File size: 7,261 Bytes
e8861c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
https://github.com/facebookresearch/detr/blob/main/engine.py

by lyuwenyu
"""

import math
import os
import sys
import pathlib
from typing import Iterable

import torch
import torch.amp 

from src.data import CocoEvaluator
from src.misc import (MetricLogger, SmoothedValue, reduce_dict)


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, **kwargs):
    model.train()
    criterion.train()
    metric_logger = MetricLogger(delimiter="  ")
    metric_logger.add_meter('lr', SmoothedValue(window_size=1, fmt='{value:.6f}'))
    # metric_logger.add_meter('class_error', SmoothedValue(window_size=1, fmt='{value:.2f}'))
    header = 'Epoch: [{}]'.format(epoch)
    print_freq = kwargs.get('print_freq', 10)
    
    ema = kwargs.get('ema', None)
    scaler = kwargs.get('scaler', None)

    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]

        if scaler is not None:
            with torch.autocast(device_type=str(device), cache_enabled=True):
                outputs = model(samples, targets)
            
            with torch.autocast(device_type=str(device), enabled=False):
                loss_dict = criterion(outputs, targets)

            loss = sum(loss_dict.values())
            scaler.scale(loss).backward()
            
            if max_norm > 0:
                scaler.unscale_(optimizer)
                torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)

            scaler.step(optimizer)
            scaler.update()
            optimizer.zero_grad()

        else:
            outputs = model(samples, targets)
            loss_dict = criterion(outputs, targets)
            
            loss = sum(loss_dict.values())
            optimizer.zero_grad()
            loss.backward()
            
            if max_norm > 0:
                torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)

            optimizer.step()
        
        # ema 
        if ema is not None:
            ema.update(model)

        loss_dict_reduced = reduce_dict(loss_dict)
        loss_value = sum(loss_dict_reduced.values())

        if not math.isfinite(loss_value):
            print("Loss is {}, stopping training".format(loss_value))
            print(loss_dict_reduced)
            sys.exit(1)

        metric_logger.update(loss=loss_value, **loss_dict_reduced)
        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: torch.nn.Module, criterion: torch.nn.Module, postprocessors, data_loader, base_ds, device, output_dir):
    model.eval()
    criterion.eval()

    metric_logger = MetricLogger(delimiter="  ")
    # metric_logger.add_meter('class_error', SmoothedValue(window_size=1, fmt='{value:.2f}'))
    header = 'Test:'

    # iou_types = tuple(k for k in ('segm', 'bbox') if k in postprocessors.keys())
    iou_types = postprocessors.iou_types
    coco_evaluator = CocoEvaluator(base_ds, iou_types)
    # coco_evaluator.coco_eval[iou_types[0]].params.iouThrs = [0, 0.1, 0.5, 0.75]

    panoptic_evaluator = None
    # if 'panoptic' in postprocessors.keys():
    #     panoptic_evaluator = PanopticEvaluator(
    #         data_loader.dataset.ann_file,
    #         data_loader.dataset.ann_folder,
    #         output_dir=os.path.join(output_dir, "panoptic_eval"),
    #     )

    for samples, targets in metric_logger.log_every(data_loader, 10, header):
        samples = samples.to(device)
        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]

        # with torch.autocast(device_type=str(device)):
        #     outputs = model(samples)

        outputs = model(samples)
        print(outputs)
        # loss_dict = criterion(outputs, targets)
        # weight_dict = criterion.weight_dict
        # # reduce losses over all GPUs for logging purposes
        # loss_dict_reduced = 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'])

        orig_target_sizes = torch.stack([t["orig_size"] for t in targets], dim=0)        
        results = postprocessors(outputs, orig_target_sizes)
        # results = postprocessors(outputs, targets)

        # if 'segm' in postprocessors.keys():
        #     target_sizes = torch.stack([t["size"] for t in targets], dim=0)
        #     results = postprocessors['segm'](results, outputs, orig_target_sizes, 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)

        # if panoptic_evaluator is not None:
        #     res_pano = postprocessors["panoptic"](outputs, target_sizes, orig_target_sizes)
        #     for i, target in enumerate(targets):
        #         image_id = target["image_id"].item()
        #         file_name = f"{image_id:012d}.png"
        #         res_pano[i]["image_id"] = image_id
        #         res_pano[i]["file_name"] = file_name
        #     panoptic_evaluator.update(res_pano)

    # 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()
    if panoptic_evaluator is not None:
        panoptic_evaluator.synchronize_between_processes()

    # accumulate predictions from all images
    if coco_evaluator is not None:
        coco_evaluator.accumulate()
        coco_evaluator.summarize()

    # panoptic_res = None
    # if panoptic_evaluator is not None:
    #     panoptic_res = panoptic_evaluator.summarize()
    
    stats = {}
    # stats = {k: meter.global_avg for k, meter in metric_logger.meters.items()}
    if coco_evaluator is not None:
        if 'bbox' in iou_types:
            stats['coco_eval_bbox'] = coco_evaluator.coco_eval['bbox'].stats.tolist()
        if 'segm' in iou_types:
            stats['coco_eval_masks'] = coco_evaluator.coco_eval['segm'].stats.tolist()
            
    # if panoptic_res is not None:
    #     stats['PQ_all'] = panoptic_res["All"]
    #     stats['PQ_th'] = panoptic_res["Things"]
    #     stats['PQ_st'] = panoptic_res["Stuff"]

    return stats, coco_evaluator