def evaluate(model, criterion, postprocessors, data_loader, base_ds, device, output_dir):
model.eval()
criterion.eval()
metric_logger = utils.MetricLogger(delimiter=" ")
metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
header = 'Test:'
iou_types = tuple(k for k in ('segm', 'bbox') if k in postprocessors.keys())
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]
outputs = model(samples)
loss_dict = criterion(outputs, targets)
weight_dict = criterion.weight_dict
# 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'])
orig_target_sizes = torch.stack([t["orig_size"] for t in targets], dim=0)
results = postprocessors['bbox'](outputs, orig_target_sizes)
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, targets)
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 = {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()
if 'segm' in postprocessors.keys():
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