chen wei

The _reshape_layer method

5

I can't understand the `_reshape_layer` method in the following code: ```python rpn_cls_score_reshape = self._reshape_layer(rpn_cls_score, 2, 'rpn_cls_score_reshape') ``` Why not write like this: ``` cls_score_shape = tf.shape(rpn_cls_score_reshape) rpn_cls_score_reshape = tf.reshape(rpn_cls_score, [cls_score_shape[0],...

nan value

6

I reimplemented in tensorflow, but find it is hard to train. It is very easy get nan value. How could to avoid this?

accuracy on casia training dataset

4

I am using the sphereface code implemented by pytorch in the third-party re-implementation lists. After 20 epochs, I only get `93.3490%` accuracy on training dataset. Does this correct? This model...

The first stage training average face shape

1

The paper said `The first stage only takes the input image as the initial landmarks are always assumed to be the average face shape S0 located in the middle`, but...

```Python from nms2.nms import py_nms_wrapper, cpu_nms_wrapper, gpu_nms_wrapper boxes2 = np.array([ [0, 100, 0, 0, 100, 0, 100, 100, 0.99], [10, 110, 10, 10, 130, 10, 150, 110, 0.88],#keep 0.68 [150,...

ohem

1

Have you tried `ohem`. I have tried and found it seems have no effective. I have tried with several different parameters. I don't know it was my code error or...

why not using softmax loss function

1

The supervisied loss function used for mnist feature matching is [loss_lab = -T.mean(l_lab) + T.mean(z_exp_lab)](https://github.com/openai/improved-gan/blob/master/mnist_svhn_cifar10/train_mnist_feature_matching.py#L69) Why not use softmax loss function?

https://github.com/willard-yuan/pcv-book-code/blob/master/PCV/PCV/imagesearch/imagesearch.py#L58 ``` self.con.execute("insert into imwords(imid,wordid,vocname) values (?,?,?)", (imid,word,self.voc.name)) ``` 这行程序是不是有问题，这种写法写入数据库的不是wordid，而是每个image直方图中word的个数。

How to avoid nan exception?

3

I am using `ShangHaiTech Part A` to train model, but only a few iteration it get the `nan` excpetion. ``` Traceback (most recent call last): File "Counting-with-Focus-for-Free/code/main.py", line 50, in...