This repository was archived by the owner on Jan 24, 2024. It is now read-only.
[High-Level-API] Rewrite Chapter 5 Personalized Recommendation in Book to use new Flui…#526
Merged
nickyfantasy merged 4 commits intoPaddlePaddle:high-level-api-branchfrom Jun 5, 2018
Conversation
daming-lu
reviewed
May 31, 2018
05.recommender_system/README.md
Outdated
| First, we must import and initialize PaddlePaddle (enable/disable GPU, set the number of trainers, etc). | ||
| ## Model Configuration | ||
|
|
||
| Our program starts with importing necessary packages and initializes some global variables: |
Contributor
There was a problem hiding this comment.
starts with importing necessary packages and initializing
05.recommender_system/README.md
Outdated
| ``` | ||
|
|
||
| Movie title, a sequence of words represented by an integer word index sequence, will be feed into a `sequence_conv_pool` layer, which will apply convolution and pooling on time dimension. Because pooling is done on time dimension, the output will be a fixed-length vector regardless the length of the input sequence. | ||
| Movie title, which is a sequence of words represented by an integer word index sequence, will be feed into a `sequence_conv_pool` layer, which will apply convolution and pooling on time dimension. Because pooling is done on time dimension, the output will be a fixed-length vector regardless the length of the input sequence. |
05.recommender_system/README.md
Outdated
|
|
||
|
|
||
| Finally, we can use cosine similarity to calculate the similarity between user characteristics and movie features. | ||
| Finally, we can define a `inference_program` that use cosine similarity to calculate the similarity between user characteristics and movie features. |
Contributor
There was a problem hiding this comment.
an inference_program that uses
05.recommender_system/README.md
Outdated
|
|
||
| Before jumping into creating a training module, algorithm setting is also necessary. Here we specified Adam optimization algorithm via `paddle.optimizer`. | ||
| Next we define data feeders for test and train. The feeder reads a `BATCH_SIZE` of data each time and feed them to the training/testing process. | ||
| `paddle.dataset.movielens.train` will yield records during each pass, after shuffling, a batch input of `buf_size` is generated for training. |
Contributor
There was a problem hiding this comment.
the sentence is not clear. Plus, buf_size is larger than BATCH_SIZE. I think the logic is reversed...
05.recommender_system/README.md
Outdated
| ### Create Trainer | ||
|
|
||
| `paddle.dataset.movielens.train` will yield records during each pass, after shuffling, a batch input is generated for training. | ||
| Create a trainer that takes `train_program` as input and specifies optimizer. |
05.recommender_system/README.md
Outdated
| if step % 100 == 0: # every 100 batches, update cost plot | ||
| cost_ploter.plot() | ||
| Use create_lod_tensor(data, lod, place) API to generate LoD Tensor, where `data` is a list of sequences of index numbers, `lod` is the level of detail (lod) info associated with `data`. | ||
| For example, data = [[10, 2, 3], [2, 3]] means that it contains two sequences of indexes, of length 3 and 2, respectively. |
05.recommender_system/README.md
Outdated
| Finally, we can invoke `trainer.train` to start training: | ||
| ### Infer | ||
|
|
||
| Now we can infer with inputs that matched with the yield records that we provide in `feed_order` during training. |
Contributor
There was a problem hiding this comment.
This sentence is not clear. Maybe break it into two?
jetfuel
reviewed
May 31, 2018
|
|
||
| We use the [MovieLens ml-1m](http://files.grouplens.org/datasets/movielens/ml-1m.zip) to train our model. This dataset includes 10,000 ratings of 4,000 movies from 6,000 users to 4,000 movies. Each rate is in the range of 1~5. Thanks to GroupLens Research for collecting, processing and publishing the dataset. | ||
|
|
||
| `paddle.v2.datasets` package encapsulates multiple public datasets, including `cifar`, `imdb`, `mnist`, `moivelens` and `wmt14`, etc. There's no need for us to manually download and preprocess `MovieLens` dataset. |
Contributor
There was a problem hiding this comment.
I told Nicki the same. He really has a keen sight 👀
| ``` | ||
|
|
||
| Finally, we can invoke `trainer.train` to start training: | ||
| ### Infer |
jetfuel
changed the title
daming-lu
approved these changes
Jun 5, 2018
| }, | ||
| return_numpy=False) | ||
|
|
||
| print("infer results: ", np.array(results[0])) |
Contributor
There was a problem hiding this comment.
Can we show a comparison between prediction and the real data? For example, user 23::M::35::0::90049 rated movie 2278::Ronin (1998)::Action|Crime|Thriller a 4.0 score. Our prediction is 3.458
Contributor
There was a problem hiding this comment.
Good suggestion, i think it would be helpful
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…d API
I will add plot in next PR