
https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/nn.py#L86 |
|
Take the mean over all non-batch dimensions. |
|
""" |
|
return tensor.mean(dim=list(range(1, len(tensor.shape)))) |
|
|
|
|
|
def count_params(model, verbose=False): |
|
total_params = sum(p.numel() for p in model.parameters()) |
|
if verbose: |
|
print(f"{model.__class__.__name__} has {total_params*1.e-6:.2f} M params.") |
|
return total_params |
|
|
|
|
|
def instantiate_from_config(config,reload=False): |
|
if not "target" in config: |
|
if config == '__is_first_stage__': |
|
return None |
|
elif config == "__is_unconditional__": |
|
return None |
|
raise KeyError("Expected key `target` to instantiate.") |
|
return get_obj_from_str(config["target"],reload=reload)(**config.get("params", dict())) |
|
|
|
|
|
def get_obj_from_str(string, reload=False): |
|
module, cls = string.rsplit(".", 1) |
|
if reload: |
|
module_imp = importlib.import_module(module) |
|
importlib.reload(module_imp) |
|
return getattr(importlib.import_module(module, package=None), cls) |
|
|
|
def get_ckpt_path(name, root, check=False): |
|
assert name in URL_MAP |
|
path = os.path.join(root, CKPT_MAP[name]) |
|
if not os.path.exists(path) or (check and not md5_hash(path) == MD5_MAP[name]): |
|
print("Downloading {} model from {} to {}".format(name, URL_MAP[name], path)) |
|
download(URL_MAP[name], path) |
|
md5 = md5_hash(path) |
|
assert md5 == MD5_MAP[name], md5 |
|
return path |
|
|
