falling leaves are beautiful
YOLOv4
YOLOv4 - note arxiv.org/abs/2004.10934 -> translation: https://tongtianta.…
Read more ⟶tf2.0
练习代码 pex 基于tensorflow2.0
tensorflow_vs_pytorch
tf1.* 静态图
import tensorflow as tf
print(tf.__version__) # 1.9.0
x = tf.Variable(0.)
y = tf.Variable(1.)
print(x)
print(y)
# 构建计算图
# x = x + y
add_op = x.assign(x +y)
# y = y / 2
div_op = y.assign(y / 2)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(50):
sess.run(add_op)
sess.run(div_op)
print(x.eval())
tf2.* 动态图 -> tf1.x中调用tf.enable_eager_execution()方法打开eager mode
import tensorflow as tf
print(tf.__version__) # 2.0.0
x = tf.constant(0.)
y = tf.constant(1.)
for i in range(50):
x = x + y
y = y / 2
print(x.numpy())
PyTorch 动态图
import torch
print(torch.__version__) # 1.4.0
x = torch.Tensor([0.])
y = torch.Tensor([1.])
for i in range(50):
x = x + y
y = y / 2
print(x)
YOLOv3
论文地址
YOLOv3结构图 DBL:卷积 + BN(Batch Normalization) + Leaky relu resn:n表示包含的res_unit个数 concat:张量拼接,拼接会扩充张量的维度 backbone Darknet-53没有设置池化层和全连接层,而通过改变卷积核的步长进行张量的尺寸变换,在yolov3中没有最后的全局平均池化层,所以张量变化只考虑5层。…
Read more ⟶ResNet
残差网路
这是一个两层神经网络。
计算过程从a[l]开始,先进行线性运算。 $$ z^{[l+1] }= W^{[l+1]}a^{[l]} + b^{[l+1]} $$ 在由激活函数g得到a[l+1],这里g是线性整流函数relu $$ a^{[l+1]} = g(z^{[l+1]}) $$ 随后进行第二层线性运算 $$ z^{[l+2]} = W^{[l+2]}a^{[l+1]} + b^{[l+2]} $$ 再经过Relu $$ a^{[l+2]} = g(z^{[l+2]}) $$ 在残差网络中加入一点变化…
Read more ⟶