Anacondaを使用してMacでDeepLabの動作確認

2019年2月7日 17:35

日本語情報が少ないのであれこれググりながら実行した結果まとめ。
TensorFlowはpip installした方がよさげかもしれないが、とりあえずcondaで統一して下記インストレーションを最後まで通してみた。

Anacondaのインストール

下記サイトから3.7をダウンロード。

インストーラを実行。
Microsoft Visual Studio Codeは不要。

Tensorflowのインストール

Anaconda Navigatorを起動。
Environmentsで新規環境をCreate。（Python3.6を選択）
Environmentsでtensowflowのパッケージをインストール。
（インストールが凍ってApplyできない場合、Navigatorを再起動）
HomeでJupyter Notebookをインストール。

DeepLabのインストール

EnvironmentsでPillowのパッケージをインストール。
EnvironmentsでNumpyのパッケージをインストール。（tensowflowと同時にインストール済のはず）
EnvironmentsでJupyterのパッケージをインストール。
EnvironmentsでMatplotlibのパッケージをインストール。
環境の▶︎をクリックしてターミナルを起動して、以下を実行。

$ cd
$ mkdir tensorflow
$ cd tensorflow
$ git clone https://github.com/tensorflow/models.git

以下を実行。

$ cd tensorflow/models/research/
$ export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim
$ python deeplab/model_test.py

自分の環境では以下のエラーが発生。

2019-02-06 16:24:20.133489: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 16:24:20.134495: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
F....
======================================================================
FAIL: testBuildDeepLabWithDensePredictionCell (__main__.DeeplabModelTest)
----------------------------------------------------------------------
Traceback (most recent call last):
 File "deeplab/model_test.py", line 141, in testBuildDeepLabWithDensePredictionCell
   expected_endpoints)
AssertionError: First sequence is not a list: dict_keys(['merged_logits'])
----------------------------------------------------------------------
Ran 5 tests in 26.326s
FAILED (failures=1)

上記のようなエラーが出たら、model_test.pyの140行目を

self.assertListEqual(scales_to_model_results.keys(),

から

self.assertListEqual(list(scales_to_model_results.keys()),

に修正。
再実行。

$ python deeplab/model_test.py

OKが表示される。

2019-02-06 16:37:42.922340: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 16:37:42.922908: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
.....
----------------------------------------------------------------------
Ran 5 tests in 27.716s
OK

以下を実行。

$ cd deeplab
$ sh local_test.sh

OKは表示されたがwgetがないらしい。

testBuildDeepLabWithDensePredictionCell (__main__.DeeplabModelTest) ... 2019-02-06 16:46:00.970801: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 16:46:00.971175: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
ok
testBuildDeepLabv2 (__main__.DeeplabModelTest) ... ok
testForwardpassDeepLabv3plus (__main__.DeeplabModelTest) ... ok
testWrongDeepLabVariant (__main__.DeeplabModelTest) ... ok
test_session (__main__.DeeplabModelTest)
Use cached_session instead. ... ok
----------------------------------------------------------------------
Ran 5 tests in 26.655s
OK
Downloading VOCtrainval_11-May-2012.tar to ./pascal_voc_seg
download_and_convert_voc2012.sh: line 50: wget: command not found

Environmentsでwgetのパッケージをインストール。
再実行（環境によるが時間がかかるので余裕のある時に実行推奨）。

＄ sh local_test.sh

ダウンロードからEvalutaion、Visualizingまで成功したっぽい。
（長いので"INFO:tensorflow:Visualizing batch xxx / 1449"は中略）

testBuildDeepLabWithDensePredictionCell (__main__.DeeplabModelTest) ... 2019-02-06 16:57:25.872729: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 16:57:25.874423: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
ok
testBuildDeepLabv2 (__main__.DeeplabModelTest) ... ok
testForwardpassDeepLabv3plus (__main__.DeeplabModelTest) ... ok
testWrongDeepLabVariant (__main__.DeeplabModelTest) ... ok
test_session (__main__.DeeplabModelTest)
Use cached_session instead. ... ok

----------------------------------------------------------------------
Ran 5 tests in 31.875s

OK
Downloading VOCtrainval_11-May-2012.tar to ./pascal_voc_seg
--2019-02-06 16:57:58--  http://host.robots.ox.ac.uk/pascal/VOC/voc2012//VOCtrainval_11-May-2012.tar
Resolving host.robots.ox.ac.uk... 129.67.94.152
Connecting to host.robots.ox.ac.uk|129.67.94.152|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1999639040 (1.9G) [application/x-tar]
Saving to: 'VOCtrainval_11-May-2012.tar'

VOCtrainval_11-May- 100%[===================>]   1.86G  54.9KB/s    in 2h 42m  

2019-02-06 19:40:03 (201 KB/s) - 'VOCtrainval_11-May-2012.tar' saved [1999639040/1999639040]

Uncompressing VOCtrainval_11-May-2012.tar
Removing the color map in ground truth annotations...
Converting PASCAL VOC 2012 dataset...
2019-02-06 19:40:50.485184: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 19:40:50.486977: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
>> Converting image 1/1464 shard 0WARNING:tensorflow:From ./build_voc2012_data.py:116: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.gfile.GFile.
>> Converting image 366/1464 shard 0
>> Converting image 732/1464 shard 1
>> Converting image 1098/1464 shard 2
>> Converting image 1464/1464 shard 3
>> Converting image 729/2913 shard 0
>> Converting image 1458/2913 shard 1
>> Converting image 2187/2913 shard 2
>> Converting image 2913/2913 shard 3
>> Converting image 363/1449 shard 0
>> Converting image 726/1449 shard 1
>> Converting image 1089/1449 shard 2
>> Converting image 1449/1449 shard 3
--2019-02-06 19:41:44--  http://download.tensorflow.org/models/deeplabv3_pascal_train_aug_2018_01_04.tar.gz
Resolving download.tensorflow.org... 172.217.161.208
Connecting to download.tensorflow.org|172.217.161.208|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 460058541 (439M) [application/x-tar]
Saving to: 'deeplabv3_pascal_train_aug_2018_01_04.tar.gz'

deeplabv3_pascal_tr 100%[===================>] 438.75M  8.47MB/s    in 72s     

2019-02-06 19:42:57 (6.09 MB/s) - 'deeplabv3_pascal_train_aug_2018_01_04.tar.gz' saved [460058541/460058541]

INFO:tensorflow:Training on trainval set
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:242: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:276: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:94: TFRecordReader.__init__ (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.TFRecordDataset`.
WARNING:tensorflow:From /Users/yogo/tensorflow/models/research/deeplab/utils/input_generator.py:168: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
INFO:tensorflow:Initializing model from path: /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/init_models/deeplabv3_pascal_train_aug/model.ckpt
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/learning.py:737: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2019-02-06 19:43:44.560821: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 19:43:44.561108: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
INFO:tensorflow:Restoring parameters from /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/init_models/deeplabv3_pascal_train_aug/model.ckpt
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Starting Session.
INFO:tensorflow:Saving checkpoint to path /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt
INFO:tensorflow:Starting Queues.
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:Recording summary at step 0.
INFO:tensorflow:global_step/sec: 0.00502611
INFO:tensorflow:Recording summary at step 3.
INFO:tensorflow:Saving checkpoint to path /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt
INFO:tensorflow:global_step/sec: 0.00658143
INFO:tensorflow:Recording summary at step 7.
INFO:tensorflow:global step 10: loss = 0.1952 (150.083 sec/step)
INFO:tensorflow:Stopping Training.
INFO:tensorflow:Finished training! Saving model to disk.
INFO:tensorflow:Evaluating on val set
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:242: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:276: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:94: TFRecordReader.__init__ (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.TFRecordDataset`.
WARNING:tensorflow:From /Users/yogo/tensorflow/models/research/deeplab/utils/input_generator.py:168: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
INFO:tensorflow:Performing single-scale test.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/summaries.py:127: Print (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2018-08-20.
Instructions for updating:
Use tf.print instead of tf.Print. Note that tf.print returns a no-output operator that directly prints the output. Outside of defuns or eager mode, this operator will not be executed unless it is directly specified in session.run or used as a control dependency for other operators. This is only a concern in graph mode. Below is an example of how to ensure tf.print executes in graph mode:
```python
    sess = tf.Session()
    with sess.as_default():
        tensor = tf.range(10)
        print_op = tf.print(tensor)
        with tf.control_dependencies([print_op]):
          out = tf.add(tensor, tensor)
        sess.run(out)
    ```
Additionally, to use tf.print in python 2.7, users must make sure to import
the following:

  `from __future__ import print_function`

INFO:tensorflow:Eval num images 1449
INFO:tensorflow:Eval batch size 1 and num batch 1449
INFO:tensorflow:Waiting for new checkpoint at /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train
INFO:tensorflow:Found new checkpoint at /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
INFO:tensorflow:Graph was finalized.
2019-02-06 20:13:13.623543: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 20:13:13.623839: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
INFO:tensorflow:Restoring parameters from /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py:804: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
INFO:tensorflow:Starting evaluation at 2019-02-06-11:13:22
INFO:tensorflow:Evaluation [144/1449]
INFO:tensorflow:Evaluation [288/1449]
INFO:tensorflow:Evaluation [432/1449]
INFO:tensorflow:Evaluation [576/1449]
INFO:tensorflow:Evaluation [720/1449]
INFO:tensorflow:Evaluation [864/1449]
INFO:tensorflow:Evaluation [1008/1449]
INFO:tensorflow:Evaluation [1152/1449]
INFO:tensorflow:Evaluation [1296/1449]
INFO:tensorflow:Evaluation [1440/1449]
INFO:tensorflow:Evaluation [1449/1449]
INFO:tensorflow:Finished evaluation at 2019-02-06-14:45:44
miou_1.0[0.822012126]
INFO:tensorflow:Visualizing on val set
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:242: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:276: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /anaconda3/envs/deeplab/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py:94: TFRecordReader.__init__ (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.TFRecordDataset`.
WARNING:tensorflow:From /Users/yogo/tensorflow/models/research/deeplab/utils/input_generator.py:168: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
INFO:tensorflow:Performing single-scale test.
WARNING:tensorflow:From /Users/yogo/tensorflow/models/research/deeplab/vis.py:270: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
INFO:tensorflow:Waiting for new checkpoint at /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train
INFO:tensorflow:Found new checkpoint at /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
INFO:tensorflow:Starting visualization at 2019-02-06-14:46:03
INFO:tensorflow:Visualizing with model /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
2019-02-06 23:46:03.104288: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-06 23:46:03.104504: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Restoring parameters from /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
INFO:tensorflow:Visualizing batch 1 / 1449
INFO:tensorflow:Visualizing batch 2 / 1449
INFO:tensorflow:Visualizing batch 3 / 1449
INFO:tensorflow:Visualizing batch 4 / 1449
INFO:tensorflow:Visualizing batch 5 / 1449
INFO:tensorflow:Visualizing batch 6 / 1449
INFO:tensorflow:Visualizing batch 7 / 1449
INFO:tensorflow:Visualizing batch 8 / 1449
INFO:tensorflow:Visualizing batch 9 / 1449
INFO:tensorflow:Visualizing batch 10 / 1449

...

INFO:tensorflow:Visualizing batch 1447 / 1449
INFO:tensorflow:Visualizing batch 1448 / 1449
INFO:tensorflow:Visualizing batch 1449 / 1449
INFO:tensorflow:Finished visualization at 2019-02-06-20:27:44
INFO:tensorflow:Prepare to export model to: /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/export/frozen_inference_graph.pb
INFO:tensorflow:Exported model performs single-scale inference.
2019-02-07 05:28:02.344834: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-07 05:28:02.345091: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
INFO:tensorflow:Restoring parameters from /Users/yogo/tensorflow/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_trainval_set/train/model.ckpt-10
INFO:tensorflow:Froze 732 variables.
INFO:tensorflow:Converted 732 variables to const ops.

使用環境

機種：MacBook AIr (13-inch, 2017)
OS：Mojave 10.14.2

この記事が気に入ったらサポートをしてみませんか？