When I call the cosine_decay function in tensorflow, it shows this error:
'<' not supported between instances of 'CosineDecay' and 'int'
Here is my code:
decay_steps = 1000
lr_decayed_fn = tf.keras.experimental.CosineDecay(initial_learning_rate=0.01, decay_steps=1000)
model.compile(optimizer=Adam(lr=lr_decayed_fn), loss=dice_coef_loss, metrics=[dice_coef])
I just followed the tutorial on tensorflow and I don't know why there is this error
Change Adam(lr=lr_decayed_fn) to Adam(learning_rate=lr_decayed_fn)
The Adam optimizer call in tensorflow v2 needs learning_rate to be spelled out, it does not take the argument as "lr." See this issue: https://github.com/tensorflow/tensorflow/issues/44172
Related
I am trying to run inference on my trained model following this tutorial. I am using TF 2.1.0 and I have tried with tf-nightly 2.5.0.dev20201202.
But I get TypeError: 'AutoTrackable' object is not callable when I hit the following line detections = detect_fn(input_tensor)
I am aware that
'AutoTrackable' object is not callable in Python
exists but I am not using tensorflow hub and I don't understand how the answer could help me.
Thanks
Try using detect_fn.signatures\['default'](input_tensor)
Changing detections = detect_fn(input_tensor) to
detections = detect_fn.signatures['serving_default'](input_tensor)
fixed the issue for me.
I am designing a custom loss function in which i need to access model weights in the loss function.
Code:
def my_loss(y_true, y_pred):
model.get_weights()
return K.sum(-(y_true * K.log(y_pred)))/batch_size + ((error2/num_conv)*scal_f)
But when I try to access weights in loss function by calling get_weights() it gives me following error
Error = "Cannot get value inside Tensorflow graph function."
I figured it out with some help that the problem was by default eager execution in tf 2.0 I just turned it off and it worked
I am trying to understand Pytorch autograd in depth; I would like to observe the gradient of a simple tensor after going through a sigmoid function as below:
import torch
from torch import autograd
D = torch.arange(-8, 8, 0.1, requires_grad=True)
with autograd.set_grad_enabled(True):
S = D.sigmoid()
S.backward()
My goal is to get D.grad() but even before calling it I get the runtime error:
RuntimeError: grad can be implicitly created only for scalar outputs
I see another post with similar question but the answer over there is not applied to my question. Thanks
The error means you can only run .backward (with no arguments) on a unitary/scalar tensor. I.e. a tensor with a single element.
For example, you could do
T = torch.sum(S)
T.backward()
since T would be a scalar output.
I posted some more information on using pytorch to compute derivatives of tensors in this answer.
Summary
My question is composed by:
A context in which I present my project, my working environment and my workflow
The detailed problem
The concerned parts of my code
The solutions I tried to solve my problem
The question reminder
Context
I've written a Python Keras implementation of a downgraded version of the original Super-Resolution GAN. Now I want to test it using Google Firebase Machine Learning Kit, by hosting it in the Google servers. That's why I have to convert my Keras program to a TensorFlow Lite one.
Environment and workflow (with the problem)
I'm training my program on Google Colab working environment: there, I've installed TF 2.0.0-beta1 (this choice is motivated by this uncorrect answer: https://datascience.stackexchange.com/a/57408/78409).
Workflow (and problem):
I write locally my Python Keras program, keeping in mind that it will run on TF 2. So I use TF 2 imports, for example: from tensorflow.keras.optimizers import Adam and also from tensorflow.keras.layers import Conv2D, BatchNormalization
I send my code to my Drive
I run without any problem my Google Colab Notebook: TF 2 is used.
I get the output model in my Drive, and I download it.
I try to convert this model to the TFLite format by executing the following CLI: tflite_convert --output_file=srgan.tflite --keras_model_file=srgan.h5: here the problem appears.
The problem
Instead of outputing the TF Lite converted model from the TF (Keras) model, the previous CLI outputs this error:
ValueError: Unknown loss function:build_vgg19_loss_network
The function build_vgg19_loss_network is a custom loss function that I've implemented and that must be used by the GAN.
Parts of code that rise this problem
Presenting the custom loss function
The custom loss function is implemented like that:
def build_vgg19_loss_network(ground_truth_image, predicted_image):
loss_model = Vgg19Loss.define_loss_model(high_resolution_shape)
return mean(square(loss_model(ground_truth_image) - loss_model(predicted_image)))
Compiling the generator network with my custom loss function
generator_model.compile(optimizer=the_optimizer, loss=build_vgg19_loss_network)
What I've tried to do in order to solve the problem
As I read it on StackOverflow (link at the beginning of this question), TF 2 was thought to be sufficient to output a Keras model which would be correctly processed by my tflite_convert CLI. But it's not, obviously.
As I read it on GitHub, I tried to manually set my custom loss function among Keras' loss functions, by adding these lines: import tensorflow.keras.losses
tensorflow.keras.losses.build_vgg19_loss_network = build_vgg19_loss_network. It didn't work.
I read on GitHub I could use custom objects with load_model Keras function: but I only want to use compile Keras function. Not load_model.
My final question
I want to do only minor changes to my code, since it works fine. So I don't want, for example, to replace compile with load_model. With this constraint, could you help me, please, to make my CLI tflite_convert works with my custom loss function?
Since you are claiming that TFLite conversion is failing due to a custom loss function, you can save the model file without keep the optimizer details. To do that, set include_optimizer parameter to False as shown below:
model.save('model.h5', include_optimizer=False)
Now, if all the layers inside your model are convertible, they should get converted into TFLite file.
Edit:
You can then convert the h5 file like this:
import tensorflow as tf
model = tf.keras.models.load_model('model.h5') # srgan.h5 for you
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)
Usual practice to overcome the unsupported operators in TFLite conversion is documented here.
I had the same error. I recommend changing the loss to "mse" since you already have a well-trained model and you don't need to train with the .tflite file.
I've adapted the VAE example from the keras site to train on my data, and everything runs fine. But I'm unable to convert to coreml. The error is:
NameError: global name `batch_size' is not defined
Since batch_size clearly is defined in the python source, I'm guessing it has to do with how the conversion tool captures variable names. Does anyone know how I can fix it (or whether it is, indeed, possible to fix)?
Many thanks,
J.
I ran into a similar message when using parameters to construct the neural net. This should work:
from keras import models
batch_size = 50
model = models.load_model(filename, custom_objects={'batch_size': batch_size})
See also documentation: https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model