forked from huggingface/pytorch-image-models
-
Notifications
You must be signed in to change notification settings - Fork 0
/
inference.py
executable file
·365 lines (315 loc) · 15.6 KB
/
inference.py
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
#!/usr/bin/env python3
"""PyTorch Inference Script
An example inference script that outputs top-k class ids for images in a folder into a csv.
Hacked together by / Copyright 2020 Ross Wightman (https://github.com/rwightman)
"""
import argparse
import json
import logging
import os
import time
from contextlib import suppress
from functools import partial
import numpy as np
import pandas as pd
import torch
from timm.data import create_dataset, create_loader, resolve_data_config, ImageNetInfo, infer_imagenet_subset
from timm.layers import apply_test_time_pool
from timm.models import create_model
from timm.utils import AverageMeter, setup_default_logging, set_jit_fuser, ParseKwargs
try:
from apex import amp
has_apex = True
except ImportError:
has_apex = False
has_native_amp = False
try:
if getattr(torch.cuda.amp, 'autocast') is not None:
has_native_amp = True
except AttributeError:
pass
try:
from functorch.compile import memory_efficient_fusion
has_functorch = True
except ImportError as e:
has_functorch = False
has_compile = hasattr(torch, 'compile')
_FMT_EXT = {
'json': '.json',
'json-record': '.json',
'json-split': '.json',
'parquet': '.parquet',
'csv': '.csv',
}
torch.backends.cudnn.benchmark = True
_logger = logging.getLogger('inference')
parser = argparse.ArgumentParser(description='PyTorch ImageNet Inference')
parser.add_argument('data', nargs='?', metavar='DIR', const=None,
help='path to dataset (*deprecated*, use --data-dir)')
parser.add_argument('--data-dir', metavar='DIR',
help='path to dataset (root dir)')
parser.add_argument('--dataset', metavar='NAME', default='',
help='dataset type + name ("<type>/<name>") (default: ImageFolder or ImageTar if empty)')
parser.add_argument('--split', metavar='NAME', default='validation',
help='dataset split (default: validation)')
parser.add_argument('--model', '-m', metavar='MODEL', default='resnet50',
help='model architecture (default: resnet50)')
parser.add_argument('-j', '--workers', default=2, type=int, metavar='N',
help='number of data loading workers (default: 2)')
parser.add_argument('-b', '--batch-size', default=256, type=int,
metavar='N', help='mini-batch size (default: 256)')
parser.add_argument('--img-size', default=None, type=int,
metavar='N', help='Input image dimension, uses model default if empty')
parser.add_argument('--in-chans', type=int, default=None, metavar='N',
help='Image input channels (default: None => 3)')
parser.add_argument('--input-size', default=None, nargs=3, type=int,
metavar='N N N', help='Input all image dimensions (d h w, e.g. --input-size 3 224 224), uses model default if empty')
parser.add_argument('--use-train-size', action='store_true', default=False,
help='force use of train input size, even when test size is specified in pretrained cfg')
parser.add_argument('--crop-pct', default=None, type=float,
metavar='N', help='Input image center crop pct')
parser.add_argument('--crop-mode', default=None, type=str,
metavar='N', help='Input image crop mode (squash, border, center). Model default if None.')
parser.add_argument('--mean', type=float, nargs='+', default=None, metavar='MEAN',
help='Override mean pixel value of dataset')
parser.add_argument('--std', type=float, nargs='+', default=None, metavar='STD',
help='Override std deviation of of dataset')
parser.add_argument('--interpolation', default='', type=str, metavar='NAME',
help='Image resize interpolation type (overrides model)')
parser.add_argument('--num-classes', type=int, default=None,
help='Number classes in dataset')
parser.add_argument('--class-map', default='', type=str, metavar='FILENAME',
help='path to class to idx mapping file (default: "")')
parser.add_argument('--log-freq', default=10, type=int,
metavar='N', help='batch logging frequency (default: 10)')
parser.add_argument('--checkpoint', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('--pretrained', dest='pretrained', action='store_true',
help='use pre-trained model')
parser.add_argument('--num-gpu', type=int, default=1,
help='Number of GPUS to use')
parser.add_argument('--test-pool', dest='test_pool', action='store_true',
help='enable test time pool')
parser.add_argument('--channels-last', action='store_true', default=False,
help='Use channels_last memory layout')
parser.add_argument('--device', default='cuda', type=str,
help="Device (accelerator) to use.")
parser.add_argument('--amp', action='store_true', default=False,
help='use Native AMP for mixed precision training')
parser.add_argument('--amp-dtype', default='float16', type=str,
help='lower precision AMP dtype (default: float16)')
parser.add_argument('--fuser', default='', type=str,
help="Select jit fuser. One of ('', 'te', 'old', 'nvfuser')")
parser.add_argument('--model-kwargs', nargs='*', default={}, action=ParseKwargs)
scripting_group = parser.add_mutually_exclusive_group()
scripting_group.add_argument('--torchscript', default=False, action='store_true',
help='torch.jit.script the full model')
scripting_group.add_argument('--torchcompile', nargs='?', type=str, default=None, const='inductor',
help="Enable compilation w/ specified backend (default: inductor).")
scripting_group.add_argument('--aot-autograd', default=False, action='store_true',
help="Enable AOT Autograd support.")
parser.add_argument('--results-dir', type=str, default=None,
help='folder for output results')
parser.add_argument('--results-file', type=str, default=None,
help='results filename (relative to results-dir)')
parser.add_argument('--results-format', type=str, nargs='+', default=['csv'],
help='results format (one of "csv", "json", "json-split", "parquet")')
parser.add_argument('--results-separate-col', action='store_true', default=False,
help='separate output columns per result index.')
parser.add_argument('--topk', default=1, type=int,
metavar='N', help='Top-k to output to CSV')
parser.add_argument('--fullname', action='store_true', default=False,
help='use full sample name in output (not just basename).')
parser.add_argument('--filename-col', type=str, default='filename',
help='name for filename / sample name column')
parser.add_argument('--index-col', type=str, default='index',
help='name for output indices column(s)')
parser.add_argument('--label-col', type=str, default='label',
help='name for output indices column(s)')
parser.add_argument('--output-col', type=str, default=None,
help='name for logit/probs output column(s)')
parser.add_argument('--output-type', type=str, default='prob',
help='output type colum ("prob" for probabilities, "logit" for raw logits)')
parser.add_argument('--label-type', type=str, default='description',
help='type of label to output, one of "none", "name", "description", "detailed"')
parser.add_argument('--include-index', action='store_true', default=False,
help='include the class index in results')
parser.add_argument('--exclude-output', action='store_true', default=False,
help='exclude logits/probs from results, just indices. topk must be set !=0.')
def main():
setup_default_logging()
args = parser.parse_args()
# might as well try to do something useful...
args.pretrained = args.pretrained or not args.checkpoint
if torch.cuda.is_available():
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.benchmark = True
device = torch.device(args.device)
# resolve AMP arguments based on PyTorch / Apex availability
amp_autocast = suppress
if args.amp:
assert has_native_amp, 'Please update PyTorch to a version with native AMP (or use APEX).'
assert args.amp_dtype in ('float16', 'bfloat16')
amp_dtype = torch.bfloat16 if args.amp_dtype == 'bfloat16' else torch.float16
amp_autocast = partial(torch.autocast, device_type=device.type, dtype=amp_dtype)
_logger.info('Running inference in mixed precision with native PyTorch AMP.')
else:
_logger.info('Running inference in float32. AMP not enabled.')
if args.fuser:
set_jit_fuser(args.fuser)
# create model
in_chans = 3
if args.in_chans is not None:
in_chans = args.in_chans
elif args.input_size is not None:
in_chans = args.input_size[0]
model = create_model(
args.model,
num_classes=args.num_classes,
in_chans=in_chans,
pretrained=args.pretrained,
checkpoint_path=args.checkpoint,
**args.model_kwargs,
)
if args.num_classes is None:
assert hasattr(model, 'num_classes'), 'Model must have `num_classes` attr if not set on cmd line/config.'
args.num_classes = model.num_classes
_logger.info(
f'Model {args.model} created, param count: {sum([m.numel() for m in model.parameters()])}')
data_config = resolve_data_config(vars(args), model=model)
test_time_pool = False
if args.test_pool:
model, test_time_pool = apply_test_time_pool(model, data_config)
model = model.to(device)
model.eval()
if args.channels_last:
model = model.to(memory_format=torch.channels_last)
if args.torchscript:
model = torch.jit.script(model)
elif args.torchcompile:
assert has_compile, 'A version of torch w/ torch.compile() is required for --compile, possibly a nightly.'
torch._dynamo.reset()
model = torch.compile(model, backend=args.torchcompile)
elif args.aot_autograd:
assert has_functorch, "functorch is needed for --aot-autograd"
model = memory_efficient_fusion(model)
if args.num_gpu > 1:
model = torch.nn.DataParallel(model, device_ids=list(range(args.num_gpu)))
root_dir = args.data or args.data_dir
dataset = create_dataset(
root=root_dir,
name=args.dataset,
split=args.split,
class_map=args.class_map,
)
if test_time_pool:
data_config['crop_pct'] = 1.0
workers = 1 if 'tfds' in args.dataset or 'wds' in args.dataset else args.workers
loader = create_loader(
dataset,
batch_size=args.batch_size,
use_prefetcher=True,
num_workers=workers,
**data_config,
)
to_label = None
if args.label_type in ('name', 'description', 'detail'):
imagenet_subset = infer_imagenet_subset(model)
if imagenet_subset is not None:
dataset_info = ImageNetInfo(imagenet_subset)
if args.label_type == 'name':
to_label = lambda x: dataset_info.index_to_label_name(x)
elif args.label_type == 'detail':
to_label = lambda x: dataset_info.index_to_description(x, detailed=True)
else:
to_label = lambda x: dataset_info.index_to_description(x)
to_label = np.vectorize(to_label)
else:
_logger.error("Cannot deduce ImageNet subset from model, no labelling will be performed.")
top_k = min(args.topk, args.num_classes)
batch_time = AverageMeter()
end = time.time()
all_indices = []
all_labels = []
all_outputs = []
use_probs = args.output_type == 'prob'
with torch.no_grad():
for batch_idx, (input, _) in enumerate(loader):
with amp_autocast():
output = model(input)
if use_probs:
output = output.softmax(-1)
if top_k:
output, indices = output.topk(top_k)
np_indices = indices.cpu().numpy()
if args.include_index:
all_indices.append(np_indices)
if to_label is not None:
np_labels = to_label(np_indices)
all_labels.append(np_labels)
all_outputs.append(output.cpu().numpy())
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if batch_idx % args.log_freq == 0:
_logger.info('Predict: [{0}/{1}] Time {batch_time.val:.3f} ({batch_time.avg:.3f})'.format(
batch_idx, len(loader), batch_time=batch_time))
all_indices = np.concatenate(all_indices, axis=0) if all_indices else None
all_labels = np.concatenate(all_labels, axis=0) if all_labels else None
all_outputs = np.concatenate(all_outputs, axis=0).astype(np.float32)
filenames = loader.dataset.filenames(basename=not args.fullname)
output_col = args.output_col or ('prob' if use_probs else 'logit')
data_dict = {args.filename_col: filenames}
if args.results_separate_col and all_outputs.shape[-1] > 1:
if all_indices is not None:
for i in range(all_indices.shape[-1]):
data_dict[f'{args.index_col}_{i}'] = all_indices[:, i]
if all_labels is not None:
for i in range(all_labels.shape[-1]):
data_dict[f'{args.label_col}_{i}'] = all_labels[:, i]
for i in range(all_outputs.shape[-1]):
data_dict[f'{output_col}_{i}'] = all_outputs[:, i]
else:
if all_indices is not None:
if all_indices.shape[-1] == 1:
all_indices = all_indices.squeeze(-1)
data_dict[args.index_col] = list(all_indices)
if all_labels is not None:
if all_labels.shape[-1] == 1:
all_labels = all_labels.squeeze(-1)
data_dict[args.label_col] = list(all_labels)
if all_outputs.shape[-1] == 1:
all_outputs = all_outputs.squeeze(-1)
data_dict[output_col] = list(all_outputs)
df = pd.DataFrame(data=data_dict)
results_filename = args.results_file
if results_filename:
filename_no_ext, ext = os.path.splitext(results_filename)
if ext and ext in _FMT_EXT.values():
# if filename provided with one of expected ext,
# remove it as it will be added back
results_filename = filename_no_ext
else:
# base default filename on model name + img-size
img_size = data_config["input_size"][1]
results_filename = f'{args.model}-{img_size}'
if args.results_dir:
results_filename = os.path.join(args.results_dir, results_filename)
for fmt in args.results_format:
save_results(df, results_filename, fmt)
print(f'--result')
print(df.set_index(args.filename_col).to_json(orient='index', indent=4))
def save_results(df, results_filename, results_format='csv', filename_col='filename'):
results_filename += _FMT_EXT[results_format]
if results_format == 'parquet':
df.set_index(filename_col).to_parquet(results_filename)
elif results_format == 'json':
df.set_index(filename_col).to_json(results_filename, indent=4, orient='index')
elif results_format == 'json-records':
df.to_json(results_filename, lines=True, orient='records')
elif results_format == 'json-split':
df.to_json(results_filename, indent=4, orient='split', index=False)
else:
df.to_csv(results_filename, index=False)
if __name__ == '__main__':
main()