Tomhouxin

DBnet 使用ploy方式，检测弯曲文本，有没有预训练模型呀

10

由于样本数据比较少，只有400张，单纯的用resnet18模型做预训练模型太难收敛了，如果用quad没有问题，但是样本大部分是弯曲样本，所以来请教一下，谢谢！

RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed.

1

@lizhengwei1992 , 在训练的时候，计算交叉熵这里cross_entropy_loss = criterion(seg, mask_gt[:, 0, :, :].long())报错，查了些资料没搞明白什么原因，其中criterion的参数shape如下 seg.shape torch.Size([1, 2, 256, 256]) mask_gt torch.Size([1, 256, 256]) 能帮忙看看如何解决么

It seems to be the best model， when i use it， got error： myModel.eval() AttributeError: 'dict' object has no attribute 'eval' I wonder if this model is better than model_obj.pth

test m_net

3

在测试test里的m_net时候，发现代码跑不通，原因如下 1， trimap = np.eye(3)[trimap.reshape(-1)].reshape(list(trimap.shape) + [3]) 这里应该是准备把一通道的trimap变成三通道，但np.eye(3)[trimap.reshape(-1)]会out of bounds，3*3的对角矩阵下标越界 2，frame_seg = seg_process(args, (tensor_img, tensor_tri), net, trimap=trimap_src) 应该把最后一个参数去掉，seg_process方法没有这个参数

When I was running demo.py, I found that the template of weights.18-4.06. Hdf5 was time-consuming to predict, so I felt whether the template could be improved

load tflite model with shufflenet, get error

1

RuntimeError: tensorflow/lite/kernels/transpose.cc Transpose op only supports 1D-4D input arrays.Node number 9 (TRANSPOSE) failed to prepare

训练数据为什么不需要给出坐标，而是直接一张图呀

Assertion `cur_target >= 0 && cur_target < n_classes' failed

1

L_t = criterion(trimap_pre, trimap_gt[:,0,:,:].long()) got error

你好！ 我看里面有shufflenet和mobilenet作为主干网络，那是不是应该可以多分类呢,比如（飞机，汽车，船......）

Input side face map, output positive face map？

5

hello, I don't understand what you're result, Input side face map, output positive face map?