Deep-Learning-21-Examples

Deep-Learning-21-Examples copied to clipboard

YuhaoYeSteve

YuhaoYeSteve

书和代码里(eval_image_classifier)给出的是计算accuracy和recall_5，不过这个recall_5好像并不是真正的recall，我理解其实是top5的accuracy. 所以如果我要算recall该怎么算

YuhaoYeSteve

输入28*28 图片通过两层卷积层处理后怎么得到一个7*7的 图片 ？

1

能布恩那个给我教下详细的计算方法？？？？？？？？

uyplayer

chapter3 convert.py 问题求助

1

InvalidArgumentError (see above for traceback): Expected image (JPEG, PNG, or GIF), got unknown format starting with '\303\277\303\230\303\277\303\240\000\020JFIF\000\001' 之前是编码问题，换成 with codecs.open(filename,'r',encoding='iso-8859-15') as f: 之后是上面的问题。。求助！！！

Fandeqing

lychees

`def render_naive(t_obj, img0, iter_n=20, step=50.0): # t_score是优化目标。它是t_obj的平均值 # 结合调用处看，实际上就是layer_output[:, :, :, channel]的平均值 t_score = tf.reduce_mean(t_obj) # 计算t_score对t_input的梯度 t_grad = tf.gradients(t_score, t_input)[0] # 创建新图 img = img0.copy() for i in range(iter_n):...

zcc720

orchardlucky

ValueError: Attempted to map inputs that were not found in graph_def: [input:0] 作为一个自学机器学习,tf的同学，真的很绝望，刚开始看到何之源的书，非常激动，一章一章往下打怪，可是从第2章开始，发现每一章代码基本都跑不起来，真心绝望，到底是怎么了？为什么何大佬写的书配套代码都这样，代码没跑过的吗？还是机器学习学术都是这种华而不实？

0xwang

```python python main.py --network_header_type=nips --env_name=Breakout-v0 --use_gpu=False /anaconda3/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 ==...

eric-h