Jia Li

Why need define "log_sum_exp" other than use the cross entropy loss in pytorch?

1

I'm a green hand in pytorch. Any help is welcomed. Thank you!

How to undersatand the criterion？

3

in demo.ipynb： `score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1]) score_with_dist_prior = sum(score_midpts)/len(score_midpts) \ + min(0.5*oriImg.shape[0]/norm-1, 0) criterion1 = len(np.nonzero(score_midpts > param['thre2'])[0]) > 0.8 * len(score_midpts) # parm['thre2'] = 0.05 criterion2...

Why is the output shape of discriminator is (None, 2)?

1

Hi everyone. I'm a green hand in GAN. Seeing the following code: `def discriminator_network(input_image_tensor): """ The discriminator network, Dφ, contains 5 convolution layers and 2 max-pooling layers. :param input_image_tensor: Input...

the performace of training

6

HI~ Grateful for your work! I run the code, setting the epoch to 6000, but the performance is seemed to be poor. The refined images has no difference with the...

Could you please provide the average FPS number on COCO test-dev dataset? Thank you very much.

Could you please provide the detailed results on COCO test-dev dataset for the convenient of citing your paper? In the TPAMI version, only part of the AP entries is reported...

Dose Apex support Transformer or Vision Transformer considering the existence of Layer Norm layers and statistics synchronous across GPUs?

https://github.com/GengDavid/pytorch-cpn/blob/48696a9203ad6dac78cf7e9e74b572b77f30aad9/networks/refineNet.py#L65 Why the final layer appends a BN layer? Why the output is normalized? Could you give me a hint? Thank you!

Hi~ I have tried to estimate with only one stage of hourglass network, but the performance is very poor. How can I improve it? The input size of training images...

Do you use BN layers? Thank you~