Initialize a tensorflow model in main(), pass it to __init__ and execute inside another method











up vote
0
down vote

favorite












I want to build a web service with flask where multiple deep learning models will be applied to certain types of data to give back a result. Currently, I want to load them locally on main() once at start, pass them to init to just initialize them once when the execution of the script starts and then call it every time it is needed to perform a forward pass to return something. So far that's what I ve done with the rest but I don't know how to handle a pure tensorflow model initialization. The below code works fine. Any Suggestions, alterations are appreciated:



def evaluate_sample(numpy_array, no_of_frames):
_IMAGE_SIZE = 224
_SAMPLE_VIDEO_FRAMES = no_of_frames
_CHECKPOINT_PATHS = {'flow': 'data/checkpoints/flow_scratch/model.ckpt'}
NUM_CLASSES = 400

flow_input = tf.placeholder(
tf.float32,
shape=(1, _SAMPLE_VIDEO_FRAMES, _IMAGE_SIZE, _IMAGE_SIZE, 2))
with tf.variable_scope('Flow', reuse=tf.AUTO_REUSE):
flow_model = i3d.InceptionI3d(NUM_CLASSES, spatial_squeeze=True, final_endpoint='Logits')
flow_logits, _ = flow_model(flow_input, is_training=False, dropout_keep_prob=1.0)
flow_variable_map = {}
for variable in tf.global_variables():
if variable.name.split('/')[0] == 'Flow':
flow_variable_map[variable.name.replace(':0', '')] = variable
flow_saver = tf.train.Saver(var_list=flow_variable_map, reshape=True)
model_logits = flow_logits
model_predictions = tf.nn.softmax(model_logits)

with tf.Session() as sess:
feed_dict = {}
flow_saver.restore(sess, _CHECKPOINT_PATHS['flow'])
flow_sample = numpy_array
feed_dict[flow_input] = flow_sample
out_logits, out_predictions = sess.run(
[model_logits, model_predictions],
feed_dict=feed_dict)
logits2=np.asarray(out_logits)

return logits2




def get_flow_features(video_path):
.....
aggregated_flow_vector = evaluate_sample(final_np_cropped_flow, len(all_frames_flow))
.....


class GetOutOfContext:
def __init__(self, keras_model, pytorch_model, word2vec_model, max_pooling):
self.keras_model = keras_model
self.pytorch_model = pytorch_model
self.word2vec_model = word2vec_model
self.max_pooling = max_pooling
#self.kineticsi3d = kineticsi3d
print("Similarity Between Video and Text Service Initialized...")

def get(self):
dirpath = tempfile.mkdtemp()+"/"
video_path = download_video(url,dirpath)
aggregated_audio = get_audio_features(video_path)
aggregated_flow = get_flow_features(video_path)
aggregated_video = get_visual_features(video_path, dirpath)
aggregated_text = get_word_features(text)
.......

if __name__ == "__main__":
"""Loading Prediction Model"""
video_modality_dim = {'face': (128,128), 'audio': (128*16,128),'visual': (2048,2048), 'motion': (1024,1024)}
the_model = Net(video_modality_dim, 300, audio_cluster=16)
the_model.load_state_dict(torch.load('/home/estathop/Desktop/journalmodel/msrvttjournal.pt', map_location=lambda storage, loc: storage))
the_model.eval()
"""Loading Image Feature Extraction Model"""
model = ResNet152(include_top=False, weights='imagenet', pooling = 'avg') #cons
"""Loading Word2Vec Model"""
model2 = api.load("word2vec-google-news-300")
maxpoolingmodel = keras.layers.pooling.GlobalMaxPooling1D()
word_vectors = model2.wv
nltk.download('stopwords')

x = GetOutOfContext(model,the_model,model2, maxpoolingmodel)
y = x.get()









share|improve this question


























    up vote
    0
    down vote

    favorite












    I want to build a web service with flask where multiple deep learning models will be applied to certain types of data to give back a result. Currently, I want to load them locally on main() once at start, pass them to init to just initialize them once when the execution of the script starts and then call it every time it is needed to perform a forward pass to return something. So far that's what I ve done with the rest but I don't know how to handle a pure tensorflow model initialization. The below code works fine. Any Suggestions, alterations are appreciated:



    def evaluate_sample(numpy_array, no_of_frames):
    _IMAGE_SIZE = 224
    _SAMPLE_VIDEO_FRAMES = no_of_frames
    _CHECKPOINT_PATHS = {'flow': 'data/checkpoints/flow_scratch/model.ckpt'}
    NUM_CLASSES = 400

    flow_input = tf.placeholder(
    tf.float32,
    shape=(1, _SAMPLE_VIDEO_FRAMES, _IMAGE_SIZE, _IMAGE_SIZE, 2))
    with tf.variable_scope('Flow', reuse=tf.AUTO_REUSE):
    flow_model = i3d.InceptionI3d(NUM_CLASSES, spatial_squeeze=True, final_endpoint='Logits')
    flow_logits, _ = flow_model(flow_input, is_training=False, dropout_keep_prob=1.0)
    flow_variable_map = {}
    for variable in tf.global_variables():
    if variable.name.split('/')[0] == 'Flow':
    flow_variable_map[variable.name.replace(':0', '')] = variable
    flow_saver = tf.train.Saver(var_list=flow_variable_map, reshape=True)
    model_logits = flow_logits
    model_predictions = tf.nn.softmax(model_logits)

    with tf.Session() as sess:
    feed_dict = {}
    flow_saver.restore(sess, _CHECKPOINT_PATHS['flow'])
    flow_sample = numpy_array
    feed_dict[flow_input] = flow_sample
    out_logits, out_predictions = sess.run(
    [model_logits, model_predictions],
    feed_dict=feed_dict)
    logits2=np.asarray(out_logits)

    return logits2




    def get_flow_features(video_path):
    .....
    aggregated_flow_vector = evaluate_sample(final_np_cropped_flow, len(all_frames_flow))
    .....


    class GetOutOfContext:
    def __init__(self, keras_model, pytorch_model, word2vec_model, max_pooling):
    self.keras_model = keras_model
    self.pytorch_model = pytorch_model
    self.word2vec_model = word2vec_model
    self.max_pooling = max_pooling
    #self.kineticsi3d = kineticsi3d
    print("Similarity Between Video and Text Service Initialized...")

    def get(self):
    dirpath = tempfile.mkdtemp()+"/"
    video_path = download_video(url,dirpath)
    aggregated_audio = get_audio_features(video_path)
    aggregated_flow = get_flow_features(video_path)
    aggregated_video = get_visual_features(video_path, dirpath)
    aggregated_text = get_word_features(text)
    .......

    if __name__ == "__main__":
    """Loading Prediction Model"""
    video_modality_dim = {'face': (128,128), 'audio': (128*16,128),'visual': (2048,2048), 'motion': (1024,1024)}
    the_model = Net(video_modality_dim, 300, audio_cluster=16)
    the_model.load_state_dict(torch.load('/home/estathop/Desktop/journalmodel/msrvttjournal.pt', map_location=lambda storage, loc: storage))
    the_model.eval()
    """Loading Image Feature Extraction Model"""
    model = ResNet152(include_top=False, weights='imagenet', pooling = 'avg') #cons
    """Loading Word2Vec Model"""
    model2 = api.load("word2vec-google-news-300")
    maxpoolingmodel = keras.layers.pooling.GlobalMaxPooling1D()
    word_vectors = model2.wv
    nltk.download('stopwords')

    x = GetOutOfContext(model,the_model,model2, maxpoolingmodel)
    y = x.get()









    share|improve this question
























      up vote
      0
      down vote

      favorite









      up vote
      0
      down vote

      favorite











      I want to build a web service with flask where multiple deep learning models will be applied to certain types of data to give back a result. Currently, I want to load them locally on main() once at start, pass them to init to just initialize them once when the execution of the script starts and then call it every time it is needed to perform a forward pass to return something. So far that's what I ve done with the rest but I don't know how to handle a pure tensorflow model initialization. The below code works fine. Any Suggestions, alterations are appreciated:



      def evaluate_sample(numpy_array, no_of_frames):
      _IMAGE_SIZE = 224
      _SAMPLE_VIDEO_FRAMES = no_of_frames
      _CHECKPOINT_PATHS = {'flow': 'data/checkpoints/flow_scratch/model.ckpt'}
      NUM_CLASSES = 400

      flow_input = tf.placeholder(
      tf.float32,
      shape=(1, _SAMPLE_VIDEO_FRAMES, _IMAGE_SIZE, _IMAGE_SIZE, 2))
      with tf.variable_scope('Flow', reuse=tf.AUTO_REUSE):
      flow_model = i3d.InceptionI3d(NUM_CLASSES, spatial_squeeze=True, final_endpoint='Logits')
      flow_logits, _ = flow_model(flow_input, is_training=False, dropout_keep_prob=1.0)
      flow_variable_map = {}
      for variable in tf.global_variables():
      if variable.name.split('/')[0] == 'Flow':
      flow_variable_map[variable.name.replace(':0', '')] = variable
      flow_saver = tf.train.Saver(var_list=flow_variable_map, reshape=True)
      model_logits = flow_logits
      model_predictions = tf.nn.softmax(model_logits)

      with tf.Session() as sess:
      feed_dict = {}
      flow_saver.restore(sess, _CHECKPOINT_PATHS['flow'])
      flow_sample = numpy_array
      feed_dict[flow_input] = flow_sample
      out_logits, out_predictions = sess.run(
      [model_logits, model_predictions],
      feed_dict=feed_dict)
      logits2=np.asarray(out_logits)

      return logits2




      def get_flow_features(video_path):
      .....
      aggregated_flow_vector = evaluate_sample(final_np_cropped_flow, len(all_frames_flow))
      .....


      class GetOutOfContext:
      def __init__(self, keras_model, pytorch_model, word2vec_model, max_pooling):
      self.keras_model = keras_model
      self.pytorch_model = pytorch_model
      self.word2vec_model = word2vec_model
      self.max_pooling = max_pooling
      #self.kineticsi3d = kineticsi3d
      print("Similarity Between Video and Text Service Initialized...")

      def get(self):
      dirpath = tempfile.mkdtemp()+"/"
      video_path = download_video(url,dirpath)
      aggregated_audio = get_audio_features(video_path)
      aggregated_flow = get_flow_features(video_path)
      aggregated_video = get_visual_features(video_path, dirpath)
      aggregated_text = get_word_features(text)
      .......

      if __name__ == "__main__":
      """Loading Prediction Model"""
      video_modality_dim = {'face': (128,128), 'audio': (128*16,128),'visual': (2048,2048), 'motion': (1024,1024)}
      the_model = Net(video_modality_dim, 300, audio_cluster=16)
      the_model.load_state_dict(torch.load('/home/estathop/Desktop/journalmodel/msrvttjournal.pt', map_location=lambda storage, loc: storage))
      the_model.eval()
      """Loading Image Feature Extraction Model"""
      model = ResNet152(include_top=False, weights='imagenet', pooling = 'avg') #cons
      """Loading Word2Vec Model"""
      model2 = api.load("word2vec-google-news-300")
      maxpoolingmodel = keras.layers.pooling.GlobalMaxPooling1D()
      word_vectors = model2.wv
      nltk.download('stopwords')

      x = GetOutOfContext(model,the_model,model2, maxpoolingmodel)
      y = x.get()









      share|improve this question













      I want to build a web service with flask where multiple deep learning models will be applied to certain types of data to give back a result. Currently, I want to load them locally on main() once at start, pass them to init to just initialize them once when the execution of the script starts and then call it every time it is needed to perform a forward pass to return something. So far that's what I ve done with the rest but I don't know how to handle a pure tensorflow model initialization. The below code works fine. Any Suggestions, alterations are appreciated:



      def evaluate_sample(numpy_array, no_of_frames):
      _IMAGE_SIZE = 224
      _SAMPLE_VIDEO_FRAMES = no_of_frames
      _CHECKPOINT_PATHS = {'flow': 'data/checkpoints/flow_scratch/model.ckpt'}
      NUM_CLASSES = 400

      flow_input = tf.placeholder(
      tf.float32,
      shape=(1, _SAMPLE_VIDEO_FRAMES, _IMAGE_SIZE, _IMAGE_SIZE, 2))
      with tf.variable_scope('Flow', reuse=tf.AUTO_REUSE):
      flow_model = i3d.InceptionI3d(NUM_CLASSES, spatial_squeeze=True, final_endpoint='Logits')
      flow_logits, _ = flow_model(flow_input, is_training=False, dropout_keep_prob=1.0)
      flow_variable_map = {}
      for variable in tf.global_variables():
      if variable.name.split('/')[0] == 'Flow':
      flow_variable_map[variable.name.replace(':0', '')] = variable
      flow_saver = tf.train.Saver(var_list=flow_variable_map, reshape=True)
      model_logits = flow_logits
      model_predictions = tf.nn.softmax(model_logits)

      with tf.Session() as sess:
      feed_dict = {}
      flow_saver.restore(sess, _CHECKPOINT_PATHS['flow'])
      flow_sample = numpy_array
      feed_dict[flow_input] = flow_sample
      out_logits, out_predictions = sess.run(
      [model_logits, model_predictions],
      feed_dict=feed_dict)
      logits2=np.asarray(out_logits)

      return logits2




      def get_flow_features(video_path):
      .....
      aggregated_flow_vector = evaluate_sample(final_np_cropped_flow, len(all_frames_flow))
      .....


      class GetOutOfContext:
      def __init__(self, keras_model, pytorch_model, word2vec_model, max_pooling):
      self.keras_model = keras_model
      self.pytorch_model = pytorch_model
      self.word2vec_model = word2vec_model
      self.max_pooling = max_pooling
      #self.kineticsi3d = kineticsi3d
      print("Similarity Between Video and Text Service Initialized...")

      def get(self):
      dirpath = tempfile.mkdtemp()+"/"
      video_path = download_video(url,dirpath)
      aggregated_audio = get_audio_features(video_path)
      aggregated_flow = get_flow_features(video_path)
      aggregated_video = get_visual_features(video_path, dirpath)
      aggregated_text = get_word_features(text)
      .......

      if __name__ == "__main__":
      """Loading Prediction Model"""
      video_modality_dim = {'face': (128,128), 'audio': (128*16,128),'visual': (2048,2048), 'motion': (1024,1024)}
      the_model = Net(video_modality_dim, 300, audio_cluster=16)
      the_model.load_state_dict(torch.load('/home/estathop/Desktop/journalmodel/msrvttjournal.pt', map_location=lambda storage, loc: storage))
      the_model.eval()
      """Loading Image Feature Extraction Model"""
      model = ResNet152(include_top=False, weights='imagenet', pooling = 'avg') #cons
      """Loading Word2Vec Model"""
      model2 = api.load("word2vec-google-news-300")
      maxpoolingmodel = keras.layers.pooling.GlobalMaxPooling1D()
      word_vectors = model2.wv
      nltk.download('stopwords')

      x = GetOutOfContext(model,the_model,model2, maxpoolingmodel)
      y = x.get()






      python web-services tensorflow initialization multiple-models






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 7 at 15:42









      Evan

      277




      277
























          3 Answers
          3






          active

          oldest

          votes

















          up vote
          1
          down vote



          accepted










          In your current code, the model is defined and loaded in evaluate_sample, you can simply move the majority of the code from evaluate_sample to main or init and pass the tf.Session object and the graph to evaluate_sample.
          Here is a clumsy example:



          import tensorflow as tf

          def main():
          sess=tf.Session()
          a=tf.placeholder(tf.float32)
          b=tf.constant(5.0)
          c=a+b
          evaluate_sample(sess,c,a)

          def evaluate_sample(session,graph,input):
          print(session.run(graph,feed_dict={input:3}))

          if __name__ == "__main__":
          main()





          share|improve this answer




























            up vote
            1
            down vote













            I'd hold on to the Session and just run multiple times. saver.restore should happen just once. For error checking you can tf.get_default_graph().finalize() after you specify the model to make sure the graph isn't changing each request, which would slow things down.






            share|improve this answer




























              up vote
              0
              down vote













              Are you trying to load a pretrained model and run an inference? By initializing are you referring to loading a model or initializing new weights for each instance this is executed?






              share|improve this answer





















              • I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                – Evan
                Nov 8 at 7:53











              Your Answer






              StackExchange.ifUsing("editor", function () {
              StackExchange.using("externalEditor", function () {
              StackExchange.using("snippets", function () {
              StackExchange.snippets.init();
              });
              });
              }, "code-snippets");

              StackExchange.ready(function() {
              var channelOptions = {
              tags: "".split(" "),
              id: "1"
              };
              initTagRenderer("".split(" "), "".split(" "), channelOptions);

              StackExchange.using("externalEditor", function() {
              // Have to fire editor after snippets, if snippets enabled
              if (StackExchange.settings.snippets.snippetsEnabled) {
              StackExchange.using("snippets", function() {
              createEditor();
              });
              }
              else {
              createEditor();
              }
              });

              function createEditor() {
              StackExchange.prepareEditor({
              heartbeatType: 'answer',
              convertImagesToLinks: true,
              noModals: true,
              showLowRepImageUploadWarning: true,
              reputationToPostImages: 10,
              bindNavPrevention: true,
              postfix: "",
              imageUploader: {
              brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
              contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
              allowUrls: true
              },
              onDemand: true,
              discardSelector: ".discard-answer"
              ,immediatelyShowMarkdownHelp:true
              });


              }
              });














               

              draft saved


              draft discarded


















              StackExchange.ready(
              function () {
              StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53192824%2finitialize-a-tensorflow-model-in-main-pass-it-to-init-and-execute-inside%23new-answer', 'question_page');
              }
              );

              Post as a guest















              Required, but never shown

























              3 Answers
              3






              active

              oldest

              votes








              3 Answers
              3






              active

              oldest

              votes









              active

              oldest

              votes






              active

              oldest

              votes








              up vote
              1
              down vote



              accepted










              In your current code, the model is defined and loaded in evaluate_sample, you can simply move the majority of the code from evaluate_sample to main or init and pass the tf.Session object and the graph to evaluate_sample.
              Here is a clumsy example:



              import tensorflow as tf

              def main():
              sess=tf.Session()
              a=tf.placeholder(tf.float32)
              b=tf.constant(5.0)
              c=a+b
              evaluate_sample(sess,c,a)

              def evaluate_sample(session,graph,input):
              print(session.run(graph,feed_dict={input:3}))

              if __name__ == "__main__":
              main()





              share|improve this answer

























                up vote
                1
                down vote



                accepted










                In your current code, the model is defined and loaded in evaluate_sample, you can simply move the majority of the code from evaluate_sample to main or init and pass the tf.Session object and the graph to evaluate_sample.
                Here is a clumsy example:



                import tensorflow as tf

                def main():
                sess=tf.Session()
                a=tf.placeholder(tf.float32)
                b=tf.constant(5.0)
                c=a+b
                evaluate_sample(sess,c,a)

                def evaluate_sample(session,graph,input):
                print(session.run(graph,feed_dict={input:3}))

                if __name__ == "__main__":
                main()





                share|improve this answer























                  up vote
                  1
                  down vote



                  accepted







                  up vote
                  1
                  down vote



                  accepted






                  In your current code, the model is defined and loaded in evaluate_sample, you can simply move the majority of the code from evaluate_sample to main or init and pass the tf.Session object and the graph to evaluate_sample.
                  Here is a clumsy example:



                  import tensorflow as tf

                  def main():
                  sess=tf.Session()
                  a=tf.placeholder(tf.float32)
                  b=tf.constant(5.0)
                  c=a+b
                  evaluate_sample(sess,c,a)

                  def evaluate_sample(session,graph,input):
                  print(session.run(graph,feed_dict={input:3}))

                  if __name__ == "__main__":
                  main()





                  share|improve this answer












                  In your current code, the model is defined and loaded in evaluate_sample, you can simply move the majority of the code from evaluate_sample to main or init and pass the tf.Session object and the graph to evaluate_sample.
                  Here is a clumsy example:



                  import tensorflow as tf

                  def main():
                  sess=tf.Session()
                  a=tf.placeholder(tf.float32)
                  b=tf.constant(5.0)
                  c=a+b
                  evaluate_sample(sess,c,a)

                  def evaluate_sample(session,graph,input):
                  print(session.run(graph,feed_dict={input:3}))

                  if __name__ == "__main__":
                  main()






                  share|improve this answer












                  share|improve this answer



                  share|improve this answer










                  answered Nov 17 at 0:49









                  Qin Heyang

                  963




                  963
























                      up vote
                      1
                      down vote













                      I'd hold on to the Session and just run multiple times. saver.restore should happen just once. For error checking you can tf.get_default_graph().finalize() after you specify the model to make sure the graph isn't changing each request, which would slow things down.






                      share|improve this answer

























                        up vote
                        1
                        down vote













                        I'd hold on to the Session and just run multiple times. saver.restore should happen just once. For error checking you can tf.get_default_graph().finalize() after you specify the model to make sure the graph isn't changing each request, which would slow things down.






                        share|improve this answer























                          up vote
                          1
                          down vote










                          up vote
                          1
                          down vote









                          I'd hold on to the Session and just run multiple times. saver.restore should happen just once. For error checking you can tf.get_default_graph().finalize() after you specify the model to make sure the graph isn't changing each request, which would slow things down.






                          share|improve this answer












                          I'd hold on to the Session and just run multiple times. saver.restore should happen just once. For error checking you can tf.get_default_graph().finalize() after you specify the model to make sure the graph isn't changing each request, which would slow things down.







                          share|improve this answer












                          share|improve this answer



                          share|improve this answer










                          answered Nov 17 at 0:22









                          Allen Lavoie

                          4,3511721




                          4,3511721






















                              up vote
                              0
                              down vote













                              Are you trying to load a pretrained model and run an inference? By initializing are you referring to loading a model or initializing new weights for each instance this is executed?






                              share|improve this answer





















                              • I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                                – Evan
                                Nov 8 at 7:53















                              up vote
                              0
                              down vote













                              Are you trying to load a pretrained model and run an inference? By initializing are you referring to loading a model or initializing new weights for each instance this is executed?






                              share|improve this answer





















                              • I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                                – Evan
                                Nov 8 at 7:53













                              up vote
                              0
                              down vote










                              up vote
                              0
                              down vote









                              Are you trying to load a pretrained model and run an inference? By initializing are you referring to loading a model or initializing new weights for each instance this is executed?






                              share|improve this answer












                              Are you trying to load a pretrained model and run an inference? By initializing are you referring to loading a model or initializing new weights for each instance this is executed?







                              share|improve this answer












                              share|improve this answer



                              share|improve this answer










                              answered Nov 7 at 16:36









                              vr9494

                              516




                              516












                              • I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                                – Evan
                                Nov 8 at 7:53


















                              • I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                                – Evan
                                Nov 8 at 7:53
















                              I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                              – Evan
                              Nov 8 at 7:53




                              I am trying to load a pre-trained model once at the start and run inference many times on demand.But I want this to happen in a structure way within main() and init , just like with keras_model, pytorch_model, max_pooling and word2vec
                              – Evan
                              Nov 8 at 7:53


















                               

                              draft saved


                              draft discarded



















































                               


                              draft saved


                              draft discarded














                              StackExchange.ready(
                              function () {
                              StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53192824%2finitialize-a-tensorflow-model-in-main-pass-it-to-init-and-execute-inside%23new-answer', 'question_page');
                              }
                              );

                              Post as a guest















                              Required, but never shown





















































                              Required, but never shown














                              Required, but never shown












                              Required, but never shown







                              Required, but never shown

































                              Required, but never shown














                              Required, but never shown












                              Required, but never shown







                              Required, but never shown







                              這個網誌中的熱門文章

                              Xamarin.form Move up view when keyboard appear

                              Post-Redirect-Get with Spring WebFlux and Thymeleaf

                              Anylogic : not able to use stopDelay()