Ywj

def preprocess_image(self, batched_inputs): for a in batched_inputs: img = a["image"].cpu().permute(1, 2, 0).numpy().astype(np.uint8) **ins = a['instances']** bboxes = ins.gt_boxes.tensor.cpu().numpy().astype(int) clss = ins.gt_classes.cpu().numpy() im = img.copy() bit_masks = ins.gt_masks.tensor.cpu().numpy() im = vis_bitmasks(im,...

AttributeError: 'dict' object has no attribute 'size'

1

AttributeError: 'dict' object has no attribute 'size'

OSError: [Errno 9] Bad file descriptor

1

OSError: [Errno 9] Bad file descriptor

AttributeError: 'str' object has no attribute 'keys'

1

python tools/evaluate.py --config ccaddn_ocrnet_hrnet_w18_kitti.yml --model caddn_ocrnet_hrnet_w18_kitti/model.pdparams

dd3d怎么自己深度估计训练

1

修改网路结构后，怎么自己进行对DD3D的dense depth预训练

建议

5

建议出一个选项可以将commit内容复制到剪切板，不切换到source control界面。有子模块时候commit信息有时不会填充到正确位置。