Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
[BUG] model load, then fit (re-train), error of layer_crf #244
You must follow the issue template and provide as much information as possible. otherwise, this issue will be closed.
Thanks for considering to open an issue. Before you submit your issue, please confirm these boxes are checked.
You can post pictures, but if specific text or code is required to reproduce the issue, please provide the text in a plain text format for easy copy/paste.
Hi, I have trained a model (BiLSTM_CRF_Model).
model = kashgari.utils.load_model(READ_MODEL_PATH) model.compile_model(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) model.fit_without_generator(train_x, train_y, x_validate=dev_x, y_validate=dev_y, epochs=2, batch_size=64)
File "/home/userroot/.local/lib/python3.6/site-packages/kashgari/tasks/base_model.py", line 345, in fit_without_generator
ValueError: Variable <tf.Variable 'layer_crf/transitions:0' shape=(6, 6) dtype=float32> has
[The steps to reproduce this issue. What is the URL you were trying to play, where did you put your code, etc.]
[Add anything else here]