epoch | A simple but powerful Epoch converter

Im attempting to find model performance metrics (F1 score, accuracy, recall) following this guide https://machinelearningmastery.com/how-to-calculate-precision-recall-f1-and-more-for-deep-learning-models/

This exact code was working a few months ago but now returning all sorts of errors, very confusing since i havent changed one character of this code. Maybe a package update has changed things?

I fit the sequential model with model.fit, then used model.evaluate to find test accuracy. Now i am attempting to use model.predict_classes to make class predictions (model is a multi-class classifier). Code shown below:

When recognizing hand gesture classes, I always get the same class, although I tried changing the parameters and even passed the data without normalization:

We have a bunch of microservices based on Spring Boot 2.5.4 also including spring-kafka:2.7.6 and spring-boot-actuator:2.5.4. All the services use Tomcat as servlet container and graceful shutdown enabled. These microservices are containerized using docker.
Due to a misconfiguration, yesterday we faced a problem on one of these containers because it took a port already bound from another one.
Log states:

I have created a working CNN model in Keras/Tensorflow, and have successfully used the CIFAR-10 & MNIST datasets to test this model. The functioning code as seen below:

So I was trying to convert my data's timestamps from Unix timestamps to a more readable date format. I created a simple Java program to do so and write to a .csv file, and that went smoothly. I tried using it for my model by one-hot encoding it into numbers and then turning everything into normalized data. However, after my attempt to one-hot encode (which I am not sure if it even worked), my normalization process using make_column_transformer failed.

I am trying to train a seq2seq model for language translation, and I am copy-pasting code from this Kaggle Notebook on Google Colab. The code is working fine with CPU and GPU, but it is giving me errors while training on a TPU. This same question has been already asked here.

Here is my code:

I am writing a Splittable DoFn to read a MongoDB change stream. It allows me to observe events describing changes to a collection, and I can start reading at an arbitrary cluster timestamp I want, provided oplog has enough history. Cluster timestamps are seconds since epoch combined with the serial number of operation in a given second.

I have looked at other examples of an SDF but all I have seen so far assume a "seekable" data source (Kafka topic-partition, Parquet/Avro file, etc.)

The interface exposed by MongoDB is a simple Iterable, so I cannot really seek to a precise offset (aside from getting a new Iterable starting after a timestamp), and events produced by it have only cluster timestamps - again, no precise offset associated with an output element.

To configure the SDF I use the following class as my input element type:

I'm trying to fine-tune the ReformerModelWithLMHead (google/reformer-enwik8) for NER. I used the padding sequence length same as in the encode method (max_length = max([len(string) for string in list_of_strings])) along with attention_masks. And I got this error:

ValueError: If training, make sure that config.axial_pos_shape factors: (128, 512) multiply to sequence length. Got prod((128, 512)) != sequence_length: 2248. You might want to consider padding your sequence length to 65536 or changing config.axial_pos_shape.

• When I changed the sequence length to 65536, my colab session crashed by getting all the inputs of 65536 lengths.
• According to the second option(changing config.axial_pos_shape), I cannot change it.

I would like to know, Is there any chance to change config.axial_pos_shape while fine-tuning the model? Or I'm missing something in encoding the input strings for reformer-enwik8?

Thanks!

Question Update: I have tried the following methods:

1. By giving paramteres at the time of model instantiation:

model = transformers.ReformerModelWithLMHead.from_pretrained("google/reformer-enwik8", num_labels=9, max_position_embeddings=1024, axial_pos_shape=[16,64], axial_pos_embds_dim=[32,96],hidden_size=128)

It gives me the following error:

RuntimeError: Error(s) in loading state_dict for ReformerModelWithLMHead: size mismatch for reformer.embeddings.word_embeddings.weight: copying a param with shape torch.Size([258, 1024]) from checkpoint, the shape in current model is torch.Size([258, 128]). size mismatch for reformer.embeddings.position_embeddings.weights.0: copying a param with shape torch.Size([128, 1, 256]) from checkpoint, the shape in current model is torch.Size([16, 1, 32]).

This is quite a long error.

1. Then I tried this code to update the config:

model1 = transformers.ReformerModelWithLMHead.from_pretrained('google/reformer-enwik8', num_labels = 9)

I have probem with this code , why ?

the code :