大大们指导，复现faster rcnn时碰到一个问题：提示local variable 'pooled_feat' referenced before assignment

Question

问题遇到的现象和发生背景

问题相关代码，请勿粘贴截图

if cfg.POOLING_MODE == 'align':
            pooled_feat = self.RCNN_roi_align(base_feat, rois.view(-1, 5))
        elif cfg.POOLING_MODE == 'pool':
            pooled_feat = self.RCNN_roi_pool(base_feat, rois.view(-1, 5))

        # feed pooled features to top model
        pooled_feat = self._head_to_tail(pooled_feat)

        # compute bbox offset
        bbox_pred = self.RCNN_bbox_pred(pooled_feat)
        if self.training and not self.class_agnostic:
            # select the corresponding columns according to roi labels
            bbox_pred_view = bbox_pred.view(bbox_pred.size(0), int(bbox_pred.size(1) / 4), 4)
            bbox_pred_select = torch.gather(bbox_pred_view, 1, rois_label.view(rois_label.size(0), 1, 1).expand(rois_label.size(0), 1, 4))
            bbox_pred = bbox_pred_select.squeeze(1)

        # compute object classification probability
        cls_score = self.RCNN_cls_score(pooled_feat)
        cls_prob = F.softmax(cls_score, 1)

运行结果及报错内容

Traceback (most recent call last):
  File "/home/jsj/faster-rcnn.pytorch-pytorch-1.0/trainval_net.py", line 323, in <module>
    rois_label = fasterRCNN(im_data, im_info, gt_boxes, num_boxes)
  File "/home/jsj/anaconda3/envs/faster-rcnn/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/jsj/faster-rcnn.pytorch-pytorch-1.0/lib/model/faster_rcnn/faster_rcnn.py", line 83, in forward
    pooled_feat = self._head_to_tail(pooled_feat)
**UnboundLocalError: local variable 'pooled_feat' referenced before assignment**

我的解答思路和尝试过的方法

试过在if前pooled_feat=0，但是后续在vgg16文件中会报错'int' object has no attribute 'view'

我想要达到的结果

Answer 1

model文件下的config里__C.POOLING_MODE 是'crop'，所以未赋值。