Dive-into-DL-TensorFlow2.0

Dive-into-DL-TensorFlow2.0 copied to clipboard

at file 9.1_image-augmentation.ipynb show_images(x[0:32][0], 4, 8, scale=0.8); should be changed: show_images(x[0:32], 4, 8, scale=0.8);

thuongle2210

无法访问4.3 模型参数的延后初始化

1

https://trickygo.github.io/Dive-into-DL-TensorFlow2.0/#/chapter04_DL-computation/4.3_deferred-init 2021年2月16日 11点，提示404 - Not found

itsgoodtobebad

hablee

ch6.8代码不符,lstm中最后一个简单版本实现的最后一个函数train_and_predict_rnn_keras并没有device的参数

2

去掉device后报错： 

sxzhou1937

 上面是GoogLeNet的源码运行结果

NiceRingNode

itsgoodtobebad

缺失章节“机器翻译”

hurun

The funtion of colormap2label may not be effective , the converted label does not correspond.

4

[test-rgb2label.pdf](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/files/5728510/test-rgb2label.pdf) The result for [0,0,128] should be labeled as 4, but got the 0. Hope to get your reply, thank you! The input image from VOC2012\SegmentationClass\2007_000061.png 

lihua7351

```python with tf.GradientTape(persistent=True) as g: g.watch(x) y = x * x z = y * y dz_dx = g.gradient(z, x) # 108.0 (4*x^3 at x = 3) dy_dx = g.gradient(y,...

xinetzone


leeyy2020