我正在尝试使用 detectron2 框架提取类别检测高于某个阈值的区域特征。我稍后将在我的流程中使用这些功能(类似于:VilBert 第 3.1 节训练 ViLBERT)到目前为止,我已经使用此 config 训练了 Mask R-CNN,并根据一些自定义数据对其进行了微调。它表现良好。我想做的是从我训练的模型中提取生成的边界框的特征。
为什么我只得到一个 预测实例,但是当我查看时 在预测 CLS 分数,有超过 1 个通过 阈值?
我相信这是生成 ROI 特征的正确方法:
images = ImageList.from_tensors(lst[:1], size_divisibility=32).to("cuda") # preprocessed input tensor
#setup config
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml"))
cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.SOLVER.IMS_PER_BATCH = 1
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1 # only has one class (pnumonia)
#Just run these lines if you have the trained model im memory
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7 # set the testing threshold for this model
#build model
model = build_model(cfg)
DetectionCheckpointer(model).load("output/model_final.pth")
model.eval()#make sure its in eval mode
#run model
with torch.no_grad():
features = model.backbone(images.tensor.float())
proposals, _ = model.proposal_generator(images, features)
instances = model.roi_heads._forward_box(features, proposals)
然后
pred_boxes = [x.pred_boxes for x in instances]
rois = model.roi_heads.box_pooler([features[f] for f in model.roi_heads.in_features], pred_boxes)
这应该是我的投资回报率特征。
我非常困惑的是,我可以使用提案和提案框及其类别分数来获取该图像的前 n 个特征,而不是使用推理时生成的边界框。很酷,所以我尝试了以下方法:
proposal_boxes = [x.proposal_boxes for x in proposals]
proposal_rois = model.roi_heads.box_pooler([features[f] for f in model.roi_heads.in_features], proposal_boxes)
#found here: https://detectron2.readthedocs.io/_modules/detectron2/modeling/roi_heads/roi_heads.html
box_features = model.roi_heads.box_head(proposal_rois)
predictions = model.roi_heads.box_predictor(box_features)
pred_instances, losses = model.roi_heads.box_predictor.inference(predictions, proposals)
我应该在我的预测对象中获取我的提案框功能及其cls。检查这个 predictions 对象,我看到每个框的分数:
预测对象中的 CLS 分数
(tensor([[ 0.6308, -0.4926],
[-1.6662, 1.5430],
[-0.2080, 0.4856],
...,
[-6.9698, 6.6695],
[-5.6361, 5.4046],
[-4.4918, 4.3899]], device='cuda:0', grad_fn=<AddmmBackward>),
经过 softmaxing 并将这些 cls 分数放入数据框中并设置阈值 0.6 后,我得到:
pred_df = pd.DataFrame(predictions[0].softmax(-1).tolist())
pred_df[pred_df[0] > 0.6]
0 1
0 0.754618 0.245382
6 0.686816 0.313184
38 0.722627 0.277373
在我的预测对象中,我得到了相同的最高分,但只有 1 个实例而不是 2 个(我设置了
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7
):
预测实例:
[Instances(num_instances=1, image_height=800, image_width=800, fields=[pred_boxes: Boxes(tensor([[548.5992, 341.7193, 756.9728, 438.0507]], device='cuda:0',
grad_fn=<IndexBackward>)), scores: tensor([0.7546], device='cuda:0', grad_fn=<IndexBackward>), pred_classes: tensor([0], device='cuda:0')])]
预测还包含 张量:Nx4 或 Nx(Kx4) 边界框回归增量。我不太清楚它们的作用和外观:
预测对象中的边界框回归增量
tensor([[ 0.2502, 0.2461, -0.4559, -0.3304],
[-0.1359, -0.1563, -0.2821, 0.0557],
[ 0.7802, 0.5719, -1.0790, -1.3001],
...,
[-0.8594, 0.0632, 0.2024, -0.6000],
[-0.2020, -3.3195, 0.6745, 0.5456],
[-0.5542, 1.1727, 1.9679, -2.3912]], device='cuda:0',
grad_fn=<AddmmBackward>)
还有一点奇怪的是我的提案框和我的预测框不同但相似:
提案边界框
[Boxes(tensor([[532.9427, 335.8969, 761.2068, 438.8086],#this box vs the instance box
[102.7041, 352.5067, 329.4510, 440.7240],
[499.2719, 317.9529, 764.1958, 448.1386],
...,
[ 25.2890, 379.3329, 28.6030, 429.9694],
[127.1215, 392.6055, 328.6081, 489.0793],
[164.5633, 275.6021, 295.0134, 462.7395]], device='cuda:0'))]
你就快到了。查看roi_heads.box_predictor.inference(),您会发现它并不简单地对候选框的分数进行排序。首先,它应用框增量来重新调整提案框。然后,它计算非极大值抑制以删除非重叠框(同时还应用其他超级设置,例如分数阈值)。最后,它根据得分对前 k 个框进行排名。这可能解释了为什么您的方法产生相同的框分数但输出框的数量及其坐标不同。
回到你原来的问题,以下是在一次推理过程中提取建议框特征的方法:
image = cv2.imread('my_image.jpg')
height, width = image.shape[:2]
image = torch.as_tensor(image.astype("float32").transpose(2, 0, 1))
inputs = [{"image": image, "height": height, "width": width}]
with torch.no_grad():
images = model.preprocess_image(inputs) # don't forget to preprocess
features = model.backbone(images.tensor) # set of cnn features
proposals, _ = model.proposal_generator(images, features, None) # RPN
features_ = [features[f] for f in model.roi_heads.box_in_features]
box_features = model.roi_heads.box_pooler(features_, [x.proposal_boxes for x in proposals])
box_features = model.roi_heads.box_head(box_features) # features of all 1k candidates
predictions = model.roi_heads.box_predictor(box_features)
pred_instances, pred_inds = model.roi_heads.box_predictor.inference(predictions, proposals)
pred_instances = model.roi_heads.forward_with_given_boxes(features, pred_instances)
# output boxes, masks, scores, etc
pred_instances = model._postprocess(pred_instances, inputs, images.image_sizes) # scale box to orig size
# features of the proposed boxes
feats = box_features[pred_inds]