/
data.load.html
613 lines (456 loc) · 42.5 KB
/
data.load.html
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
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
---
title: Title
keywords: fastai
sidebar: home_sidebar
summary: "summary"
---
<!--
#################################################
### THIS FILE WAS AUTOGENERATED! DO NOT EDIT! ###
#################################################
# file to edit: 04_data_load.ipynb
# instructions: https://docs.fast.ai/gen_doc_main.html
-->
<div class="container" id="notebook-container">
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">from</span> <span class="nn">nbdev.showdoc</span> <span class="k">import</span> <span class="o">*</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">bs</span> <span class="o">=</span> <span class="mi">4</span>
<span class="n">letters</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">string</span><span class="o">.</span><span class="n">ascii_lowercase</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="DataLoader">DataLoader<a class="anchor-link" href="#DataLoader">¶</a></h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h4 id="fa_collate" class="doc_header"><code>fa_collate</code><a href="https://github.com/fastai/fastai_dev/tree/master/devfastai2/data/load.py#L44" class="source_link" style="float:right">[source]</a></h4><blockquote><p><code>fa_collate</code>(<strong><code>t</code></strong>)</p>
</blockquote>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="c1">#e.g. x is int, y is tuple</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">[(</span><span class="mi">1</span><span class="p">,(</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">)),(</span><span class="mi">1</span><span class="p">,(</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">))]</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">fa_collate</span><span class="p">(</span><span class="n">t</span><span class="p">),</span> <span class="n">default_collate</span><span class="p">(</span><span class="n">t</span><span class="p">))</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">fa_collate</span><span class="p">(</span><span class="n">t</span><span class="p">))</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">type</span><span class="p">),</span> <span class="p">[</span><span class="n">Tensor</span><span class="p">,</span><span class="nb">tuple</span><span class="p">])</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">[(</span><span class="mi">1</span><span class="p">,(</span><span class="mi">2</span><span class="p">,(</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">))),(</span><span class="mi">1</span><span class="p">,(</span><span class="mi">2</span><span class="p">,(</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">)))]</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">fa_collate</span><span class="p">(</span><span class="n">t</span><span class="p">),</span> <span class="n">default_collate</span><span class="p">(</span><span class="n">t</span><span class="p">))</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">fa_collate</span><span class="p">(</span><span class="n">t</span><span class="p">))</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">type</span><span class="p">),</span> <span class="p">[</span><span class="n">Tensor</span><span class="p">,</span><span class="nb">tuple</span><span class="p">])</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">fa_collate</span><span class="p">(</span><span class="n">t</span><span class="p">)[</span><span class="mi">1</span><span class="p">])</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">type</span><span class="p">),</span> <span class="p">[</span><span class="n">Tensor</span><span class="p">,</span><span class="nb">tuple</span><span class="p">])</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h4 id="fa_convert" class="doc_header"><code>fa_convert</code><a href="https://github.com/fastai/fastai_dev/tree/master/devfastai2/data/load.py#L51" class="source_link" style="float:right">[source]</a></h4><blockquote><p><code>fa_convert</code>(<strong><code>t</code></strong>)</p>
</blockquote>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">t0</span> <span class="o">=</span> <span class="n">array</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">])</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">[</span><span class="n">t0</span><span class="p">,(</span><span class="n">t0</span><span class="p">,</span><span class="n">t0</span><span class="p">)]</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">fa_convert</span><span class="p">(</span><span class="n">t</span><span class="p">),</span> <span class="n">default_convert</span><span class="p">(</span><span class="n">t</span><span class="p">))</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">fa_convert</span><span class="p">(</span><span class="n">t</span><span class="p">))</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">type</span><span class="p">),</span> <span class="p">[</span><span class="n">Tensor</span><span class="p">,</span><span class="nb">tuple</span><span class="p">])</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h2 id="SkipItemException" class="doc_header"><code>class</code> <code>SkipItemException</code><a href="https://github.com/fastai/fastai_dev/tree/master/devfastai2/data/load.py#L57" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>SkipItemException</code>() :: <code>Exception</code></p>
</blockquote>
<p>Common base class for all non-exit exceptions.</p>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h2 id="DataLoader" class="doc_header"><code>class</code> <code>DataLoader</code><a href="https://github.com/fastai/fastai_dev/tree/master/devtorch/utils/data/dataloader.py#L60" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>DataLoader</code>(<strong><code>dataset</code></strong>, <strong><code>batch_size</code></strong>=<em><code>1</code></em>, <strong><code>shuffle</code></strong>=<em><code>False</code></em>, <strong><code>sampler</code></strong>=<em><code>None</code></em>, <strong><code>batch_sampler</code></strong>=<em><code>None</code></em>, <strong><code>num_workers</code></strong>=<em><code>0</code></em>, <strong><code>collate_fn</code></strong>=<em><code>None</code></em>, <strong><code>pin_memory</code></strong>=<em><code>False</code></em>, <strong><code>drop_last</code></strong>=<em><code>False</code></em>, <strong><code>timeout</code></strong>=<em><code>0</code></em>, <strong><code>worker_init_fn</code></strong>=<em><code>None</code></em>, <strong><code>multiprocessing_context</code></strong>=<em><code>None</code></em>)</p>
</blockquote>
<p>Data loader. Combines a dataset and a sampler, and provides an iterable over
the given dataset.</p>
<p>The :class:<code>~torch.utils.data.DataLoader</code> supports both map-style and
iterable-style datasets with single- or multi-process loading, customizing
loading order and optional automatic batching (collation) and memory pinning.</p>
<p>See :py:mod:<code>torch.utils.data</code> documentation page for more details.</p>
<p>Arguments:
dataset (Dataset): dataset from which to load the data.
batch_size (int, optional): how many samples per batch to load
(default: <code>1</code>).
shuffle (bool, optional): set to <code>True</code> to have the data reshuffled
at every epoch (default: <code>False</code>).
sampler (Sampler, optional): defines the strategy to draw samples from
the dataset. If specified, :attr:<code>shuffle</code> must be <code>False</code>.
batch_sampler (Sampler, optional): like :attr:<code>sampler</code>, but returns a batch of
indices at a time. Mutually exclusive with :attr:<code>batch_size</code>,
:attr:<code>shuffle</code>, :attr:<code>sampler</code>, and :attr:<code>drop_last</code>.
num_workers (int, optional): how many subprocesses to use for data
loading. <code>0</code> means that the data will be loaded in the main process.
(default: <code>0</code>)
collate_fn (callable, optional): merges a list of samples to form a
mini-batch of Tensor(s). Used when using batched loading from a
map-style dataset.
pin_memory (bool, optional): If <code>True</code>, the data loader will copy Tensors
into CUDA pinned memory before returning them. If your data elements
are a custom type, or your :attr:<code>collate_fn</code> returns a batch that is a custom type,
see the example below.
drop_last (bool, optional): set to <code>True</code> to drop the last incomplete batch,
if the dataset size is not divisible by the batch size. If <code>False</code> and
the size of dataset is not divisible by the batch size, then the last batch
will be smaller. (default: <code>False</code>)
timeout (numeric, optional): if positive, the timeout value for collecting a batch
from workers. Should always be non-negative. (default: <code>0</code>)
worker_init_fn (callable, optional): If not <code>None</code>, this will be called on each
worker subprocess with the worker id (an int in <code>[0, num_workers - 1]</code>) as
input, after seeding and before data loading. (default: <code>None</code>)</p>
<p>.. warning:: If the <code>spawn</code> start method is used, :attr:<code>worker_init_fn</code>
cannot be an unpicklable object, e.g., a lambda function. See
:ref:<code>multiprocessing-best-practices</code> on more details related
to multiprocessing in PyTorch.</p>
<p>.. note:: <code>len(dataloader)</code> heuristic is based on the length of the sampler used.
When :attr:<code>dataset</code> is an :class:<code>~torch.utils.data.IterableDataset</code>,
an infinite sampler is used, whose :meth:<code>__len__</code> is not
implemented, because the actual length depends on both the
iterable as well as multi-process loading configurations. So one
should not query this method unless they work with a map-style
dataset. See <code>Dataset Types</code>_ for more details on these two types
of datasets.</p>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>Override <code>item</code> and use the default infinite sampler to get a stream of unknown length (<code>stop()</code> when you want to stop the stream).</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">class</span> <span class="nc">RandDL</span><span class="p">(</span><span class="n">DataLoader</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">create_item</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">s</span><span class="p">):</span>
<span class="n">r</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span>
<span class="k">return</span> <span class="n">r</span> <span class="k">if</span> <span class="n">r</span><span class="o"><</span><span class="mf">0.95</span> <span class="k">else</span> <span class="n">stop</span><span class="p">()</span>
<span class="n">L</span><span class="p">(</span><span class="n">RandDL</span><span class="p">())</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>(#13) [0.7885827705643671,0.9445681666865668,0.2012097820885873,0.22599163641827813,0.838555182773626,0.7551127591888557,0.7415013121824475,0.5171421446320487,0.014315549406187067,0.09518320819805359...]</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">L</span><span class="p">(</span><span class="n">RandDL</span><span class="p">(</span><span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">drop_last</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">len</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>(#2) [4,4]</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">dl</span> <span class="o">=</span> <span class="n">RandDL</span><span class="p">(</span><span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">drop_last</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">L</span><span class="p">(</span><span class="n">dl</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">len</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>(#25) [4,4,4,4,4,4,4,4,4,4...]</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">test_eq</span><span class="p">(</span><span class="n">dl</span><span class="o">.</span><span class="n">fake_l</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span>
<span class="k">with</span> <span class="n">dl</span><span class="o">.</span><span class="n">fake_l</span><span class="o">.</span><span class="n">no_multiproc</span><span class="p">():</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">dl</span><span class="o">.</span><span class="n">fake_l</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">L</span><span class="p">(</span><span class="n">dl</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="nb">len</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">dl</span><span class="o">.</span><span class="n">fake_l</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">_rand_item</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="n">r</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span>
<span class="k">return</span> <span class="n">r</span> <span class="k">if</span> <span class="n">r</span><span class="o"><</span><span class="mf">0.95</span> <span class="k">else</span> <span class="n">stop</span><span class="p">()</span>
<span class="n">L</span><span class="p">(</span><span class="n">DataLoader</span><span class="p">(</span><span class="n">create_item</span><span class="o">=</span><span class="n">_rand_item</span><span class="p">))</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>(#8) [0.6492435216654613,0.7686011830380626,0.4006885521657221,0.43493759826957445,0.798701306941883,0.14328729229619985,0.3979884837428669,0.17959300625304775]</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>If you don't set <code>bs</code>, then <code>dataset</code> is assumed to provide an iterator or a <code>__getitem__</code> that returns a batch.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">letters</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="n">letters</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="mi">26</span><span class="p">)</span>
<span class="n">test_shuffled</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">DataLoader</span><span class="p">(</span><span class="n">letters</span><span class="p">,</span> <span class="n">shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">)),</span> <span class="n">letters</span><span class="p">)</span>
<span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">letters</span><span class="p">,</span> <span class="n">indexed</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="n">letters</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="mi">26</span><span class="p">)</span>
<span class="n">t2</span> <span class="o">=</span> <span class="n">L</span><span class="p">(</span><span class="n">tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">]),</span><span class="n">tensor</span><span class="p">([</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]))</span>
<span class="n">ds2</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">t2</span><span class="p">)</span>
<span class="n">test_eq_type</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds2</span><span class="p">),</span> <span class="n">t2</span><span class="p">)</span>
<span class="n">t3</span> <span class="o">=</span> <span class="n">L</span><span class="p">(</span><span class="n">array</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">]),</span><span class="n">array</span><span class="p">([</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]))</span>
<span class="n">ds3</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">t3</span><span class="p">)</span>
<span class="n">test_eq_type</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds3</span><span class="p">),</span> <span class="n">t3</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">tensor</span><span class="p">))</span>
<span class="n">ds4</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">t3</span><span class="p">,</span> <span class="n">create_batch</span><span class="o">=</span><span class="n">noop</span><span class="p">,</span> <span class="n">after_iter</span><span class="o">=</span><span class="k">lambda</span><span class="p">:</span> <span class="nb">setattr</span><span class="p">(</span><span class="n">t3</span><span class="p">,</span> <span class="s1">'f'</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span>
<span class="n">test_eq_type</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds4</span><span class="p">),</span> <span class="n">t3</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">t3</span><span class="o">.</span><span class="n">f</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>If you do set <code>bs</code>, then <code>dataset</code> is assumed to provide an iterator or a <code>__getitem__</code> that returns a single item of a batch.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">twoepochs</span><span class="p">(</span><span class="n">d</span><span class="p">):</span> <span class="k">return</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">o</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">d</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">letters</span><span class="p">,</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">drop_last</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">twoepochs</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="s1">'abcd efgh ijkl mnop qrst uvwx abcd efgh ijkl mnop qrst uvwx'</span><span class="p">)</span>
<span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">letters</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="n">num_workers</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">twoepochs</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="s1">'abcd efgh ijkl mnop qrst uvwx yz abcd efgh ijkl mnop qrst uvwx yz'</span><span class="p">)</span>
<span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="mi">12</span><span class="p">),</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
<span class="n">test_eq_type</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="n">L</span><span class="p">(</span><span class="n">tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">]),</span><span class="n">tensor</span><span class="p">([</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">,</span><span class="mi">6</span><span class="p">,</span><span class="mi">7</span><span class="p">]),</span><span class="n">tensor</span><span class="p">([</span><span class="mi">8</span><span class="p">,</span><span class="mi">9</span><span class="p">,</span><span class="mi">10</span><span class="p">,</span><span class="mi">11</span><span class="p">])))</span>
<span class="n">ds1</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">11</span><span class="p">)],</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">after_iter</span><span class="o">=</span><span class="k">lambda</span><span class="p">:</span> <span class="nb">setattr</span><span class="p">(</span><span class="n">t3</span><span class="p">,</span> <span class="s1">'f'</span><span class="p">,</span> <span class="mi">2</span><span class="p">))</span>
<span class="n">test_eq_type</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">ds1</span><span class="p">),</span> <span class="n">L</span><span class="p">([</span><span class="s1">'0'</span><span class="p">,</span><span class="s1">'1'</span><span class="p">,</span><span class="s1">'2'</span><span class="p">,</span><span class="s1">'3'</span><span class="p">],[</span><span class="s1">'4'</span><span class="p">,</span><span class="s1">'5'</span><span class="p">,</span><span class="s1">'6'</span><span class="p">,</span><span class="s1">'7'</span><span class="p">],[</span><span class="s1">'8'</span><span class="p">,</span><span class="s1">'9'</span><span class="p">,</span><span class="s1">'10'</span><span class="p">]))</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">t3</span><span class="o">.</span><span class="n">f</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="n">it</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">DataLoader</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="n">noop</span><span class="p">,</span><span class="nb">range</span><span class="p">(</span><span class="mi">20</span><span class="p">)),</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
<span class="n">test_eq_type</span><span class="p">([</span><span class="nb">next</span><span class="p">(</span><span class="n">it</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">3</span><span class="p">)],</span> <span class="p">[</span><span class="n">tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">]),</span><span class="n">tensor</span><span class="p">([</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">,</span><span class="mi">6</span><span class="p">,</span><span class="mi">7</span><span class="p">]),</span><span class="n">tensor</span><span class="p">([</span><span class="mi">8</span><span class="p">,</span><span class="mi">9</span><span class="p">,</span><span class="mi">10</span><span class="p">,</span><span class="mi">11</span><span class="p">])])</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">class</span> <span class="nc">SleepyDL</span><span class="p">(</span><span class="nb">list</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span><span class="n">i</span><span class="p">):</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span><span class="o">/</span><span class="mi">50</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__getitem__</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">SleepyDL</span><span class="p">(</span><span class="n">letters</span><span class="p">)</span>
<span class="o">%</span><span class="k">time</span> test_eq(DataLoader(t, num_workers=0), letters)
<span class="o">%</span><span class="k">time</span> test_eq(DataLoader(t, num_workers=2), letters)
<span class="o">%</span><span class="k">time</span> test_eq(DataLoader(t, num_workers=4), letters)
<span class="n">dl</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">t</span><span class="p">,</span> <span class="n">shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">test_shuffled</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">dl</span><span class="p">),</span> <span class="n">letters</span><span class="p">)</span>
<span class="n">test_shuffled</span><span class="p">(</span><span class="n">L</span><span class="p">(</span><span class="n">dl</span><span class="p">),</span> <span class="n">L</span><span class="p">(</span><span class="n">dl</span><span class="p">))</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>CPU times: user 4.56 ms, sys: 0 ns, total: 4.56 ms
Wall time: 203 ms
CPU times: user 12.5 ms, sys: 17.9 ms, total: 30.4 ms
Wall time: 163 ms
CPU times: user 18 ms, sys: 29.9 ms, total: 47.9 ms
Wall time: 139 ms
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">class</span> <span class="nc">SleepyQueue</span><span class="p">():</span>
<span class="s2">"Simulate a queue with varying latency"</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">q</span><span class="p">):</span> <span class="bp">self</span><span class="o">.</span><span class="n">q</span><span class="o">=</span><span class="n">q</span>
<span class="k">def</span> <span class="nf">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span><span class="o">/</span><span class="mi">100</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span> <span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">q</span><span class="o">.</span><span class="n">get_nowait</span><span class="p">()</span>
<span class="k">except</span> <span class="n">queues</span><span class="o">.</span><span class="n">Empty</span><span class="p">:</span> <span class="k">return</span>
<span class="n">q</span> <span class="o">=</span> <span class="n">Queue</span><span class="p">()</span>
<span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">30</span><span class="p">):</span> <span class="n">q</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">o</span><span class="p">)</span>
<span class="n">it</span> <span class="o">=</span> <span class="n">SleepyQueue</span><span class="p">(</span><span class="n">q</span><span class="p">)</span>
<span class="o">%</span><span class="k">time</span> test_shuffled(L(DataLoader(it, num_workers=4)), range(30))
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>CPU times: user 10.8 ms, sys: 35.6 ms, total: 46.4 ms
Wall time: 137 ms
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">class</span> <span class="nc">A</span><span class="p">(</span><span class="n">TensorBase</span><span class="p">):</span> <span class="k">pass</span>
<span class="k">for</span> <span class="n">nw</span> <span class="ow">in</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span><span class="mi">2</span><span class="p">):</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">A</span><span class="p">(</span><span class="n">tensor</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">]))</span>
<span class="n">dl</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">([</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">],</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="n">nw</span><span class="p">)</span>
<span class="n">b</span> <span class="o">=</span> <span class="n">first</span><span class="p">(</span><span class="n">dl</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">b</span><span class="p">),</span> <span class="n">A</span><span class="p">)</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">(</span><span class="n">A</span><span class="p">(</span><span class="n">tensor</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">])),)</span>
<span class="n">dl</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">([</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">],</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="n">nw</span><span class="p">)</span>
<span class="n">b</span> <span class="o">=</span> <span class="n">first</span><span class="p">(</span><span class="n">dl</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">b</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="n">A</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">class</span> <span class="nc">A</span><span class="p">(</span><span class="n">TensorBase</span><span class="p">):</span> <span class="k">pass</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">A</span><span class="p">(</span><span class="n">tensor</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">))</span>
<span class="n">tdl</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">([</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">,</span><span class="n">t</span><span class="p">],</span> <span class="n">bs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">after_batch</span><span class="o">=</span><span class="n">to_device</span><span class="p">)</span>
<span class="n">b</span> <span class="o">=</span> <span class="n">first</span><span class="p">(</span><span class="n">tdl</span><span class="p">)</span>
<span class="n">test_eq</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">b</span><span class="p">),</span> <span class="n">A</span><span class="p">)</span>
<span class="c1"># Unknown attributes are delegated to `dataset`</span>
<span class="n">test_eq</span><span class="p">(</span><span class="n">tdl</span><span class="o">.</span><span class="n">pop</span><span class="p">(),</span> <span class="n">tensor</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">))</span>
</pre></div>
</div>
</div>
</div>
</div>
</div>