-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathinference.py
More file actions
177 lines (152 loc) · 7.19 KB
/
inference.py
File metadata and controls
177 lines (152 loc) · 7.19 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
#!/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 os
import os.path as osp
import time
import argparse
import logging
import numpy as np
import torch
from timm.models import create_model, apply_test_time_pool
from timm.data import ImageDataset, create_loader, resolve_data_config
from timm.utils import AverageMeter, setup_default_logging
from timm.models.helpers import load_checkpoint
from datasets import *
import models as custom_models
from torchvision.models import shufflenet_v2_x2_0, shufflenet_v2_x1_5, mobilenet_v2, mnasnet1_0, mnasnet1_3, resnet18
torch.backends.cudnn.benchmark = True
_logger = logging.getLogger('inference')
parser = argparse.ArgumentParser(description='PyTorch ImageNet Inference')
parser.add_argument('data', metavar='DIR',
help='path to dataset')
parser.add_argument('--output_dir', metavar='DIR', default='./',
help='path to output files')
parser.add_argument('--model', '-m', metavar='MODEL', default='dpn92',
help='model architecture (default: dpn92)')
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')
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('--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=1000,
help='Number classes in dataset')
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('--no-test-pool', dest='no_test_pool', action='store_true',
help='disable test time pool')
parser.add_argument('--topk', default=5, type=int,
metavar='N', help='Top-k to output to CSV')
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
device = 'cpu' # 'cuda'
# create model
LOAD_CHECKPOINT = True
if args.model == 'shufflenet_v2_x2_0':
model = shufflenet_v2_x2_0(num_classes=args.num_classes)
elif args.model == 'shufflenet_v2_x1_5':
model = shufflenet_v2_x1_5(num_classes=args.num_classes)
elif args.model == 'mobilenet_v2':
model = mobilenet_v2(num_classes=args.num_classes)
elif args.model == 'mnasnet1_0':
model = mnasnet1_0(num_classes=args.num_classes)
elif args.model == 'mnasnet1_3':
model = mnasnet1_3(num_classes=args.num_classes)
elif args.model == 'resnet18':
model = resnet18(num_classes=args.num_classes)
elif args.model in custom_models.__all__:
if args.model == "mobileone":
model = custom_models.mobileone(variant='s3', num_classes=args.num_classes, inference_mode=False)
elif args.model == "pdcnet":
model = custom_models.pdcnet(variant='s1', num_classes=args.num_classes, inference_mode=False)
else:
ValueError(f"{args.model} is not support now.")
else:
model = create_model(
args.model,
num_classes=args.num_classes,
in_chans=3,
pretrained=args.pretrained,
checkpoint_path=args.checkpoint)
LOAD_CHECKPOINT = False
if LOAD_CHECKPOINT:
load_checkpoint(model, args.checkpoint)
if args.model in ["mobileone", "pdcnet"]:
model.eval()
model = custom_models.reparameterize_model(model)
model.inference_mode = True
_logger.info('Model %s created, param count: %d' %
(args.model, sum([m.numel() for m in model.parameters()])))
config = resolve_data_config(vars(args), model=model)
model, test_time_pool = (model, False) if args.no_test_pool else apply_test_time_pool(model, config)
if args.num_gpu > 1:
model = torch.nn.DataParallel(model, device_ids=list(range(args.num_gpu))).cuda()
else:
# model = model.cuda()
model = model.to(device)
dataset_eval = SAAS_Pdc_Apple_Dataset(
root=args.data,
split_file=osp.join(args.data, 'test_saas_pdc_apple_leaf_20220808.list'),
train=True
)
loader = create_loader(
dataset_eval,
input_size=config['input_size'],
batch_size=args.batch_size,
use_prefetcher=True,
interpolation=config['interpolation'],
mean=config['mean'],
std=config['std'],
num_workers=args.workers,
crop_pct=1.0 if test_time_pool else config['crop_pct'])
model.eval()
k = min(args.topk, args.num_classes)
batch_time = AverageMeter()
loader_len = len(loader)
end = time.time()
START = time.time()
topk_ids = []
with torch.no_grad():
for batch_idx, (input, _) in enumerate(loader):
# input = input.cuda()
input = input.to(device)
labels = model(input)
topk = labels.topk(k)[1]
topk_ids.append(topk.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))
# topk_ids = np.concatenate(topk_ids, axis=0)
END = time.time()
print('Time Cost: ', END - START)
print('Avg batch: ', (END - START)/loader_len, 'Avg img: ', (END - START)/(loader_len*args.batch_size))
# with open(os.path.join(args.output_dir, './topk_ids.csv'), 'w') as out_file:
# filenames = 'saas_pdc_apple' # loader.dataset.filenames(basename=True)
# for filename, label in zip(filenames, topk_ids):
# out_file.write('{0},{1}\n'.format(
# filename, ','.join([ str(v) for v in label])))
if __name__ == '__main__':
main()