我尝试过运行VGG16 keras脚本。 我收到这个错误：
Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5
Traceback (most recent call last):
File "test_imagenet.py", line 40, in
model = VGG16(weights="imagenet")
File "/home/nvidia/deep-learning-models/imagenet-example/vgg16.py", line 143, in VGG16
cache_subdir='models')
File "build/bdist.linux-aarch64/egg/keras/utils/data_utils.py", line 222, in get_file
Exception: URL fetch failure on https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5:
我尝试从here手动下载并将其粘贴到~/.keras/models。
但是，我仍然遇到同样的错误。为什么？我不理解错误，因为正确的模型已经在.keras/models。
答案 0 :(得分：2)
<body>
<div class="container">
<div class="body">
<div class="content">
<div class="ribbon">STUFF<br>BLAH</div>
<!-- there is actually a bunch of other stuff in between "content" and "inner"-->
<div class="inner">
content<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br> content
<br>content<br>content<br>content<br>content<br>content<br>content<br>content<br>
</div>
</div>
</div>
<div class="footer">footer</div>
</div>
</body>函数中include_top参数的默认值为VGG16。这意味着如果您想使用全层预训练的VGG网络（具有完全连接的部分），您需要下载True文件，而不是vgg16_weights_tf_dim_ordering_tf_kernels.h5。