llSourcell / tensorflow_chatbot

Tensorflow chatbot demo by @Sirajology on Youtube
1.45k stars 806 forks source link

migrate to tensorflow 2.10 #101

Open shabthi opened 4 years ago

shabthi commented 4 years ago

Mode : train

Preparing data in working_dir/ 2020-03-11 21:17:23.309411: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2020-03-11 21:17:23.336349: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2599990000 Hz 2020-03-11 21:17:23.336705: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55debfb184a0 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2020-03-11 21:17:23.336727: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2020-03-11 21:17:23.336994: I tensorflow/core/common_runtime/process_util.cc:147] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance. Creating 3 layers of 256 units. WARNING:tensorflow:From /home/shabthi/anaconda3/envs/ml/lib/python3.6/site-packages/tensorflow_core/python/ops/resource_variable_ops.py:1635: calling BaseResourceVariable.init (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. WARNING:tensorflow:From /home/shabthi/Desktop/ML/tensorflow_chatbot/seq2seq_model.py:106: GRUCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version. Instructions for updating: This class is equivalent as tf.keras.layers.GRUCell, and will be replaced by that in Tensorflow 2.0. WARNING:tensorflow:From /home/shabthi/Desktop/ML/tensorflow_chatbot/seq2seq_model.py:111: MultiRNNCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version. Instructions for updating: This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0. WARNING:tensorflow:At least two cells provided to MultiRNNCell are the same object and will share weights. Traceback (most recent call last): File "execute.py", line 319, in train() File "execute.py", line 137, in train model = create_model(sess, False) File "execute.py", line 104, in create_model model = seq2seq_model.Seq2SeqModel( gConfig['enc_vocab_size'], gConfig['dec_vocab_size'], _buckets, gConfig['layer_size'], gConfig['num_layers'], gConfig['max_gradient_norm'], gConfig['batch_size'], gConfig['learning_rate'], gConfig['learning_rate_decay_factor'], forward_only=forward_only) File "/home/shabthi/Desktop/ML/tensorflow_chatbot/seq2seq_model.py", line 154, in init self.outputs, self.losses = tf.contrib.legacy_seq2seq.model_with_buckets( AttributeError: module 'tensorflow' has no attribute 'contrib'