-
Notifications
You must be signed in to change notification settings - Fork 49
/
engine.py
189 lines (153 loc) · 8.78 KB
/
engine.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
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# Copyright (c) Institute of Information Processing, Leibniz University Hannover.
"""
Train and eval functions used in main.py
"""
import math
import sys
from typing import Iterable
import numpy as np
import torch
from datasets.coco_eval import CocoEvaluator
import util.misc as utils
from util.box_ops import rescale_bboxes
from lib.evaluation.sg_eval import BasicSceneGraphEvaluator, calculate_mR_from_evaluator_list
def train_one_epoch(model: torch.nn.Module, criterion: torch.nn.Module,
data_loader: Iterable, optimizer: torch.optim.Optimizer,
device: torch.device, epoch: int, max_norm: float = 0):
model.train()
criterion.train()
metric_logger = utils.MetricLogger(delimiter=" ")
metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value:.6f}'))
metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('sub_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('obj_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('rel_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
header = 'Epoch: [{}]'.format(epoch)
print_freq = 500
for samples, targets in metric_logger.log_every(data_loader, print_freq, header):
samples = samples.to(device)
targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
outputs = model(samples)
loss_dict = criterion(outputs, targets)
weight_dict = criterion.weight_dict
losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)
# reduce losses over all GPUs for logging purposes
loss_dict_reduced = utils.reduce_dict(loss_dict)
loss_dict_reduced_unscaled = {f'{k}_unscaled': v
for k, v in loss_dict_reduced.items()}
loss_dict_reduced_scaled = {k: v * weight_dict[k]
for k, v in loss_dict_reduced.items() if k in weight_dict}
losses_reduced_scaled = sum(loss_dict_reduced_scaled.values())
loss_value = losses_reduced_scaled.item()
if not math.isfinite(loss_value):
print("Loss is {}, stopping training".format(loss_value))
print(loss_dict_reduced)
sys.exit(1)
optimizer.zero_grad()
losses.backward()
if max_norm > 0:
torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)
optimizer.step()
metric_logger.update(loss=loss_value, **loss_dict_reduced_scaled, **loss_dict_reduced_unscaled)
metric_logger.update(class_error=loss_dict_reduced['class_error'])
metric_logger.update(sub_error=loss_dict_reduced['sub_error'])
metric_logger.update(obj_error=loss_dict_reduced['obj_error'])
metric_logger.update(rel_error=loss_dict_reduced['rel_error'])
metric_logger.update(lr=optimizer.param_groups[0]["lr"])
# gather the stats from all processes
metric_logger.synchronize_between_processes()
print("Averaged stats:", metric_logger)
return {k: meter.global_avg for k, meter in metric_logger.meters.items()}
@torch.no_grad()
def evaluate(model, criterion, postprocessors, data_loader, base_ds, device, args):
model.eval()
criterion.eval()
metric_logger = utils.MetricLogger(delimiter=" ")
metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('sub_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('obj_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('rel_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
header = 'Test:'
# initilize evaluator
evaluator = BasicSceneGraphEvaluator.all_modes(multiple_preds=False)
if args.eval:
evaluator_list = []
for index, name in enumerate(data_loader.dataset.rel_categories):
if index == 0:
continue
evaluator_list.append((index, name, BasicSceneGraphEvaluator.all_modes()))
else:
evaluator_list = None
iou_types = tuple(k for k in ('segm', 'bbox') if k in postprocessors.keys())
coco_evaluator = CocoEvaluator(base_ds, iou_types)
for samples, targets in metric_logger.log_every(data_loader, 100, header):
samples = samples.to(device)
targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
outputs = model(samples)
loss_dict = criterion(outputs, targets)
weight_dict = criterion.weight_dict
evaluate_rel_batch(outputs, targets, evaluator, evaluator_list)
# reduce losses over all GPUs for logging purposes
loss_dict_reduced = utils.reduce_dict(loss_dict)
loss_dict_reduced_scaled = {k: v * weight_dict[k]
for k, v in loss_dict_reduced.items() if k in weight_dict}
loss_dict_reduced_unscaled = {f'{k}_unscaled': v
for k, v in loss_dict_reduced.items()}
metric_logger.update(loss=sum(loss_dict_reduced_scaled.values()),
**loss_dict_reduced_scaled,
**loss_dict_reduced_unscaled)
metric_logger.update(class_error=loss_dict_reduced['class_error'])
metric_logger.update(sub_error=loss_dict_reduced['sub_error'])
metric_logger.update(obj_error=loss_dict_reduced['obj_error'])
metric_logger.update(rel_error=loss_dict_reduced['rel_error'])
orig_target_sizes = torch.stack([t["orig_size"] for t in targets], dim=0)
results = postprocessors['bbox'](outputs, orig_target_sizes)
res = {target['image_id'].item(): output for target, output in zip(targets, results)}
if coco_evaluator is not None:
coco_evaluator.update(res)
evaluator['sgdet'].print_stats()
if args.eval:
calculate_mR_from_evaluator_list(evaluator_list, 'sgdet')
# gather the stats from all processes
metric_logger.synchronize_between_processes()
print("Averaged stats:", metric_logger)
if coco_evaluator is not None:
coco_evaluator.synchronize_between_processes()
# accumulate predictions from all images
if coco_evaluator is not None:
coco_evaluator.accumulate()
coco_evaluator.summarize()
stats = {k: meter.global_avg for k, meter in metric_logger.meters.items()}
if coco_evaluator is not None:
if 'bbox' in postprocessors.keys():
stats['coco_eval_bbox'] = coco_evaluator.coco_eval['bbox'].stats.tolist()
return stats, coco_evaluator
def evaluate_rel_batch(outputs, targets, evaluator, evaluator_list):
for batch, target in enumerate(targets):
target_bboxes_scaled = rescale_bboxes(target['boxes'].cpu(), torch.flip(target['orig_size'],dims=[0]).cpu()).clone().numpy() # recovered boxes with original size
gt_entry = {'gt_classes': target['labels'].cpu().clone().numpy(),
'gt_relations': target['rel_annotations'].cpu().clone().numpy(),
'gt_boxes': target_bboxes_scaled}
sub_bboxes_scaled = rescale_bboxes(outputs['sub_boxes'][batch].cpu(), torch.flip(target['orig_size'],dims=[0]).cpu()).clone().numpy()
obj_bboxes_scaled = rescale_bboxes(outputs['obj_boxes'][batch].cpu(), torch.flip(target['orig_size'],dims=[0]).cpu()).clone().numpy()
pred_sub_scores, pred_sub_classes = torch.max(outputs['sub_logits'][batch].softmax(-1)[:, :-1], dim=1)
pred_obj_scores, pred_obj_classes = torch.max(outputs['obj_logits'][batch].softmax(-1)[:, :-1], dim=1)
rel_scores = outputs['rel_logits'][batch][:,1:-1].softmax(-1)
#
pred_entry = {'sub_boxes': sub_bboxes_scaled,
'sub_classes': pred_sub_classes.cpu().clone().numpy(),
'sub_scores': pred_sub_scores.cpu().clone().numpy(),
'obj_boxes': obj_bboxes_scaled,
'obj_classes': pred_obj_classes.cpu().clone().numpy(),
'obj_scores': pred_obj_scores.cpu().clone().numpy(),
'rel_scores': rel_scores.cpu().clone().numpy()}
evaluator['sgdet'].evaluate_scene_graph_entry(gt_entry, pred_entry)
if evaluator_list is not None:
for pred_id, _, evaluator_rel in evaluator_list:
gt_entry_rel = gt_entry.copy()
mask = np.in1d(gt_entry_rel['gt_relations'][:, -1], pred_id)
gt_entry_rel['gt_relations'] = gt_entry_rel['gt_relations'][mask, :]
if gt_entry_rel['gt_relations'].shape[0] == 0:
continue
evaluator_rel['sgdet'].evaluate_scene_graph_entry(gt_entry_rel, pred_entry)