wangce888

Results 16 issues of wangce888

tensorflowTUT/tf23_BN/的代码里好像没用到滑动平均,没有ema.average(fc_mean)函数

Which of the IMDB-wiki and UTKface performs better? I find that some labels were wrong on IMDB-wiki, so I used UTKface

SegDesc = (PSEGMENT_DESCRIPTOR)((PUCHAR)GdtBase + (Selector & ~0x7)); Hi, I didn't understand this line. Should (Selector & ~0x7) be multiplied by 8? because GdtBase is unsigned char*,it's 8 bits,Adding 1 means...

At the beginning, the loss is about 9.x, After training 28,000 times, how much is the loss value. My loss value is approximately 4.x, the accuracy is 91%, and I...

我重新训练了一下,用的UTKface数据集,只有1万多张图片,loss也是一直下降的。但是测试时发现,无论输入什么脸,结果都是男,16岁,这是怎么回事

年龄值和对应的概率值相乘再求和是什么意思 age_ = tf.cast(tf.constant([i for i in range(0, 101)]), tf.float32) age = tf.reduce_sum(tf.multiply(tf.nn.softmax(age_logits), age_), axis=1) 为什么不能用argmax求最大可能性的年龄

My input image is [batch, 3, None, None], how to represent any size in the signature.json file. I think a solution is to remove image.resize(img_arr, w, h) in mxnet_vision_servion_service.py. But...

question

new_high = new_high * tf.minimum(input_width / new_width, input_high / new_high) new_width = new_high * tf.minimum(input_width / new_width, input_high / new_high) line2:I think it is new_width*tf.minimum()