We Keep Coding

Tensorflow's cycle gan model: error in fit method

I tried to run the code from here: https://keras.io/examples/generative/cyclegan/
but when running model.fit(..) I get the following error:
ValueError: Model <__main__.CycleGan object at 0x7fec3de767c0> cannot be saved either because the
input shape is not available or because the forward pass of the model is not defined.To define a
forward pass, please override `Model.call()`. To specify an input shape, either call
`build(input_shape)` directly, or call the model on actual data using `Model()`, `Model.fit()`, or
`Model.predict()`. If you have a custom training step, please make sure to invoke the forward pass
in train step through `Model.__call__`, i.e. `model(inputs)`, as opposed to `model.call()`.
Even if I run it through the linked colab file from the author. Did anyone else already faced this issue and knows how to fix it ?
I also tried to predefine the inputsize by model.build((batch_size,256,256,3)), but still get the same error.
If i comment the callbacks, it works. I think the problem is in the model_checkpoint_callback. Without it, the code works, but then I don't save the model.
Thanks a lot in advance for every answer!

The solution is to add this line:
# Create cycle gan model
cycle_gan_model = CycleGan(
generator_G=gen_G, generator_F=gen_F, discriminator_X=disc_X, discriminator_Y=disc_Y
)
# add following line:
cycle_gan_model.compute_output_shape(input_shape=(None, 256, 256, 3))

Compute class weight function issue in 'sklearn' library when used in 'Keras' classification (Python 3.8, only in VS code)

The classifier script I wrote is working fine and recently added weight balancing to the fitting. Since I added the weight estimate function using 'sklearn' library I get the following error :
compute_class_weight() takes 1 positional argument but 3 were given
This error does not make sense per documentation. The script should have three inputs but not sure why it says expecting only one variable. Full error and code information is shown below. Apparently, this is failing only in VS code. I tested in the Jupyter notebook and working fine. So it seems an issue with VS code compiler. Any one notice? ( I am using Python 3.8 with other latest other libraries)
from sklearn.utils import compute_class_weight
train_classes = train_generator.classes
class_weights = compute_class_weight(
"balanced",
np.unique(train_classes),
train_classes
)
class_weights = dict(zip(np.unique(train_classes), class_weights)),
class_weights
In Jupyter Notebook,

After spending a lot of time, this is how I fixed it. I still don't know why but when the code is modified as follows, it works fine. I got the idea after seeing this solution for a similar but slightly different issue.
class_weights = compute_class_weight(
class_weight = "balanced",
classes = np.unique(train_classes),
y = train_classes
)
class_weights = dict(zip(np.unique(train_classes), class_weights))
class_weights

I solved this problem with recode configuraiton.
from sklearn.utils.class_weight import compute_class_weight
class_weights = compute_class_weight(class_weight = "balanced", classes= np.unique(train_labels), y= train_labels)

You need to use older version of sklearn than you have.
for me it works fine with scikit-learn version 0.24.2.

Just follow this:
Why doesn't class_weight.compute_weight() work?
You just need to use class_weight, classes, y terms when you assign the related values.

How to Deploy Amazon-SageMaker Locally in Python

I trained my model in Amazon-SageMaker and downloaded it to my local computer. Unfortunately, I don't have any idea how to run the model locally.
The Model is in a directory with files like:
image-classification-0001.params
image-classification-0002.params
image-classification-0003.params
image-classification-0004.params
image-classification-0005.params
image-classification-symbol.json
model-shapes.json
Would anyone know how to run this locally with Python, or be able to point me to a resource that could help? I am trying to avoid calling the model using the Amazon API.
Edit: The model I used was created with code very similar to this example.
Any help is appreciated, I will award the bounty to whoever is most helpful, even if they don't completely solve the question.

This is not a complete answer as I do not have SageMaker setup (And I do not know MXNet) and so I can not practically test this approach (yes, as already mentioned, I do not want to call this a complete answer rather a probable pointer/approach to solve this issue).
The Assumption -
You mentioned a that your model is very similar to the notebook link you provided. If you read the text in the notebook carefully, you will see at some point there is something like this -
"In this demo, we are using Caltech-256 dataset, which contains 30608 images of 256 objects. For the training and validation data, we follow the splitting scheme in this MXNet example."
See the mention of MXNet there? Let us assume that you did not change a lot and hence your model is built using MXNet as well.
The Approach -
Assuming what I just mentioned, if you go and search in the documentation of AWS SageMaker Python SDK you will see a section about serialization of the modules. Which again, by itself, starts with another assumption -
"If you train function returns a Module object, it will be serialized by the default Module serialization system, unless you've specified a custom save function."
Assuming that this is True for your case, further reading in the same document tells us that "model-shapes.json" is a JSON serialised representation of your models, "model-symbol.json" is the serialization of the module symbols created by calling the 'save' function on the 'symbol' property of module, and finally "module.params" is the serialized (I am not sure if it is text or binary format) form of the module parameters.
Equipped with this knowledge we go and look into the documentation of MXNet. And Voila! We see here how we can save and load models with MXNet. So as you already have those saved files, you just need to load them in a local installation of MXNet and then run them to predict the unknown.
I hope this will help you to find a direction to solve your problem.
Bonus -
I am not sure if this also can do the same job, (it is also mentioned by #Seth Rothschild in the comments) but it should, you can see that AWS SageMaker Python SDK has a way to load models from saved ones as well.

Following SRC's advice, I was able to get it to work by following the instructions in this question and this doc which describe how to load a MXnet model.
I loaded the model like so:
lenet_model = mx.mod.Module.load('model_directory/image-classification',5)
image_l = 64
image_w = 64
lenet_model.bind(for_training=False, data_shapes=[('data',(1,3,image_l,image_w))],label_shapes=lenet_model._label_shapes)
Then predicted using the slightly modified helper functions in the previously linked documentation:
import mxnet as mx
import matplotlib.pyplot as plot
import cv2
import numpy as np
from mxnet.io import DataBatch
def get_image(url, show=False):
# download and show the image
fname = mx.test_utils.download(url)
img = cv2.cvtColor(cv2.imread(fname), cv2.COLOR_BGR2RGB)
if img is None:
return None
if show:
plt.imshow(img)
plt.axis('off')
# convert into format (batch, RGB, width, height)
img = cv2.resize(img, (64, 64))
img = np.swapaxes(img, 0, 2)
img = np.swapaxes(img, 1, 2)
img = img[np.newaxis, :]
return img
def predict(url, labels):
img = get_image(url, show=True)
# compute the predict probabilities
lenet_model.forward(DataBatch([mx.nd.array(img)]))
prob = lenet_model.get_outputs()[0].asnumpy()
# print the top-5
prob = np.squeeze(prob)
a = np.argsort(prob)[::-1]
for i in a[0:5]:
print('probability=%f, class=%s' %(prob[i], labels[i]))
Finally I called the prediction with this code:
labels = ['a','b','c', 'd','e', 'f']
predict('https://eximagesite/img_tst_a.jpg', labels )

If you want to host your trained model locally, and you are using Apache MXNet as your model framework (as you have in the above example), the simplest way is to use MXNet Model Server: https://github.com/awslabs/mxnet-model-server
Once you installed it locally, you can start serving using:
mxnet-model-server \
--models squeezenet=https://s3.amazonaws.com/model-server/models/squeezenet_v1.1/squeezenet_v1.1.model
and then call the local endpoint with the image
curl -O https://s3.amazonaws.com/model-server/inputs/kitten.jpg
curl -X POST http://127.0.0.1:8080/squeezenet/predict -F "data=#kitten.jpg"

Why does from read_data import get_minibatch() return ModuleNotFoundError: No module named 'read_data'

I'm currently going through the book Fundamentals of Deep Learning by Nikhil Buduma and it appears there's an error in one of the scripts it provides. The script is meant to provide an introduction into sessions in Tensorflow and is as follows:
import tensorflow as tf
from read_data import get_minibatch
x = tf.placeholder(tf.float32, name="x", shape=[None, 784])
w = tf.Variable(tf.random_uniform([784,10], -1, 1), name = "w")
b = tf.Variable(tf.zeroes([10]), name = "biases")
output = tf.matmul(x,w) + b
init_op = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init_op)
feed_dict = {"x" : get_minibatch()}
sess.run(output, feed_dict=feed_dict)
The problem I'm having is that I receive the error ModuleNotFoundError: No module named 'read_data'. The original script also had empty parenthesis after line 2's get_minibatch but I removed them to remove a different error. Do I have to externally download this library or something?

I ran across this same problem, reading the book.
read_data isn't any sort standard python library.
As Nick T said, it sort of seems like it ought to be a function that comes with the example source code for the book.
If you look at the example code on github, there are a few examples of reading data that are almost similar but not quite exact.
Anyway, i think the point is just that get_minibatch would be the function that feeds input data to the session.
I suspect the author didn't really intend us to run these examples verbatim.... or at least didn't test his examples really worked after writing them. (This is the second example that didn't run for me).

It's a known bug in the script provided in the book:
Read more here: http://www.oreilly.com/catalog/errataunconfirmed.csp?isbn=0636920039709

where do I find bidirectional_rnn in tensorflow 1.0.0?

I am using some code from here: https://github.com/monikkinom/ner-lstm with tensorflow. I think the code was written for an older version of tensorflow, I am using version 1.0.0. I used tf_upgrade.py to upgrade model.py in that github repos, but I am still getting the error:
output, _, _ = contrib_rnn.bidirectional_rnn(fw_cell, bw_cell,
AttributeError: 'module' object has no attribute 'bidirectional_rnn'
this is after I changed the bidirectional_rnn call to use contrib_rnn which is:
from tensorflow.contrib.rnn.python.ops import core_rnn as contrib_rnn
The old call was
output, _, _ = tf.nn.bidirectional_rnn(fw_cell, bw_cell,
tf.unpack(tf.transpose(self.input_data, perm=[1, 0, 2])),
dtype=tf.float32, sequence_length=self.length)
which also doesn't work.
I had to change the LSTMCell, DroputWrapper, etc. to rnn.LSTMCell, but they seem to work fine. It is the bidirectional_rnn that I can't figure out how to change.

In TensorFlow 1.0, you have the choice of two bidirectional RNN functions:
tf.nn.bidirectional_dynamic_rnn()
tf.contrib.rnn.static_bidirectional_rnn()

Maybe you can try to reimplement a bidirectional RNN by simply wrapping into a single class two monodirectional RNNs with the parameter "go_backwards=True" set on one of them. Then you can also have control over the type of merge done with the outputs. Maybe taking a look at the implementation in https://github.com/fchollet/keras/blob/master/keras/layers/wrappers.py (see the class Bidirectional) could get you started.