How can I load a .pb protobuf model and then tweak the network as needed (specially the outer layers) in order to train a new model for completely different classes? Effectively doing transfer learning?
I want to do something like these (i.e. train the outer layers with a bigger learning rate than the inner layers) among other things, so I need a way to not only load the graph with the variables, but to alter the network's structure and hyperparameters too.
If anyone has an example to follow with the inception model, it would be amazing!
My question is very similar to this one.
I've searched all over the internet (TF docs, Github, StackOverflow, Google...) but I can't seam to find something useful for a novice.
Thanks a lot!
This is the updated tutorial from official Tensorflow website https://www.tensorflow.org/hub/tutorials/image_retraining
They use the pre trained Inception V3 model and everything works fine. You can change the dataset folder to your own dataset
tf.import_graph_def() is the function for loading a GraphDef:
https://www.tensorflow.org/versions/0.6.0/api_docs/python/framework.html#import_graph_def
Hopefully once imported, you can make the modifications to the graph you need. It would be easier, though, to modify the Python code that generated the graph in the first place, if you have access to that.
Related
I am new to Deep Learning. I finished training a model that took 8 hours to run, but I forgot to plot the accuracy graph before closing the jupyter notebook.
I need to plot the graph, and I did save the model to my hard-disk. But how do I plot the accuracy graph of a pre-trained model? I searched online for solutions and came up empty.
Any help would be appreciated! Thanks!
What kind of framework did you use and which version? In the future problem, you may face, this information can play a key role in the way we can help you.
Unfortunately, for Pytorch/Tensorflow the model you saved is likely to be saved with only the weights of the neurons, not with its history. Once Jupyter Notebook is closed, the memory is cleaned (and with it, the data of your training history).
The only thing you can extract is the final loss/accuracy you had.
However, if you regularly saved a version of the model, you can load them and compute manually the accuracy/loss that you need. Next, you can use matplotlib to reconstruct the graph.
I understand this is probably not the answer you were looking for. However, if the hardware is yours, I would recommend you to restart training. 8h is not that much to train a model in deep learning.
I am following this tutorial:
https://www.tensorflow.org/tutorials/keras/text_classification_with_hub
It only goes up to fitting the model but I couldn't find how to use the model on a new dataset to classify unlabeled data. I tried following other tutorials but I couldn't get them to work since they might not be text based.
model.add(tf.keras.layers.Dense(1))
I run into an issue where I try to set the layer to 2 for positive, negative but that doesn't work either.
I think you misunderstood the purpose of that tutorial. That tutorial is applying the use of what is known as "transfer learning". Transfer Learning is when you take an already trained model, and train it with other data. What you are doing is creating an entirely new model, which is not the purpose of that specific tutorial. Furthermore, for that model you need a labeled dataset, which is provided in the tutorial using the Tensorflow Datasets library. To accomplish what you are trying to do, you must look at a different tutorial explaining how to train an LSTM model for text classification from scratch.
I want to use a pre-trained ResNet model which Tensorflow provides here.
First I downloaded the code (resnet_v1.py) to reconstruct the model's graph here. The model's weights (resnet_v1_50.ckpt) can be found on the same page here.
The model can be tested using the following script (resnet_v1_test.py) from here. However, I have problems to extract the right information from resnet_v1_test.py. I don't understand many things that happen in this script. Which are the essential functions to pass a random image through the network? How can I access the weights and activations for further work?
What are the next steps from here? I would appreciate any help!
TL;DR: How can I use the resnet_v1_test.py script to perform classification and access weights and activations?
I am searching for a way to forward lower layer output to a higher layer with a loaded VGG16 model using CNTK.
The background of my problem is:
I reimplemented some parts of Fully Convolutional Networks for Semantic Segmentation but then I ran into some problems: Starting with this example I first replaced the fully connected layers with fully convolutional and slit the sequence in the model definition part into chunks where I could simply access pool3 and pool4 for the later usage in eg. Convolution2D((1,1), num_classes, name='score_pool4')(pool4). This works fine but after building the model I noticed, that I need to implement an own way to read batches because the build-in reader does not support 2D labels right now. Now I simply read the images using OpenCV and replaced the training_session(...).train() with a for loop and trainer.train_minibatch({model['features']: my_loaded_features, model['labels']: my_2D_labels}) this works well but because of the removed training_session part I don't know where I could apply the existing VGG16 weights.
My problem is:
I searched for transfer learning examples where those guys load models using C.load_model(...) and then clone the needed layers but now I am wondering how could I access cloned_layers->pool4 (in the middle of the loaded model) if I also want to use it in deeper layers.
I tried Convolution2D((1,1), num_classes, name='score_pool4')(cloned_layers.find_by_name('pool4'))but I ended up with some error messages while learner initialization because of "unknown shape information" in used weight variables.
So how can I access those layers within the loaded model for later (deeper) usage?
Thanks for reading (and maybe helping)!
If you are looking to read custom data. There are two tutorials on building your own readers. https://cntk.ai/pythondocs/manuals.html
Regarding cloning parts of a network - here is a link to another post on StackOverflow that has exemplar code
I want to train a cnn for 20000 steps. In the 100th step I want to save all variables and after that I want to re-run my code restoring model and starting from the 100th step. I am trying to make it work with tensorflow documentation: https://www.tensorflow.org/versions/r0.10/how_tos/variables/index.html but I can't. Any help?
Im stuck in something similar but maybe this link can help you. Im new in tensorflow but i think you cant restore and fit without need to training again you model.
This functionality is still unstable , and the documentation is outdated so is confusing, what worked for me(this was a suggestion of people from google that works directly on tensorflow) was to use the model_dir parameter on the constructor of my models before training, in this you will tell where to store your model, after training you just instantiate again a model using the same model_dir and it will restore the model from the files and checkpoints generated.