I've been using this tutorial from TensorFlow's site to create a script (python3) that performs a style transfer. I'm trying to train a model on a particular art piece and then apply that style to any random photo. From my understanding of this tutorial the script takes a style image and a content image, runs them through the VGG19 model and spits out a final image (takes about 30min on my machine). But I see no way to save the trained model to apply it to another content photo. This tutorial doesn't use TF's model fit(), predict(), and save() methods like I would expect. It just seems to be applying the prediction to the image as it trains.
How do I save the trained model? Once saved how do I use it on another content photo?
Use model.save() method.
Read this tutorial: https://www.tensorflow.org/guide/keras/save_and_serialize
Related
I am trying to train a custom object detector using tflite model maker (https://www.tensorflow.org/lite/tutorials/model_maker_object_detection). I want to deploy trained tflite model to coral edgeTPU. I want to use tensorflow tfrecord (multiple) as input for training a model like object detection API. I tried with
tflite_model_maker.object_detector.DataLoader(
tfrecord_file_patten, size, label_map, annotations_json_file=None
) but I am not able to work around it. I have following questions.
Is it possible to tfrecord for training like mentioned above?
Is it also possible to pass multiple CSV files for training?
For multiple CSV files, you could probably just append one file to the other. Then you'd just have to pass one csv file.
As for passing a tfrecord instead, this should be possible. I'm also attempting to do this, so if I get it working I'll update my post. Looking at the source, it seems from_cache is the function internally used. Following that structure, should be able to create a DataLoader object similarly:
train_data = DataLoader(tfrecord_file_patten, meta_data['size'],
meta_data['label_map'], ann_json_file)
In this case, tfrecord_file_patten should be a tfrecord of your training data. You can construct the validation and test data the same way. This will work provided you're constructing your TFRecords correctly. There appears to be some inconsistency to how it's done in different places, so make sure you follow the same structure in creating the TFRecords as found in the ModelMaker source. This worked for me. One specific thing to watch out for is to use an integer for the 'image/source_id' feature in your TFExamples. If you use a string it'll throw an error.
According to the demo code
"Image similarity estimation using a Siamese Network with a contrastive loss"
https://keras.io/examples/vision/siamese_contrastive/
I'm trying to save model by model.save to h5 or hdf5; however, after I used load_model (even tried load_weights)
it showed error message for : unknown opcode
Have done googling job which all tells me it's python version problem between py3.5~py3.6
But actually I use only python 3.8....
other info say that there's some extra job need to be done either in model building or load_model
It would be very kind for any one to help provide the save and load model part
to make this demo code more completed
thanks!!
Actually here they are using two individual factors which come in a custom object.
Custom objects:
contrastive loss
embedding layer: where we are finding euclidean_distance.
Saving model:
for the saving model, it's straightforward
<model_name>.save("siamese_contrastive.h5")
Loading model:
Here the good part will come model will not load directly here because it doesn't have an understanding of two things one is your custom layer and 2nd is your loss.
model = tf.keras.models.load_model('siamese_contrastive.h5', custom_objects={ })
In the custom object mentioned above, you have to provide the definition of those two objects.
After that, it will accept your model and it will run separately at inferencing time.
Still figuring out how??
Have a look at my implementation let me know if you still have any questions: https://github.com/anukash/Keras_siamese_contrastive
I have defined a deep learning model my_unet() in tensorflow. During training I set save_weigths=False since I wanted to save the entire model (not only the wieghts bu the whole configuration). The generated file is path_to_model.hdf5.
However, when loading back the model I used the earlier version (I forgot to update it) in which I first called the model and then load the model using:
model = my_unet()
model.load_weights(path_to_model.hdf5)
Instead of simply using: model = tf.keras.models.load_model(path_to_model.hdf5) to load the entire model.
Both ways of loading the model and the weights provided the same predictions when run in some dummy data and there were no errors.
My question is: Why loading the entire model using model.load_weights() does not generate any problem? What is the structure of the hdf5 file and how theese two ways of loading exactly work? Where can I find this information?
You can please see the documentation here for any future reference: http://davis.lbl.gov/Manuals/HDF5-1.8.7/UG/03_DataModel.html
I am using matterport repository to train MASK RCNN on a custom dataset. I have been successful in training. Now I want to save the trained model and use it in a web application to detect objects. How do I save the mask rcnn model after training? Please guide me.
The link of the repository:
https://github.com/matterport/Mask_RCNN
Based on this discussion on GitHub, it appears that trained model or weights of matterport/Mask RCNN can be saved as a JSON file in a manner similar to those trained via standard Keras:
import keras
import json
def save_model(trained_model, out_fname="model.json"):
jsonObj = trained_model.keras_model.to_json()
with open(out_fname, "w") as fh:
fj.write(jsonObj)
save_model(model, "mymodel.json")
Update: If you run into the error related to thread-like object, you might find this post helpful...
In the Inspect_model.ipynb notebook under the "Load Model" topic you can save it after it loads the model in inference mode.
in the folder Mask_RCNN/logs generates a folder inside it
I am not sure if we really need to save the whole model again since normally when we used the matterport git we just train new weights on the existing architecture and doesnt make changes to the architecture. When we used this for a pet project , post training - we defined a new model as the MASK RCNN object (from mrcnn.model import MaskRCNN) with the parameter mode as inference and then loaded the newly trained weights model.load_weights('<logpath/trainedweights.h5>', by_name=True)
I am trying to implement Neural Style Transfer using TensorFlow and want to integrate the same within an Android application for image filtering. Can anyone help me save this TensorFlow model, so I can restore it whenever in use in the application?
I've tried creating .ckpt file of this TensorFlow model, but I'm not able to create one.
I haven't copied the code here as it consists of dozens of lines. Here is the link for the model https://colab.research.google.com/github/tensorflow/models/blob/master/research/nst_blogpost/4_Neural_Style_Transfer_with_Eager_Execution.ipynb
I am expecting to save this model to generate a new image at very low latency. Currently, I've to run hundreds of iterations for every image and that's what I don't want in real time while running in the application.