yangqian-qian

data_dict['X2'] = np.concatenate((data_dict['X2'], np.load(DATASET.train_folder + '/hog_features.npy')), axis=1)

15

when i did 'python train.py --train=yes', code 'data_dict['X2'] = np.concatenate((data_dict['X2'], np.load(DATASET.train_folder + '/hog_features.npy')), axis=1)' from data_loader.py reprted a error, which is 'numpy.AxisError: axis 1 is out of bounds for array...

why do you train on 5 expressions instead of 7 expressions?

hi, dear Pedro Diamel Marrero Fernández, Recently, I am reading the paper "ferratt: facial expression recognition with attentionnet". Then I have a question about the loss function. I don't understand...

有关loss函数以及预训练模型的问题

2

作者您好，我有个问题想问下，我看论文里面两个损失函数是各自乘以0.5然后相加的，为什么这里的代码是直接相加呢，是不是说因为是同样重要，所以乘不乘0.5是一样的效果啊？然后那个预训练模型我下载不了，可不可以发我邮箱啊？非常希望您能帮我解惑。