Log In Sign Up
Models:
David Feaster
DavidFeaster/
Surgical-Bleeding-AMAGI
0
Downloads: 1
[6d389a]: / tests / test_models / test_recognizers / test_recognizer3d.py

Download this file

314 lines (243 with data), 10.2 kB 

  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
# Copyright (c) OpenMMLab. All rights reserved.

import torch



from mmaction.models import build_recognizer

from ..base import generate_recognizer_demo_inputs, get_recognizer_cfg





def test_i3d():

    config = get_recognizer_cfg('i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py')

    config.model['backbone']['pretrained2d'] = False

    config.model['backbone']['pretrained'] = None



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 8, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    # parrots 3dconv is only implemented on gpu

    if torch.__version__ == 'parrots':

        if torch.cuda.is_available():

            recognizer = recognizer.cuda()

            imgs = imgs.cuda()

            gt_labels = gt_labels.cuda()

            losses = recognizer(imgs, gt_labels)

            assert isinstance(losses, dict)



            # Test forward test

            with torch.no_grad():

                img_list = [img[None, :] for img in imgs]

                for one_img in img_list:

                    recognizer(one_img, None, return_loss=False)



            # Test forward gradcam

            recognizer(imgs, gradcam=True)

            for one_img in img_list:

                recognizer(one_img, gradcam=True)



            # Test forward dummy

            recognizer.forward_dummy(imgs, softmax=False)

            res = recognizer.forward_dummy(imgs, softmax=True)[0]

            assert torch.min(res) >= 0

            assert torch.max(res) <= 1



    else:

        losses = recognizer(imgs, gt_labels)

        assert isinstance(losses, dict)



        # Test forward test

        with torch.no_grad():

            img_list = [img[None, :] for img in imgs]

            for one_img in img_list:

                recognizer(one_img, None, return_loss=False)



        # Test forward gradcam

        recognizer(imgs, gradcam=True)

        for one_img in img_list:

            recognizer(one_img, gradcam=True)



        # Test forward dummy

        recognizer.forward_dummy(imgs, softmax=False)

        res = recognizer.forward_dummy(imgs, softmax=True)[0]

        assert torch.min(res) >= 0

        assert torch.max(res) <= 1





def test_r2plus1d():

    config = get_recognizer_cfg(

        'r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py')

    config.model['backbone']['pretrained2d'] = False

    config.model['backbone']['pretrained'] = None

    config.model['backbone']['norm_cfg'] = dict(type='BN3d')



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 8, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    # parrots 3dconv is only implemented on gpu

    if torch.__version__ == 'parrots':

        if torch.cuda.is_available():

            recognizer = recognizer.cuda()

            imgs = imgs.cuda()

            gt_labels = gt_labels.cuda()

            losses = recognizer(imgs, gt_labels)

            assert isinstance(losses, dict)



            # Test forward test

            with torch.no_grad():

                img_list = [img[None, :] for img in imgs]

                for one_img in img_list:

                    recognizer(one_img, None, return_loss=False)



            # Test forward gradcam

            recognizer(imgs, gradcam=True)

            for one_img in img_list:

                recognizer(one_img, gradcam=True)

    else:

        losses = recognizer(imgs, gt_labels)

        assert isinstance(losses, dict)



        # Test forward test

        with torch.no_grad():

            img_list = [img[None, :] for img in imgs]

            for one_img in img_list:

                recognizer(one_img, None, return_loss=False)



        # Test forward gradcam

        recognizer(imgs, gradcam=True)

        for one_img in img_list:

            recognizer(one_img, gradcam=True)





def test_slowfast():

    config = get_recognizer_cfg(

        'slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py')



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 16, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    # parrots 3dconv is only implemented on gpu

    if torch.__version__ == 'parrots':

        if torch.cuda.is_available():

            recognizer = recognizer.cuda()

            imgs = imgs.cuda()

            gt_labels = gt_labels.cuda()

            losses = recognizer(imgs, gt_labels)

            assert isinstance(losses, dict)



            # Test forward test

            with torch.no_grad():

                img_list = [img[None, :] for img in imgs]

                for one_img in img_list:

                    recognizer(one_img, None, return_loss=False)



            # Test forward gradcam

            recognizer(imgs, gradcam=True)

            for one_img in img_list:

                recognizer(one_img, gradcam=True)

    else:

        losses = recognizer(imgs, gt_labels)

        assert isinstance(losses, dict)



        # Test forward test

        with torch.no_grad():

            img_list = [img[None, :] for img in imgs]

            for one_img in img_list:

                recognizer(one_img, None, return_loss=False)



        # Test forward gradcam

        recognizer(imgs, gradcam=True)

        for one_img in img_list:

            recognizer(one_img, gradcam=True)



        # Test the feature max_testing_views

        config.model.test_cfg['max_testing_views'] = 1

        recognizer = build_recognizer(config.model)

        with torch.no_grad():

            img_list = [img[None, :] for img in imgs]

            for one_img in img_list:

                recognizer(one_img, None, return_loss=False)





def test_csn():

    config = get_recognizer_cfg(

        'csn/ircsn_ig65m_pretrained_r152_32x2x1_58e_kinetics400_rgb.py')

    config.model['backbone']['pretrained2d'] = False

    config.model['backbone']['pretrained'] = None



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 8, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    # parrots 3dconv is only implemented on gpu

    if torch.__version__ == 'parrots':

        if torch.cuda.is_available():

            recognizer = recognizer.cuda()

            imgs = imgs.cuda()

            gt_labels = gt_labels.cuda()

            losses = recognizer(imgs, gt_labels)

            assert isinstance(losses, dict)



            # Test forward test

            with torch.no_grad():

                img_list = [img[None, :] for img in imgs]

                for one_img in img_list:

                    recognizer(one_img, None, return_loss=False)



            # Test forward gradcam

            recognizer(imgs, gradcam=True)

            for one_img in img_list:

                recognizer(one_img, gradcam=True)

    else:

        losses = recognizer(imgs, gt_labels)

        assert isinstance(losses, dict)



        # Test forward test

        with torch.no_grad():

            img_list = [img[None, :] for img in imgs]

            for one_img in img_list:

                recognizer(one_img, None, return_loss=False)



        # Test forward gradcam

        recognizer(imgs, gradcam=True)

        for one_img in img_list:

            recognizer(one_img, gradcam=True)





def test_tpn():

    config = get_recognizer_cfg(

        'tpn/tpn_slowonly_r50_8x8x1_150e_kinetics_rgb.py')

    config.model['backbone']['pretrained'] = None



    recognizer = build_recognizer(config.model)



    input_shape = (1, 8, 3, 1, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    losses = recognizer(imgs, gt_labels)

    assert isinstance(losses, dict)



    # Test forward test

    with torch.no_grad():

        img_list = [img[None, :] for img in imgs]

        for one_img in img_list:

            recognizer(one_img, None, return_loss=False)



    # Test forward gradcam

    recognizer(imgs, gradcam=True)

    for one_img in img_list:

        recognizer(one_img, gradcam=True)



    # Test dummy forward

    with torch.no_grad():

        _recognizer = build_recognizer(config.model)

        img_list = [img[None, :] for img in imgs]

        if hasattr(_recognizer, 'forward_dummy'):

            _recognizer.forward = _recognizer.forward_dummy

        for one_img in img_list:

            _recognizer(one_img)





def test_timesformer():

    config = get_recognizer_cfg(

        'timesformer/timesformer_divST_8x32x1_15e_kinetics400_rgb.py')

    config.model['backbone']['pretrained'] = None

    config.model['backbone']['img_size'] = 32



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 8, 32, 32)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    losses = recognizer(imgs, gt_labels)

    assert isinstance(losses, dict)



    # Test forward test

    with torch.no_grad():

        img_list = [img[None, :] for img in imgs]

        for one_img in img_list:

            recognizer(one_img, None, return_loss=False)



    # Test forward gradcam

    recognizer(imgs, gradcam=True)

    for one_img in img_list:

        recognizer(one_img, gradcam=True)





def test_c3d():

    config = get_recognizer_cfg('c3d/c3d_sports1m_16x1x1_45e_ucf101_rgb.py')

    config.model['backbone']['pretrained'] = None



    recognizer = build_recognizer(config.model)



    input_shape = (1, 3, 3, 16, 112, 112)

    demo_inputs = generate_recognizer_demo_inputs(input_shape, '3D')



    imgs = demo_inputs['imgs']

    gt_labels = demo_inputs['gt_labels']



    losses = recognizer(imgs, gt_labels)

    assert isinstance(losses, dict)



    # Test forward test

    with torch.no_grad():

        img_list = [img[None, :] for img in imgs]

        for one_img in img_list:

            recognizer(one_img, None, return_loss=False)



    # Test forward gradcam

    recognizer(imgs, gradcam=True)

    for one_img in img_list:

        recognizer(one_img, gradcam=True)