# Machine Learning in Elixir: comments on chapter 11, version B 3.0 **URL:** \ **Category:** PragProg Customers\ **Tags:** book-machine-learning-in-elixir, errata\ **Created:** [10 March 2024 10:57 UTC](https://forum.devtalk.com/t/machine-learning-in-elixir-comments-on-chapter-11-version-b-3-0/146857 "2024-03-10T10:57:08Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![pieteeken](https://forum.devtalk.com/letter_avatar_proxy/v4/letter/p/b9e5f3/32.png) [@pieteeken](https://forum.devtalk.com/u/pieteeken)\ **Post date:** [10 March 2024 10:57 UTC](https://forum.devtalk.com/t/machine-learning-in-elixir-comments-on-chapter-11-version-b-3-0/146857/1 "2024-03-10T10:57:08Z")
**Comments to Chapter 11 version B 3.0** @seanmor5 The dependencies from chapter 11 gave errors on 10 march 2024. I followed the advices in the errors, but at the end it still didn’t work. So I loaded this versions (They work with cuda120!) ```elixir Mix.install([ {:bumblebee, "> 0.0.0"}, {:axon, "> 0.0.0"}, {:exla, "> 0.0.0"}, {:nx, "> 0.0.0"}, {:kino, "~> 0.8"}, {:kino_bumblebee, "> 0.0.0"} ]) Nx.global_default_backend(EXLA.Backend) ``` * * * ### Section Generating Text Bumblebee.Text.conversation does not exist in BumbleBee version 0.5 So I used Bumblebee.Text.generation() Also the Kino part had to be changed! With Bumblebee.Text.generation() the model with “microsoft/DialoGPT-medium” only finishes sentences. So it is not really a chatbot. If you change the model to “gpt2” you get a real chatbot (but it is a weird bot!) Sentences are repeated. Don’t know how to handle it. * * * ```elixir # The weird bot {:ok, model} = Bumblebee.load_model({:hf, "gpt2"}) {:ok, tokenizer} = Bumblebee.load_tokenizer({:hf, "gpt2"}) {:ok, generation_config} = Bumblebee.load_generation_config({:hf, "gpt2"}) # This model "microsoft/DialoGPT-medium" only finishes sentences # {:ok, model} = Bumblebee.load_model({:hf, "microsoft/DialoGPT-medium"}) # {:ok, tokenizer} = Bumblebee.load_tokenizer({:hf, "gpt2"}) # {:ok, generation_config} = Bumblebee.load_generation_config({:hf, "microsoft/DialoGPT-medium"}) generation_config = Bumblebee.configure(generation_config, max_new_tokens: 100) ``` Also the serving statement mus be changed ```elixir serving = Bumblebee.Text.generation(model, tokenizer, generation_config, compile: [batch_size: 1, sequence_length: 1000], defn_options: [compiler: EXLA] ) ``` The Kino part must be changed a bit. In the form watch the “%{results…” line ```elixir frame = Kino.Frame.new() controls = [message: Kino.Input.text("New Message")] form = Kino.Control.form(controls, submit: "Send Message", reset_on_submit: [:message]) form |> Kino.Control.stream() |> Kino.listen(nil, fn %{data: %{message: message}}, _token_summary -> Kino.Frame.append(frame, Kino.Markdown.new(" **Me:** #{message}")) %{results: [%{text: text, token_summary: token_summary}]}= Nx.Serving.run(serving, %{text: message}) Kino.Frame.append(frame, Kino.Markdown.new(" **Bot:** #{text}")) {:cont, token_summary} end) Kino.Layout.grid([frame, form], gap: 16) ``` * * * ### Section Classifying Images In the first cell: defn\_options: [compiler: EXLA] gives an error, maybe because of use cuda120? So I removed it ```elixir {:ok, model_info} = Bumblebee.load_model({:hf, "google/vit-base-patch16-224"}) {:ok, featurizer} = Bumblebee.load_featurizer({:hf, "google/vit-base-patch16-224"}) serving = Bumblebee.Vision.image_classification(model_info, featurizer, top_k: 1, compile: [batch_size: 1] # defn_options: [compiler: EXLA] #gives error ) ``` The Kino part doesn’t work at all. Dragging the image removes all the Evalute/Reevaluate knobs Open camera and Upload work correct. But pushing the Run button gives an error. I could not repair that. So I replaced the Kino part by: * * * ```elixir image = "/home/piet/livebooks/ML_Elixir/Cat.jpg" |> StbImage.read_file!() |> StbImage.resize(224, 224) |> StbImage.to_nx() |> Nx.as_type({:u, 8}) output = Nx.Serving.run(serving, image) output.predictions |> Enum.map(&{&1.label, &1.score}) |> Kino.Bumblebee.ScoredList.new() ``` * * * ### Section Fine-tuning Pre-trained Models In the beginning training seemed to go well, although the accuracy after batch 861 was 0.0920101! And at that batch I got an error! The error after Epoch: 0, Batch: 861: ```elixir ** (MatchError) no match of right hand side value: ["\"2", "This must be the place that ..... ............ ..........."] (stdlib 5.1.1) erl_eval.erl:498: :erl_eval.expr/6 #cell:33sgnufmubmhq4l6:11: (file) #cell:33sgnufmubmhq4l6:10: (file) #cell:33sgnufmubmhq4l6:14: (file) ``` Probably there is some error in the Yelp zip file. I downloaded it twice but still an error. Also every adding to the output gave the annoying warning: ```elixir warning: passing options to Bumblebee.apply_tokenizer/3 is deprecated, please use Bumblebee. configure/2 to set tokenizer options (bumblebee 0.5.3) lib/bumblebee.ex:856: Bumblebee.apply_tokenizer/3 (elixir 1.15.7) src/elixir.erl:396: :elixir.eval_external_handler/3 (stdlib 5.1.1) erl_eval.erl:750: :erl_eval.do_apply/7 (stdlib 5.1.1) erl_eval.erl:494: :erl_eval.expr/6 (stdlib 5.1.1) erl_eval.erl:136: :erl_eval.exprs/6 (elixir 1.15.7) lib/stream.ex:613: anonymous fn/4 in Stream.map/2 ``` Since this is not the end version (I assume) and the dependencies are not right, the chapter, besides the first section, needs a rewrite. If it is necessary I can send you my livebook, But I don`t know how to attach. ---
**Author:** ![jshprentz](https://forum.devtalk.com/user_avatar/forum.devtalk.com/jshprentz/32/5389_2.png) [@jshprentz](https://forum.devtalk.com/u/jshprentz)\ **Post date:** [18 April 2024 23:31 UTC](https://forum.devtalk.com/t/machine-learning-in-elixir-comments-on-chapter-11-version-b-3-0/146857/2 "2024-04-18T23:31:13Z")
@seanmor5 As Piet reported, the code on page 260 fails at ```elixir image |> Nx.from_binary(:u8) ``` Based on the example at [Examples — Bumblebee v0.5.3](https://hexdocs.pm/bumblebee/examples.html#image-classification), I replaced the `image` line with this pipeline: ```elixir image.file_ref |> Kino.Input.file_path() |> File.read!() ``` Now the Run button successfully ingests the image, runs the model, and reports the top predictions. The `serving = ...` code on page 259 contained the option `top_k: 1`, so only one prediction is shown. After changing `1` to `5` and uploading the book’s cat image, the five predictions match those shown on page 261, albeit with different probabilities. Here is the complete modified code from page 260: ```elixir image_input = Kino.Input.image("Image", size: {224, 224}) form = Kino.Control.form([image: image_input], submit: "Run") frame = Kino.Frame.new() form |> Kino.Control.stream() |> Stream.filter(& &1.data.image) |> Kino.listen(fn %{data: %{image: image}} -> Kino.Frame.render(frame, Kino.Markdown.new("Running...")) image = image.file_ref |> Kino.Input.file_path() |> File.read!() |> Nx.from_binary(:u8) |> Nx.reshape({image.height, image.width, 3}) output = Nx.Serving.run(serving, image) output.predictions |> Enum.map(&{&1.label, &1.score}) |> Kino.Bumblebee.ScoredList.new() |> then(&Kino.Frame.render(frame, &1)) end) Kino.Layout.grid([form, frame], boxed: true, gap: 16) ```