How to load, edit, and then save a TensorFlow checkpoint? - tensorflow

I would like to be able to load in all weights and biases of a TensorFlow checkpoint, apply some mathematical operations to the weights and biases (such as thresholding, scaling, etc), and then save a new TensorFlow checkpoint with the same structure as the original but with the edited weights and biases. Using an answer to this question I am able to successfully load a TensorFlow checkpoint and view the names and contents of the tensors within it, but I am unable to make changes to these tensors. This post asks a similar question and the asker is referred to this documentation on MetaGraphs, but I am new to TensorFlow and so I don't see how this information could be helpful.
So, what is the most effective way to load, edit, and then save TensorFlow checkpoints?

Related

Which layers are frozen using Tensorflow 2 Object detection API?

How can I understand which layers are frozen fine-tuning a detection model from Tensorflow Model Zoo 2?
I have already set with success the Path for fine_tune_checkpoint and fine_tune_checkpoint_type: detection and in the file proto I have already read that "detection" means
// 2. "detection": Restores the entire feature extractor.
The only parts of the full detection model that are not restored are the box and class prediction heads.
This option is typically used when you want to use a pre-trained detection model
and train on a new dataset or task which requires different box and class prediction heads.
I didn't really understand what does that means. Restored means Frozen in this context?
As I understand it, currently the Tensorflow 2 Object detection does not freeze any layers when training from a fine tune checkpoint. There is a issue reported here to support specifying which layers to freeze in the pipeline config. If you look at the training step function, you can see that all trainable variables are used when applying gradients during training.
Restored here means that the model weights are copied from the checkpoint to be used as a starting point for training. Frozen would mean that the weights are not changed (i.e. no gradient is applied) during training.

Visualize Tensorflow Graph from Checkpoint

I am importing a pretrained mobilenet's model mobilenet_v1_0.25_128_frozen.pb into my tensorflow environment. Once imported, I want to be able to save a snapshot of the model architecture in the form of .png. I know that there is a way to do this in keras with tf.keras.utils.plot_model(model, to_file="model.png"). Is there a way to do this in tensorflow session without using Tensorboard. In case, you recommend using tensorboard, I don't want to separately run tensorboard. I want a way to save the model architecture inside the tensorflow session without starting tensorboard.

How to extract weights of DQN agent in TF-Agents framework?

I am using TF-Agents for a custom reinforcement learning problem, where I train a DQN (constructed using DqnAgents from the TF-Agents framework) on some features from my custom environment, and separately use a keras convolutional model to extract these features from images. Now I want to combine these two models into a single model and use transfer learning, where I want to initialize the weights of the first part of the network (images-to-features) as well as the second part which would have been the DQN layers in the previous case.
I am trying to build this combined model using keras.layers and compiling it with the Tf-Agents tf.networks.sequential class to bring it to the necessary form required when passing it to the DqnAgent() class. (Let's call this statement (a)).
I am able to initialize the image feature extractor network's layers with the weights since I saved it as a .h5 file and am able to obtain numpy arrays of the same. So I am able to do the transfer learning for this part.
The problem is with the DQN layers, where I saved the policy from the previous example using the prescribed Tensorflow Saved Model Format (pb) which gives me a folder containing model attributes. However, I am unable to view/extract the weights of my DQN in this way, and the recommended tf.saved_model.load('policy_directory') is not really transparent with respect to what data I can see regarding the policy. If I have to follow the transfer learning as I do in statement (a), I need to extract the weights of my DQN and assign them to the new network. The documentation seems to be quite sparse for this case where transfer learning needs to be applied.
Can anyone help me in this, by explaining how I can extract weights from the Saved Model method (from the pb file)? Or is there a better way to go about this problem?

How to run inference on inception v3 trained models?

I've successfully trained the inception v3 model on custom 200 classes from scratch. Now I have ckpt files in my output dir. How to use those models to run inference?
Preferably, load the model on GPU and pass images whenever I want while the model persists on GPU. Using TensorFlow serving is not an option for me.
Note: I've tried to freeze these models but failed to correctly put output_nodes while freezing. Used ImagenetV3/Predictions/Softmax but couldn't use it with feed_dict as I couldn't get required tensors from freezed model.
There is poor documentation on TF site & repo on this inference part.
It sounds like you're on the right track, you don't really do anything different at inference time as you do at training time except that you don't ask it to compute the optimizer at inference time, and by not doing so, no weights are ever updated.
The save and restore guide in tensorflow documentation explains how to restore a model from checkpoint:
https://www.tensorflow.org/programmers_guide/saved_model
You have two options when restoring a model, either you build the OPS again from code (usually a build_graph() method) then load the variables in from the checkpoint, I use this method most commonly. Or you can load the graph definition & variables in from the checkpoint if the graph definition was saved with the checkpoint.
Once you've loaded the graph you'll create a session and ask the graph to compute just the output. The tensor ImagenetV3/Predictions/Softmax looks right to me (I'm not immediately familiar with the particular model you're working with). You will need to pass in the appropriate inputs, your images, and possibly whatever parameters the graph requires, sometimes an is_train boolean is needed, and other such details.
Since you aren't asking tensorflow to compute the optimizer operation no weights will be updated. There's really no difference between training and inference other than what operations you request the graph to compute.
Tensorflow will use the GPU by default just as it did with training, so all of that is pretty much handled behind the scenes for you.

finetuning tensorflow seq2seq model

I've trained a seq2seq model for machine translation (DE-EN). And I have saved the trained model checkpoint. Now, I'd like to fine-tune this model checkpoint to some specific domain data samples which have not been seen in previous training phase. Is there a way to achieve this in tensorflow? Like modifying the embedding matrix somehow.
I couldn't find any relevant papers or works addressing this issue.
Also, I'm aware of the fact that the vocabulary files needs to be updated according to new sentence pairs. But, then do we have to again start training from scratch? Isn't there an easy way to dynamically update the vocabulary files and embedding matrix according to the new samples and continue training from the latest checkpoint?