I'm reading the official tutorial on save-load in Keras and it seems whether I used save or save_weights methods, then the optimizer parameters are going to be saved at any rate. How can save model's weights only?
model.save('./savedmodel.h5', save_format='h5', include_optimizer=False)
If save_format='tf', whether include_optimizer=False or True, it's useless as I tried.
In Keras, to save model weights, do:
model.save_weights('my_model_weights.h5')
To load model weights:
model.load_weights('my_model_weights.h5')
Also see additional example on saving/loading weights by layer name from here.
Related
I want to know if there is any way to see the parameters of models in tensorflow. there is a command in pytorch i.e. torch.load('/filepath').
For a prediction context, you can do a
model = tf.keras.models.load_model(PATH, compile=True)
That works with both .h5 keras models and models on SavedModel format. Otherwise you might have to provide custom metrics and training code you may not have on the prediction context.
For references, check it here: https://www.tensorflow.org/api_docs/python/tf/keras/models/load_model
Provided that you already have a model saved at MODEL_PATH, this should do the trick:
model = tf.keras.models.load_model(MODEL_PATH)
model.summary()
Check this out for more info on saving and loading models.
I am using a custom keras model in Databricks environment.
For a custom keras model, model.save(model.h5) does not work, because custom model is not serializable. Instead it is recommended to use model.save_weights(path) as an alternate.
model.save_weights(pathDirectory) works. This yields 3 files checkpoint,.data-00000-of-00001,.index in the pathDirectory
For loading weights, Following mechanism is working fine.
model = Model()
model.load_weights(path)
But I want to train my model on pretrained weights I just saved. Like I saved model weights, and continue training on these saved weights afterwards.
So, when I load model weights and apply training loop, I get this error, TypeError: 'CheckpointLoadStatus' object is not callable
After much research, I have found a workaround,
we can also save model using
model.save("model.hpy5") and read it the saved model in databricks.
model.h5 not work for customized models, but it works for standard models.
I will describe my intention here. I want to import BERT pretrained model via tf-hub function hub.module(bert_url, trainable = True) and utilize it for text classification task. I plan to use a large corpus to fine-tune weights of BERT as well as a few dense layers whose inputs are the BERT outputs. I would then like to freeze layers of BERT and train only the dense layers following BERT. How can I do this efficiently?
You mention Hub's TF1 API hub.Module, so I suppose you are writing TF1 code and using the TF1-compatible Hub assets google/bert/..., such as https://tfhub.dev/google/bert_cased_L-12_H-768_A-12/1
Are you going to have separate run of your program for the two phases of training? If so, maybe you can just drop trainable=True from the hub.Module call in the second run. This doesn't affect variable names, so you can restore the training result from the first run, including BERT's adjusted weights. (To be clear: the pre-trained weights shipped with the hub.Module are only used for initialization at the very start of training; restoring a checkpoint overrides them.)
I was wondering why do we need to save the model while training ?
isn't enough to save it once at the beginning of the train and then only save the weights during the train ?
I mean , The model isn't changing during the train , why this boolean is need for ?
class ModelCheckpoint(Callback):
...
save_weights_only: if True, then only the model's weights will be saved.
...
Thanks !
Its not a need or requirement, its just convenience. In a typical DL/DS workflow, you train a lot of models with different configurations and it is quite easy to get lost. Maybe you now have saved the weights for the best model but you don't remember which model configuration it was used. That information is not part of the weights and has to be recorded separately.
Then Keras provides a simple solution, to store the mode (which takes less than 10 KB) along with the weights, so in the case that you lose the original model configuration, it is still saved in the same HDF5 file.
Also consider the case where you send the model weights to someone else without the model configuration, how can you load the weights without a model? Again its just convenience.
In classify_image.py, the input image is fed with a loaded image in
predictions = sess.run(softmax_tensor,{'DecodeJpeg/contents:0': image_data})
What if I want to add new layers to the inception model and train the whole model again? Are the variables loaded from classify_image_graph_def.pb trainable? I saw that freeze_graph.py used convert_variables_to_constants to produce freezed graph. So can those loaded weights be trained again, are they constants? And how can I connect the input('shuffle_batch:0') to the inception model to the output of tf.train.shuffle_batch?
The model used in classify_image.py has its variables frozen into constants, and doesn't have any gradient ops, so it's not easy to turn it back into something trainable. You can see how we remove one layer and replace it with something trainable here:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py
It's hard to generalize though. You'd be better off looking at some examples of fine-tuning here:
https://github.com/tensorflow/models/tree/master/inception#how-to-fine-tune-a-pre-trained-model-on-a-new-task