`tf.keras.application.Mobilenet`がダウンロードできない

何が起こったか

機械学習プログラムを書こうと思い、試しに以下のコードを書きました。

python
1from tensorflow import keras
2
3if __name__ == "__main__":
4    inputs = keras.layers.Input(shape=(128, 128, 1))
5    x = keras.layers.Conv2D(filters=3, kernel_size=3, padding="same",
6                            activation="relu")(inputs)
7    x = keras.applications.MobileNet(include_top=False,
8                                     input_shape=(128, 128, 3),
9                                     weights="imagenet",
10                                     pooling="max")(x)
11    x = keras.layers.Dense(128, activation="relu")(x)
12    x = keras.layers.Dropout(0.3)(x)
13    pred = keras.layers.Dense(100, activation="softmax")(x)
14    model = keras.Model(inputs=inputs, outputs=pred)
15    model.summary()

mobilenetを持ってきて転移学習をしようと思ったのですがこのコードの時点で以下のエラーが発生しました。

console
12020-11-09 18:21:44.333555: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: c
2annot open shared object file: No such file or directory
32020-11-09 18:21:44.333600: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
42020-11-09 18:21:45.650596: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open
5 shared object file: No such file or directory
62020-11-09 18:21:45.650656: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
72020-11-09 18:21:45.650686: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (mochi-MizLab): /proc/driver/
8nvidia/version does not exist              
92020-11-09 18:21:45.650988: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use t
10he following CPU instructions in performance-critical operations:  AVX2 FMA
11To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
122020-11-09 18:21:45.677190: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2400500000 Hz
132020-11-09 18:21:45.680459: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x563fb5dd3270 initialized for platform Host (this does not guarantee that XLA will
14 be used). Devices:                        
152020-11-09 18:21:45.680515: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
16Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_128_tf_no_top.h5
17Traceback (most recent call last):         
18  File "/usr/lib/python3.8/urllib/request.py", line 1350, in do_open                  
19    h.request(req.get_method(), req.selector, req.data, headers,                      
20  File "/usr/lib/python3.8/http/client.py", line 1255, in request                     
21    self._send_request(method, url, body, headers, encode_chunked)                    
22  File "/usr/lib/python3.8/http/client.py", line 1301, in _send_request               
23    self.endheaders(body, encode_chunked=encode_chunked)                              
24  File "/usr/lib/python3.8/http/client.py", line 1250, in endheaders                  
25    self._send_output(message_body, encode_chunked=encode_chunked)                    
26  File "/usr/lib/python3.8/http/client.py", line 1010, in _send_output                
27    self.send(msg)                         
28  File "/usr/lib/python3.8/http/client.py", line 950, in send                         
29    self.connect()                         
30  File "/usr/lib/python3.8/http/client.py", line 1417, in connect                     
31    super().connect()                                         
32  File "/usr/lib/python3.8/http/client.py", line 921, in connect                                                                                                      [5/129]
33    self.sock = self._create_connection(                                                                                                                                     
34  File "/usr/lib/python3.8/socket.py", line 787, in create_connection                                                                                                        
35    for res in getaddrinfo(host, port, 0, SOCK_STREAM):                                                                                                                      
36  File "/usr/lib/python3.8/socket.py", line 918, in getaddrinfo                                                                                                              
37    for res in _socket.getaddrinfo(host, port, family, type, proto, flags):                                                                                                  
38socket.gaierror: [Errno -2] Name or service not known                                 
39
40During handling of the above exception, another exception occurred:                   
41
42Traceback (most recent call last):         
43  File "/home/mochi/.local/share/virtualenvs/machine-genome-classification-lm-emihK/lib/python3.8/site-packages/tensorflow/python/keras/utils/data_utils.py", line 278, in ge
44t_file                                     
45    urlretrieve(origin, fpath, dl_progress)                                           
46  File "/usr/lib/python3.8/urllib/request.py", line 247, in urlretrieve               
47    with contextlib.closing(urlopen(url, data)) as fp:                                
48  File "/usr/lib/python3.8/urllib/request.py", line 222, in urlopen                   
49    return opener.open(url, data, timeout)                                            
50  File "/usr/lib/python3.8/urllib/request.py", line 525, in open                      
51    response = self._open(req, data)                                                  
52  File "/usr/lib/python3.8/urllib/request.py", line 542, in _open                     
53    result = self._call_chain(self.handle_open, protocol, protocol +                  
54  File "/usr/lib/python3.8/urllib/request.py", line 502, in _call_chain               
55    result = func(*args)                   
56  File "/usr/lib/python3.8/urllib/request.py", line 1393, in https_open               
57    return self.do_open(http.client.HTTPSConnection, req,                             
58  File "/usr/lib/python3.8/urllib/request.py", line 1353, in do_open                  
59    raise URLError(err)                    
60urllib.error.URLError: <urlopen error [Errno -2] Name or service not known>
61
62During handling of the above exception, another exception occurred:                   
63
64Traceback (most recent call last):         
65  File "src/machine_learning/tensorflow/foo.py", line 7, in <module>                  
66    x = keras.applications.MobileNet(include_top=False,                               
67  File "/home/mochi/.local/share/virtualenvs/machine-genome-classification-lm-emihK/lib/python3.8/site-packages/tensorflow/python/keras/applications/mobilenet.py", line 304,
68 in MobileNet                              
69    weights_path = data_utils.get_file(                                               
70  File "/home/mochi/.local/share/virtualenvs/machine-genome-classification-lm-emihK/lib/python3.8/site-packages/tensorflow/python/keras/utils/data_utils.py", line 282, in ge
71t_file                                     
72    raise Exception(error_msg.format(origin, e.errno, e.reason))                      
73Exception: URL fetch failure on https://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_128_tf_no_top.h5: None -- [Errno -2] Name or service not
74known

試してみたこと

どうやらhttps://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_128_tf_no_top.h5がURLとして正しくないようなのですが、手動でこのURLにアクセスすると以下のXMLレスポンスが得られました。

xml
1
2<?xml version='1.0' encoding='UTF-8'?><Error><Code>NoSuchKey</Code><Message>The specified key does not exist.</Message><Details>No such object: tensorflow/keras-applications/mobilenet/mobilenet_1_0_128_tf_no_top.h5:</Details></Error>