Configuring RNN model... WARNING:tensorflow:From /home/luo/TensorflowProject/LSTM_2019042202/LSTM_Model0504.py:83: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version. Instructions for updating: Future major versions of TensorFlow will allow gradients to flow into the labels input on backprop by default. See @{tf.nn.softmax_cross_entropy_with_logits_v2}. Loading test data... INFO:tensorflow:Restoring parameters from checkpoints/textrnn050401/best_validation1 Testing... Test Loss: 1.6, Test Acc: 90.97% Precision, Recall and F1-Score... precision recall f1-score support 1 0.89 0.07 0.13 29 2 0.91 0.03 0.07 29 3 0.81 0.03 0.06 30 4 0.74 0.12 0.35 30 5 0.66 0.08 0.00 30 micro avg 0.23 0.23 0.23 148 macro avg 0.51 0.23 0.12 148 weighted avg 0.50 0.23 0.12 148
[[5 0 0 1 1] [0 6 0 1 0] [0 0 4 2 1] [1 1 0 3 1] [0 2 1 2 2]]
[[5 0 1 0 1] [0 6 0 1 0] [1 0 4 1 1] [1 1 0 3 1] [0 2 1 2 2]]
[[5 0 1 0 1] [0 6 0 1 0] [1 0 4 1 1] [1 0 1 3 2] [0 0 2 3 2]]
classID precision 1 0.71 2 0.86 3 0.57 4 0.43 5 0.43
precision recall f1-score support 1 1.00 0.71 0.83 7 2 0.75 0.86 0.80 7 3 0.67 0.57 0.62 7 4 0.45 0.71 0.56 7 5 0.40 0.29 0.33 7 micro avg 0.63 0.63 0.63 35 macro avg 0.65 0.63 0.63 35 weighted avg 0.65 0.63 0.63 35 Confusion Matrix... [[5 0 1 0 1] [0 6 0 1 0] [1 0 4 1 1] [1 0 1 3 2] [0 0 2 3 2]]
[[5 0 0 1 0] [0 6 0 0 0] [0 0 5 1 0] [0 0 1 4 1] [0 0 0 2 4]]
classID precision 1 0.833 2 1.000 3 0.833 4 0.667 5 0.500 Confusion Matrix... [[5 0 0 1 0] [0 6 0 0 0] [0 0 5 1 0] [0 0 1 4 1] [0 0 1 2 3]]