liguilan1227

> Can you please help me i am getting some errors which i have mentioned in the issues I would like to help you but I didnot meet this error...

> yes, I have tried it, and change the layers name from `conv4_3_norm_mbox_conf` to `ssd_cls1conv2`, but it show that `bias:0` does not exist after running. I met the problem,too. Have...

> 嗨@ markshih91 > > 我在一个玩具数据集上训练了您的模型，该任务只是预测白色背景上随机生成的黑色矩形的边缘，这应该是一个简单的任务。 > > 此处的损耗和val损耗似乎很低，但预测似乎相差甚远（预测中的负值似乎是常态，我已将其截断了）。这是因为解码层中的错误吗？ > > 这是损失的快照。 >  > > 预测（以红色显示）- >  > > 我的模型配置为使用以下配置进行训练 > > ``` > aspect_ratios_per_layer = [[1.0, 2.0,...

Is the checkpoint neccessary to train the net? When I run it, the error occured: Traceback (most recent call last): File "main.py", line 77, in assert os.path.isdir('checkpoint'), 'Error: no checkpoint...