File size: 8,596 Bytes
5085882
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
import os
import json

import torch
import numpy as np

import audioldm_train.modules.hifigan as hifigan

import importlib

import torch
import numpy as np
from collections import abc

import multiprocessing as mp
from threading import Thread
from queue import Queue

from inspect import isfunction
from PIL import Image, ImageDraw, ImageFont
import json
with open('/content/qa-mdt/offset_pretrained_checkpoints.json', 'r') as config_file:
    config_data = json.load(config_file)

def log_txt_as_img(wh, xc, size=10):
    # wh a tuple of (width, height)
    # xc a list of captions to plot
    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 int16_to_float32(x):
    return (x / 32767.0).astype(np.float32)


def float32_to_int16(x):
    x = np.clip(x, a_min=-1.0, a_max=1.0)
    return (x * 32767.0).astype(np.int16)


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):
    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"])(**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 _do_parallel_data_prefetch(func, Q, data, idx, idx_to_fn=False):
    # create dummy dataset instance

    # run prefetching
    if idx_to_fn:
        res = func(data, worker_id=idx)
    else:
        res = func(data)
    Q.put([idx, res])
    Q.put("Done")


def parallel_data_prefetch(
    func: callable,
    data,
    n_proc,
    target_data_type="ndarray",
    cpu_intensive=True,
    use_worker_id=False,
):
    # if target_data_type not in ["ndarray", "list"]:
    #     raise ValueError(
    #         "Data, which is passed to parallel_data_prefetch has to be either of type list or ndarray."
    #     )
    if isinstance(data, np.ndarray) and target_data_type == "list":
        raise ValueError("list expected but function got ndarray.")
    elif isinstance(data, abc.Iterable):
        if isinstance(data, dict):
            print(
                f'WARNING:"data" argument passed to parallel_data_prefetch is a dict: Using only its values and disregarding keys.'
            )
            data = list(data.values())
        if target_data_type == "ndarray":
            data = np.asarray(data)
        else:
            data = list(data)
    else:
        raise TypeError(
            f"The data, that shall be processed parallel has to be either an np.ndarray or an Iterable, but is actually {type(data)}."
        )

    if cpu_intensive:
        Q = mp.Queue(1000)
        proc = mp.Process
    else:
        Q = Queue(1000)
        proc = Thread
    # spawn processes
    if target_data_type == "ndarray":
        arguments = [
            [func, Q, part, i, use_worker_id]
            for i, part in enumerate(np.array_split(data, n_proc))
        ]
    else:
        step = (
            int(len(data) / n_proc + 1)
            if len(data) % n_proc != 0
            else int(len(data) / n_proc)
        )
        arguments = [
            [func, Q, part, i, use_worker_id]
            for i, part in enumerate(
                [data[i : i + step] for i in range(0, len(data), step)]
            )
        ]
    processes = []
    for i in range(n_proc):
        p = proc(target=_do_parallel_data_prefetch, args=arguments[i])
        processes += [p]

    # start processes
    print(f"Start prefetching...")
    import time

    start = time.time()
    gather_res = [[] for _ in range(n_proc)]
    try:
        for p in processes:
            p.start()

        k = 0
        while k < n_proc:
            # get result
            res = Q.get()
            if res == "Done":
                k += 1
            else:
                gather_res[res[0]] = res[1]

    except Exception as e:
        print("Exception: ", e)
        for p in processes:
            p.terminate()

        raise e
    finally:
        for p in processes:
            p.join()
        print(f"Prefetching complete. [{time.time() - start} sec.]")

    if target_data_type == "ndarray":
        if not isinstance(gather_res[0], np.ndarray):
            return np.concatenate([np.asarray(r) for r in gather_res], axis=0)

        # order outputs
        return np.concatenate(gather_res, axis=0)
    elif target_data_type == "list":
        out = []
        for r in gather_res:
            out.extend(r)
        return out
    else:
        return gather_res


def get_available_checkpoint_keys(model, ckpt):
    print("==> Attemp to reload from %s" % ckpt)
    state_dict = torch.load(ckpt)["state_dict"]
    current_state_dict = model.state_dict()
    new_state_dict = {}
    for k in state_dict.keys():
        if (
            k in current_state_dict.keys()
            and current_state_dict[k].size() == state_dict[k].size()
        ):
            new_state_dict[k] = state_dict[k]
        else:
            print("==> WARNING: Skipping %s" % k)
    print(
        "%s out of %s keys are matched"
        % (len(new_state_dict.keys()), len(state_dict.keys()))
    )
    return new_state_dict


def get_param_num(model):
    num_param = sum(param.numel() for param in model.parameters())
    return num_param


def torch_version_orig_mod_remove(state_dict):
    new_state_dict = {}
    new_state_dict["generator"] = {}
    for key in state_dict["generator"].keys():
        if "_orig_mod." in key:
            new_state_dict["generator"][key.replace("_orig_mod.", "")] = state_dict[
                "generator"
            ][key]
        else:
            new_state_dict["generator"][key] = state_dict["generator"][key]
    return new_state_dict


def get_vocoder(config, device, mel_bins):
    ROOT = config_data["hifi-gan"]

    if mel_bins == 64:
        # import pdb  
        # pdb.set_trace()
        model_path = os.path.join(ROOT, "hifigan_16k_64bins")
        with open(model_path + ".json", "r") as f:
            config = json.load(f)
        config = hifigan.AttrDict(config)
        vocoder = hifigan.Generator(config)
    elif mel_bins == 256:
        model_path = os.path.join(ROOT, "hifigan_48k_256bins")
        with open(model_path + ".json", "r") as f:
            config = json.load(f)
        config = hifigan.AttrDict(config)
        vocoder = hifigan.Generator_HiFiRes(config)

    ckpt = torch.load(model_path + ".ckpt")
    ckpt = torch_version_orig_mod_remove(ckpt)
    vocoder.load_state_dict(ckpt["generator"])
    vocoder.eval()
    vocoder.remove_weight_norm()
    vocoder.to(device)
    return vocoder


def vocoder_infer(mels, vocoder, lengths=None):
    with torch.no_grad():
        wavs = vocoder(mels).squeeze(1)

    wavs = (wavs.cpu().numpy() * 32768).astype("int16")

    if lengths is not None:
        wavs = wavs[:, :lengths]

    return wavs