File size: 6,668 Bytes
c24da45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import importlib

import random
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


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 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.")
    # import pdb; pdb.set_trace()
    return get_obj_from_str(config["target"])(**config.get("params", dict()))


def get_obj_from_str(string, reload=False):
    module, cls = string.rsplit(".", 1)
    # import pdb; pdb.set_trace()
    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 set_seed(seed=None):
    random.seed(seed)
    np.random.seed(seed)
    if seed is not None:
        torch.manual_seed(seed)
        torch.cuda.manual_seed_all(seed)

def add_random_background(image, bg_color=None):
    bg_color = np.random.rand() * 255 if bg_color is None else bg_color
    image = np.array(image)
    rgb, alpha = image[..., :3], image[..., 3:]
    alpha = alpha.astype(np.float32) / 255.0
    image_new = rgb * alpha + bg_color * (1 - alpha)
    return Image.fromarray(image_new.astype(np.uint8))