MTCNN-Tensorflow
MTCNN-Tensorflow copied to clipboard
AITTSMD
Reproduce MTCNN using Tensorflow
请问boundbox_regression输出的四个值，是关于【左上角坐标，宽，高】的，还是【左上角坐标，右下角坐标】的？代码貌似和论文不一致，求教。
执行: python prepare_data/gen_hard_example.py --test_mode=R_Net 会先把PNet先跑一遍,这个很耗费时间,请问正常吗?
梯度爆炸问题
用自有数据训练95点，训练P-NET过程中出现梯度爆炸了，请问怎么解决啊 2018-08-19 11:53:56.928519 : Step: 10, accuracy: 0.963731, cls loss: 0.328417, bbox loss: 0.195085, landmark loss: nan,L2 loss: 0.026220,lr:0.010000 2018-08-19 11:53:57.168789 : Step: 20, accuracy: 0.984848, cls loss: 0.157212, bbox...
I have download WIDER_train, and do the first step:run gen_12net_data.py. But when I run gen_landmark_aug_12.py, a mistake happened: $ python gen_landmark_aug_12.py Traceback (most recent call last): File "gen_landmark_aug_12.py", line 189,...
Hi there, Thanks for sharing the code. I'm trying to train MTCNN with a fixed size input, say 1000x1000. Could you please suggest where should I modify to achieve that?...
想问一下运行代码时出现如下错误是怎么回事 WARNING:tensorflow:From D:\github\MTCNN-Tensorflow-master\train_models\mtcnn_model.py:239: get_regularization_losses (from tensorflow.contrib.losses.python.losses.loss_ops) is deprecated and will be removed after 2016-12-30. Instructions for updating: Use tf.losses.get_regularization_losses instead. 2019-03-20 16:21:42.482675: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this...