test_superresolution.py 16.4 KB
Newer Older
Stephan Seitz's avatar
Stephan Seitz committed
1
2
3
4
5
6
7
8
9
# -*- coding: utf-8 -*-
#
# Copyright © 2019 Stephan Seitz <stephan.seitz@fau.de>
#
# Distributed under terms of the GPLv3 license.

"""

"""
10
11
from os.path import dirname, join

Stephan Seitz's avatar
Stephan Seitz committed
12
import numpy as np
13
import pytest
14
import skimage.io
Stephan Seitz's avatar
Stephan Seitz committed
15
import sympy
Stephan Seitz's avatar
Stephan Seitz committed
16
17

import pystencils
18
import pystencils_reco.transforms
19
from pystencils_reco import crazy
20
21
22
23
from pystencils_reco.filters import gauss_filter
from pystencils_reco.resampling import (
    downsample, resample, resample_to_shape, scale_transform, translate)
from pystencils_reco.stencils import BallStencil
Stephan Seitz's avatar
Stephan Seitz committed
24
25
26
27
28
29
30
31
32
33

try:
    import pyconrad.autoinit
except Exception:
    import unittest.mock
    pyconrad = unittest.mock.MagicMock()


def test_superresolution():

34
    x, y = np.random.rand(20, 10), np.zeros((20, 10))
Stephan Seitz's avatar
Stephan Seitz committed
35
36
37
38
39
40
41
42

    kernel = scale_transform(x, y, 0.5).compile()
    print(pystencils.show_code(kernel))
    kernel()

    pyconrad.show_everything()


43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
def test_torch_simple():

    import pytest
    pytest.importorskip("torch")
    import torch

    x, y = torch.zeros((20, 20)), torch.zeros((20, 20))
    a = sympy.Symbol('a')

    @crazy
    def move(x, y, a):
        return {
            y.center: x.interpolated_access((pystencils.x_, pystencils.y_ + a))
        }

    kernel = move(x, y, a).compile()
    pystencils.autodiff.show_code(kernel.ast)
Stephan Seitz's avatar
Stephan Seitz committed
60
    kernel().forward(x, y, 3)
61
62


Stephan Seitz's avatar
Stephan Seitz committed
63
64
65
def test_downsample():
    shape = (20, 10)

66
    x, y = np.random.rand(*shape), np.zeros(tuple(s // 2 for s in shape))
Stephan Seitz's avatar
Stephan Seitz committed
67
68
69
70
71
72

    kernel = downsample(x, y, 2).compile()
    print(pystencils.show_code(kernel))
    kernel()

    pyconrad.show_everything()
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91


def test_warp():
    import torch
    NUM_LENNAS = 5
    perturbation = 0.1

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    warp_vectors = list(perturbation * torch.randn(lenna.shape + (2,)) for _ in range(NUM_LENNAS))

    warped = [torch.zeros(lenna.shape) for _ in range(NUM_LENNAS)]

    warp_kernel = translate(lenna, warped[0], pystencils.autodiff.ArrayWrapper(
        warp_vectors[0], index_dimensions=1), interpolation_mode='linear').compile()

    for i in range(len(warped)):
        warp_kernel(lenna[i], warped[i], warp_vectors[i])
Stephan Seitz's avatar
Stephan Seitz committed
92
93
94
95
96
97
98
99
100
101
102


def test_polar_transform():
    x, y = pystencils.fields('x, y:  float32[2d]')

    x.set_coordinate_origin_to_field_center()
    y.set_coordinate_origin_to_field_center()

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

103
    transformed = np.zeros((400, 400), np.float32)
Stephan Seitz's avatar
Stephan Seitz committed
104
105
106

    resample(x, y).compile()(x=lenna, y=transformed)

107
    pyconrad.show_everything()
108
109
    # while True:
    # sleep(100)
110
111
112
113
114
115
116


def test_polar_transform2():
    x, y = pystencils.fields('x, y:  float32[2d]')

    class PolarTransform(sympy.Function):
        def eval(args):
Stephan Seitz's avatar
Stephan Seitz committed
117
118
119
            return sympy.Matrix((args.norm(),
                                 sympy.atan2(args[1] - x.shape[1] / 2,
                                             args[0] - x.shape[0] / 2) / sympy.pi * x.shape[1] / 2))
120
121
122
123
124
125
126
127
128
129
130
131
132

    x.set_coordinate_origin_to_field_center()
    y.coordinate_transform = PolarTransform
    y.set_coordinate_origin_to_field_center()

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    transformed = np.zeros((400, 400), np.float32)

    resample(x, y).compile()(x=lenna, y=transformed)

    pyconrad.show_everything()
133
134
    # while True:
    # sleep(100)
135
136
137
138
139
140
141
142


def test_polar_inverted_transform():
    x, y = pystencils.fields('x, y:  float32[2d]')

    class PolarTransform(sympy.Function):
        def eval(args):
            return sympy.Matrix(
Stephan Seitz's avatar
Stephan Seitz committed
143
144
145
                (args.norm(),
                 sympy.atan2(args[1] - x.shape[1] / 2,
                             args[0] - x.shape[0] / 2) / sympy.pi * x.shape[1] / 2))
146
147

        def inv():
148
149
            return lambda l: (sympy.Matrix((sympy.cos(l[1] * sympy.pi / x.shape[1] * 2) * l[0],
                                            sympy.sin(l[1] * sympy.pi / x.shape[1] * 2) * l[0]))
Stephan Seitz's avatar
Stephan Seitz committed
150
                              + sympy.Matrix(x.shape) * 0.5)
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    # transformed = np.zeros((400, 400), np.float32)
    # back_transformed = np.zeros((400, 400), np.float32)
    transformed = np.zeros_like(lenna)
    back_transformed = np.zeros_like(lenna)

    x.set_coordinate_origin_to_field_center()
    y.coordinate_transform = PolarTransform
    y.set_coordinate_origin_to_field_center()
    resample(x, y).compile()(x=lenna, y=transformed)
    resample(y, x).compile()(x=back_transformed, y=transformed)

    pyconrad.show_everything()
167
168
    # while True:
    # sleep(100)
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


def test_shift():
    x, y = pystencils.fields('x, y:  float32[2d]')

    class ShiftTransform(sympy.Function):
        def eval(args):
            return args + sympy.Matrix((5, 5))

        def inv():
            return lambda l: l - sympy.Matrix((5, 5))

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    transformed = np.zeros_like(lenna)
    back_transformed = np.zeros_like(lenna)

    x.set_coordinate_origin_to_field_center()
    y.coordinate_transform = ShiftTransform
    y.set_coordinate_origin_to_field_center()
    resample(x, y).compile()(x=lenna, y=transformed)
    resample(y, x).compile()(x=back_transformed, y=transformed)

    diff = lenna - back_transformed
    assert diff is not None

    pyconrad.show_everything()
197
198
    # while True:
    # sleep(100)
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


def test_motion_model():
    x, y = pystencils.fields('x, y:  float32[2d]')
    transform_field = pystencils.fields('t_x, t_y: float32[2d]')

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    # transformed = np.zeros((400, 400), np.float32)
    # back_transformed = np.zeros((400, 400), np.float32)
    transformed = np.zeros_like(lenna)
    back_transformed = np.zeros_like(lenna)
    translate_x = np.zeros((10, 10), np.float32)
    translate_y = np.zeros((10, 10), np.float32)

    pystencils_reco.transforms.extend_to_size_of_other_field(transform_field[0], x)
    pystencils_reco.transforms.extend_to_size_of_other_field(transform_field[1], x)

    shift = sympy.Matrix(sympy.symbols('s:2'))
    shift_val = sympy.Matrix([transform_field[i].interpolated_access(
        transform_field[i].physical_to_index(x.physical_coordinates))
        for i in range(x.ndim)])

    class ShiftTransform(sympy.Function):
        def eval(args):
            return args + shift

        def inv():
            return lambda args: args - shift

    y.coordinate_transform = ShiftTransform
    pystencils_reco.AssignmentCollection([*resample(x, y),
                                          *[pystencils.Assignment(shift[i], shift_val[i]) for i in range(2)]]
                                         ).compile()(x=lenna, y=transformed, t_x=translate_x, t_y=translate_y)

    pystencils_reco.AssignmentCollection([*resample(x, y),
                                          *[pystencils.Assignment(shift[i], shift_val[i]) for i in range(2)]]
                                         ).compile()(x=back_transformed,
                                                     y=transformed,
                                                     t_x=translate_x,
                                                     t_y=translate_y)

    pyconrad.show_everything()
243
244
    # while True:
    # sleep(100)
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


def test_motion_model2():
    x, y = pystencils.fields('x, y:  float32[2d]')
    transform_field = pystencils.fields('t_x, t_y: float32[2d]')

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    # transformed = np.zeros((400, 400), np.float32)
    # back_transformed = np.zeros((400, 400), np.float32)
    transformed = np.zeros_like(lenna)
    blurred = np.zeros_like(lenna)

    translate_x = np.zeros_like(lenna)
    translate_y = np.zeros_like(lenna)
    amplitude = 20

    resample_to_shape(amplitude * np.random.randn(10, 10).astype(np.float32), lenna.shape).compile()(output=translate_x)
    resample_to_shape(amplitude * np.random.randn(10, 10).astype(np.float32), lenna.shape).compile()(output=translate_y)

    translate(x, y, sympy.Matrix((transform_field[0].center, transform_field[1].center))
              ).compile()(x=lenna, y=transformed, t_x=translate_x, t_y=translate_y)

    # resample(x, y).compile()(x=back_transformed, y=transformed, t_x=translate_x, t_y=translate_y)

    kernel = gauss_filter(transformed, blurred, BallStencil(5, ndim=2), 10).compile()
    print(pystencils.show_code(kernel))
    kernel(input_field=transformed, output_field=blurred)

    pyconrad.show_everything()

277
278
    # while True:
    # sleep(100)
279
280
281
282
283
284
285


def test_spatial_derivative():
    x, y = pystencils.fields('x, y:  float32[2d]')
    tx, ty = pystencils.fields('t_x, t_y: float32[2d]')

    assignments = pystencils.AssignmentCollection({
Stephan Seitz's avatar
Stephan Seitz committed
286
        y.center: x.interpolated_access((tx.center + pystencils.x_, 2 * ty.center + pystencils.y_))
287
288
289
290
    })

    backward_assignments = pystencils.autodiff.create_backward_assignments(assignments)

Stephan Seitz's avatar
Stephan Seitz committed
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
    print("assignments: " + str(assignments))
    print("backward_assignments: " + str(backward_assignments))


def test_spatial_derivative2():
    import pystencils.interpolation_astnodes
    x, y = pystencils.fields('x, y:  float32[2d]')
    tx, ty = pystencils.fields('t_x, t_y: float32[2d]')

    assignments = pystencils.AssignmentCollection({
        y.center: x.interpolated_access((tx.center + pystencils.x_, ty.center + 2 * pystencils.y_))
    })

    backward_assignments = pystencils.autodiff.create_backward_assignments(assignments)

    assert backward_assignments.atoms(pystencils.interpolation_astnodes.DiffInterpolatorAccess)

    print("assignments: " + str(assignments))
309
    print("backward_assignments: " + str(backward_assignments))
Stephan Seitz's avatar
Stephan Seitz committed
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326


def test_get_shift():
    from pystencils_autodiff.framework_integration.datahandling import PyTorchDataHandling

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    dh = PyTorchDataHandling(lenna.shape)
    x, y, tx, ty = dh.add_arrays('x, y, tx, ty')

    dh.cpu_arrays['x'] = lenna
    dh.cpu_arrays['tx'][...] = 0.7
    dh.cpu_arrays['ty'][...] = -0.7
    dh.all_to_gpu()

    kernel = pystencils_reco.AssignmentCollection({
Stephan Seitz's avatar
Stephan Seitz committed
327
328
        y.center: x.interpolated_access((tx.center + pystencils.x_, 2 * ty.center +
                                         pystencils.y_), interpolation_mode='cubic_spline')
Stephan Seitz's avatar
Stephan Seitz committed
329
330
331
332
333
    }).create_pytorch_op()().forward

    dh.run_kernel(kernel)

    pyconrad.imshow(dh.gpu_arrays)
Stephan Seitz's avatar
Stephan Seitz committed
334
335


336
337
@pytest.mark.parametrize('scalar_experiment', (False,))
def test_get_shift_tensors(scalar_experiment):
Stephan Seitz's avatar
Stephan Seitz committed
338
339
340
341
342
343
344
345
346
347
348
349
350
    from pystencils_autodiff.framework_integration.datahandling import PyTorchDataHandling
    import torch

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    dh = PyTorchDataHandling(lenna.shape)
    x, y, tx, ty = dh.add_arrays('xw, yw, txw, tyw')

    dh.cpu_arrays['xw'] = lenna
    dh.cpu_arrays['txw'][...] = 0.7
    dh.cpu_arrays['tyw'][...] = -0.7
    dh.all_to_gpu()
351
    pyconrad.imshow(dh.gpu_arrays)
Stephan Seitz's avatar
Stephan Seitz committed
352
353

    kernel = pystencils_reco.AssignmentCollection({
354
        y.center: x.interpolated_access((tx.center + pystencils.x_, 2 * ty.center + pystencils.y_))
Stephan Seitz's avatar
Stephan Seitz committed
355
356
    }).create_pytorch_op()().call

357
    y_array = dh.run_kernel(kernel)
Stephan Seitz's avatar
Stephan Seitz committed
358
359
360
361

    dh = PyTorchDataHandling(lenna.shape)
    x, y, tx, ty = dh.add_arrays('x, y, tx, ty')

362
363
364
365
366
367
368
369
370
371
    if scalar_experiment:
        var_x = torch.zeros((), requires_grad=True)
        var_y = torch.zeros((), requires_grad=True)
    else:
        var_x = torch.zeros(lenna.shape, requires_grad=True)
        var_y = torch.zeros(lenna.shape, requires_grad=True)

    dh.cpu_arrays.x = lenna

    assignments = pystencils_reco.AssignmentCollection({
Stephan Seitz's avatar
Stephan Seitz committed
372
373
        y.center: x.interpolated_access((tx.center + pystencils.x_,
                                         2 * ty.center + pystencils.y_))
374
375
376
377
    })

    print(pystencils.autodiff.create_backward_assignments(assignments))
    kernel = assignments.create_pytorch_op()
Stephan Seitz's avatar
Stephan Seitz committed
378
379
380
381

    print(kernel.ast)
    kernel = kernel().call

382
383
    learning_rate = 0.1
    params = (var_x, var_y)
Stephan Seitz's avatar
Stephan Seitz committed
384
385
386
387
    # assert all([p.is_leaf for p in params])
    optimizer = torch.optim.Adam(params, lr=learning_rate)

    for i in range(100):
388
389
390
391
392
393
394
395
        if scalar_experiment:
            dh.cpu_arrays.tx = torch.ones(lenna.shape) * var_x
            dh.cpu_arrays.ty = torch.ones(lenna.shape) * var_y
        else:
            dh.cpu_arrays.tx = var_x
            dh.cpu_arrays.ty = var_y
        dh.all_to_gpu()

Stephan Seitz's avatar
Stephan Seitz committed
396
397
398
399
400
        y = dh.run_kernel(kernel)
        loss = (y - y_array).norm()

        optimizer.zero_grad()

401
        loss.backward(retain_graph=True)
Stephan Seitz's avatar
Stephan Seitz committed
402
403
404
405
        assert y.requires_grad

        optimizer.step()
        print(loss.cpu().detach().numpy())
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
        print("var_x: " + str(var_x.mean()))
        pyconrad.imshow(var_x)
    # pyconrad.imshow(dh.gpu_arrays)
    pyconrad.imshow(dh.gpu_arrays, wait_window_close=True)


@pytest.mark.parametrize('with_spline', ('with_spline', False))
def test_spline_diff(with_spline):
    from pystencils.fd import Diff
    from pystencils.datahandling import SerialDataHandling

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    dh = SerialDataHandling(lenna.shape, default_target='gpu', default_ghost_layers=0, default_layout='numpy')
    x, y, tx, ty = dh.add_arrays('x, y, tx, ty', dtype=np.float32)

    dh.cpu_arrays['x'] = lenna
    dh.cpu_arrays['tx'][...] = 0.7
    dh.cpu_arrays['ty'][...] = -0.7
    out = dh.add_array('out', dtype=np.float32)
    dh.all_to_gpu()

    kernel = pystencils_reco.AssignmentCollection({
        y.center: Diff(x, 0).interpolated_access((tx.center + pystencils.x_,
                                                  ty.center + pystencils.y_),
                                                 interpolation_mode='cubic_spline' if with_spline else 'linear')
    }).compile(target='gpu')

    dh.run_kernel(kernel)

    print(pystencils.show_code(kernel))

    kernel = pystencils_reco.AssignmentCollection({
        out.center: x.interpolated_access((tx.center + pystencils.x_, ty.center + pystencils.y_),
                                          interpolation_mode='cubic_spline' if with_spline else 'linear')
    }).compile(target='gpu')

    dh.run_kernel(kernel)

    print(pystencils.show_code(kernel))
Stephan Seitz's avatar
Stephan Seitz committed
447
448
449

    pyconrad.imshow(dh.gpu_arrays)
    pyconrad.imshow(dh.gpu_arrays)
Stephan Seitz's avatar
Stephan Seitz committed
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


@pytest.mark.parametrize('scalar_experiment', (False,))
def test_rotation(scalar_experiment):
    from pystencils_autodiff.framework_integration.datahandling import PyTorchDataHandling
    from pystencils_reco.resampling import rotation_transform

    import torch

    lenna_file = join(dirname(__file__), "test_data", "lenna.png")
    lenna = skimage.io.imread(lenna_file, as_gray=True).astype(np.float32)

    GROUNDTRUTH_ANGLE = 0.3

    target = np.zeros(lenna.shape)
    rotation_transform(lenna, target, GROUNDTRUTH_ANGLE)()
    target = torch.Tensor(target).cuda()

    dh = PyTorchDataHandling(lenna.shape)
    x, y, angle = dh.add_arrays('x, y, angle')

    if scalar_experiment:
        var_angle = torch.zeros((), requires_grad=True)
    else:
        var_angle = torch.zeros(lenna.shape, requires_grad=True)

    var_lenna = torch.autograd.Variable(torch.from_numpy(
        lenna + np.random.randn(*lenna.shape).astype(np.float32)), requires_grad=True)
    assert var_lenna.requires_grad

    learning_rate = 0.1
    params = (var_angle, var_lenna)

    optimizer = torch.optim.Adam(params, lr=learning_rate)

    assignments = rotation_transform(x, y, angle)
    kernel = assignments.create_pytorch_op()
    print(kernel)

    kernel = kernel().call

    for i in range(100000):
        if scalar_experiment:
            dh.cpu_arrays.angle = torch.ones(lenna.shape) * (var_angle + 0.29)
        else:
            dh.cpu_arrays.angle = var_angle
        dh.cpu_arrays.x = var_lenna
        dh.all_to_gpu()

        y = dh.run_kernel(kernel)
        loss = (y - target).norm()

        optimizer.zero_grad()

        loss.backward(retain_graph=True)
        assert y.requires_grad

        optimizer.step()
        print(loss.cpu().detach().numpy())
        pyconrad.imshow(var_lenna)

    pyconrad.show_everything()