Total runs:
2.0K
Run Growth:
500
Growth Rate:
25.45%
Sponsored by
ThumbnailCreator.com
flax-community / t5-recipe-generation
Model's Last Updated: August 03 2023
text-generation
Introduction of t5-recipe-generation
Model Details of t5-recipe-generation
Chef Transformer (T5)
This is part of the Flax/Jax Community Week , organized by HuggingFace and TPU usage sponsored by Google.
Want to give it a try? Then what's the wait, head over to Hugging Face Spaces here .
Team Members
- Mehrdad Farahani ( m3hrdadfi )
- Kartik Godawat ( dk-crazydiv )
- Haswanth Aekula ( hassiahk )
- Deepak Pandian ( rays2pix )
- Nicholas Broad ( nbroad )
Dataset
RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation . This dataset contains 2,231,142 cooking recipes (>2 millions) with size of 2.14 GB . It's processed in more careful way.
Example
{
"NER": [
"oyster crackers",
"salad dressing",
"lemon pepper",
"dill weed",
"garlic powder",
"salad oil"
],
"directions": [
"Combine salad dressing mix and oil.",
"Add dill weed, garlic powder and lemon pepper.",
"Pour over crackers; stir to coat.",
"Place in warm oven.",
"Use very low temperature for 15 to 20 minutes."
],
"ingredients": [
"12 to 16 oz. plain oyster crackers",
"1 pkg. Hidden Valley Ranch salad dressing mix",
"1/4 tsp. lemon pepper",
"1/2 to 1 tsp. dill weed",
"1/4 tsp. garlic powder",
"3/4 to 1 c. salad oil"
],
"link": "www.cookbooks.com/Recipe-Details.aspx?id=648947",
"source": "Gathered",
"title": "Hidden Valley Ranch Oyster Crackers"
}
How To Use
# Installing requirements
pip install transformers
from transformers import FlaxAutoModelForSeq2SeqLM
from transformers import AutoTokenizer
MODEL_NAME_OR_PATH = "flax-community/t5-recipe-generation"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME_OR_PATH, use_fast=True)
model = FlaxAutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME_OR_PATH)
prefix = "items: "
# generation_kwargs = {
# "max_length": 512,
# "min_length": 64,
# "no_repeat_ngram_size": 3,
# "early_stopping": True,
# "num_beams": 5,
# "length_penalty": 1.5,
# }
generation_kwargs = {
"max_length": 512,
"min_length": 64,
"no_repeat_ngram_size": 3,
"do_sample": True,
"top_k": 60,
"top_p": 0.95
}
special_tokens = tokenizer.all_special_tokens
tokens_map = {
"<sep>": "--",
"<section>": "\n"
}
def skip_special_tokens(text, special_tokens):
for token in special_tokens:
text = text.replace(token, "")
return text
def target_postprocessing(texts, special_tokens):
if not isinstance(texts, list):
texts = [texts]
new_texts = []
for text in texts:
text = skip_special_tokens(text, special_tokens)
for k, v in tokens_map.items():
text = text.replace(k, v)
new_texts.append(text)
return new_texts
def generation_function(texts):
_inputs = texts if isinstance(texts, list) else [texts]
inputs = [prefix + inp for inp in _inputs]
inputs = tokenizer(
inputs,
max_length=256,
padding="max_length",
truncation=True,
return_tensors="jax"
)
input_ids = inputs.input_ids
attention_mask = inputs.attention_mask
output_ids = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
**generation_kwargs
)
generated = output_ids.sequences
generated_recipe = target_postprocessing(
tokenizer.batch_decode(generated, skip_special_tokens=False),
special_tokens
)
return generated_recipe
items = [
"macaroni, butter, salt, bacon, milk, flour, pepper, cream corn",
"provolone cheese, bacon, bread, ginger"
]
generated = generation_function(items)
for text in generated:
sections = text.split("\n")
for section in sections:
section = section.strip()
if section.startswith("title:"):
section = section.replace("title:", "")
headline = "TITLE"
elif section.startswith("ingredients:"):
section = section.replace("ingredients:", "")
headline = "INGREDIENTS"
elif section.startswith("directions:"):
section = section.replace("directions:", "")
headline = "DIRECTIONS"
if headline == "TITLE":
print(f"[{headline}]: {section.strip().capitalize()}")
else:
section_info = [f" - {i+1}: {info.strip().capitalize()}" for i, info in enumerate(section.split("--"))]
print(f"[{headline}]:")
print("\n".join(section_info))
print("-" * 130)
Output: ```text [TITLE]: Macaroni and corn [INGREDIENTS]: - 1: 2 c. macaroni - 2: 2 tbsp. butter - 3: 1 tsp. salt - 4: 4 slices bacon - 5: 2 c. milk - 6: 2 tbsp. flour - 7: 1/4 tsp. pepper - 8: 1 can cream corn [DIRECTIONS]: - 1: Cook macaroni in boiling salted water until tender. - 2: Drain. - 3: Melt butter in saucepan. - 4: Blend in flour, salt and pepper. - 5: Add milk all at once. - 6: Cook and stir until thickened and bubbly. - 7: Stir in corn and bacon. - 8: Pour over macaroni and mix well.
[TITLE]: Grilled provolone and bacon sandwich [INGREDIENTS]: - 1: 2 slices provolone cheese - 2: 2 slices bacon - 3: 2 slices sourdough bread - 4: 2 slices pickled ginger [DIRECTIONS]: - 1: Place a slice of provolone cheese on one slice of bread. - 2: Top with a slice of bacon. - 3: Top with a slice of pickled ginger. - 4: Top with the other slice of bread. - 5: Heat a skillet over medium heat. - 6: Place the sandwich in the skillet and cook until the cheese is melted and the bread is golden brown.
## Evaluation
Since the test set is not available, we will evaluate the model based on a shared test set. This test set consists of 5% of the whole test (*= 5,000 records*),
and we will generate five recipes for each input(*= 25,000 records*).
The following table summarizes the scores obtained by the **Chef Transformer** and **RecipeNLG** as our baseline.
| Model | COSIM | WER | ROUGE-2 | BLEU | GLEU | METEOR |
|:------------------------------------------------------------------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
| [RecipeNLG](https://huggingface.co/mbien/recipenlg) | 0.5723 | 1.2125 | 0.1354 | 0.1164 | 0.1503 | 0.2309 |
| [Chef Transformer](huggingface.co/flax-community/t5-recipe-generation) * | **0.7282** | **0.7613** | **0.2470** | **0.3245** | **0.2624** | **0.4150** |
*From the 5 generated recipes corresponding to each NER (food items), only the highest score was taken into account in the WER, COSIM, and ROUGE metrics. At the same time, BLEU, GLEU, Meteor were designed to have many possible references.*
## Copyright
Special thanks to those who provided these fantastic materials.
- [Anatomy](https://www.flaticon.com/free-icon)
- [Chef Hat](https://www.vecteezy.com/members/jellyfishwater)
- [Moira Nazzari](https://pixabay.com/photos/food-dessert-cake-eggs-butter-3048440/)
- [Instagram Post](https://www.freepik.com/free-psd/recipes-ad-social-media-post-template_11520617.htm)
Runs of flax-community t5-recipe-generation on huggingface.co
457
Total runs
0
24-hour runs
4
3-day runs
-26
7-day runs
139
30-day runs
More Information About t5-recipe-generation huggingface.co Model
Url of t5-recipe-generation
t5-recipe-generation huggingface.co Url
Provider of t5-recipe-generation huggingface.co
Other API from flax-community
Updated:November 28 2023
Total runs:
1.7K
Run Growth:
674
Growth Rate:
39.07%
Total runs:
1.3K
Run Growth:
813
Growth Rate:
63.37%
Total runs:
852
Run Growth:
-912
Growth Rate:
-108.83%
Total runs:
849
Run Growth:
-777
Growth Rate:
-89.83%
Total runs:
592
Run Growth:
-97
Growth Rate:
-16.41%
Total runs:
533
Run Growth:
458
Growth Rate:
89.63%
Total runs:
462
Run Growth:
149
Growth Rate:
32.39%
Total runs:
312
Run Growth:
122
Growth Rate:
41.36%
Total runs:
294
Run Growth:
-81
Growth Rate:
-27.65%
Total runs:
243
Run Growth:
80
Growth Rate:
32.00%
Total runs:
233
Run Growth:
79
Growth Rate:
32.64%
Total runs:
206
Run Growth:
40
Growth Rate:
18.87%
Total runs:
206
Run Growth:
72
Growth Rate:
34.45%
Total runs:
204
Run Growth:
71
Growth Rate:
37.17%
Total runs:
202
Run Growth:
60
Growth Rate:
28.85%
Total runs:
171
Run Growth:
58
Growth Rate:
33.53%
Total runs:
167
Run Growth:
32
Growth Rate:
19.16%
Total runs:
155
Run Growth:
71
Growth Rate:
45.51%
Total runs:
151
Run Growth:
57
Growth Rate:
38.78%
Total runs:
131
Run Growth:
-18
Growth Rate:
-13.33%
Total runs:
121
Run Growth:
52
Growth Rate:
42.28%
Total runs:
118
Run Growth:
-10
Growth Rate:
-8.06%
Total runs:
116
Run Growth:
64
Growth Rate:
63.37%
Total runs:
115
Run Growth:
59
Growth Rate:
47.97%
Total runs:
107
Run Growth:
43
Growth Rate:
38.39%
Total runs:
100
Run Growth:
-27
Growth Rate:
-26.73%
Total runs:
93
Run Growth:
37
Growth Rate:
38.95%
Total runs:
90
Run Growth:
27
Growth Rate:
25.96%
Total runs:
89
Run Growth:
65
Growth Rate:
73.86%
Total runs:
88
Run Growth:
54
Growth Rate:
61.36%
Total runs:
80
Run Growth:
9
Growth Rate:
10.98%
Total runs:
66
Run Growth:
40
Growth Rate:
57.14%
Total runs:
66
Run Growth:
19
Growth Rate:
30.16%
Total runs:
54
Run Growth:
19
Growth Rate:
34.55%
Total runs:
51
Run Growth:
26
Growth Rate:
50.98%
Total runs:
47
Run Growth:
15
Growth Rate:
31.91%
Total runs:
47
Run Growth:
-7
Growth Rate:
-14.00%
Total runs:
45
Run Growth:
24
Growth Rate:
57.14%
Total runs:
42
Run Growth:
0
Growth Rate:
0.00%
Total runs:
42
Run Growth:
18
Growth Rate:
42.86%
Total runs:
42
Run Growth:
15
Growth Rate:
35.71%
Total runs:
40
Run Growth:
11
Growth Rate:
28.21%
Total runs:
40
Run Growth:
11
Growth Rate:
27.50%
Total runs:
40
Run Growth:
18
Growth Rate:
45.00%
Total runs:
40
Run Growth:
22
Growth Rate:
55.00%
Total runs:
38
Run Growth:
15
Growth Rate:
40.54%
Total runs:
37
Run Growth:
17
Growth Rate:
45.95%
Total runs:
36
Run Growth:
9
Growth Rate:
24.32%
Total runs:
36
Run Growth:
11
Growth Rate:
31.43%
Total runs:
35
Run Growth:
7
Growth Rate:
20.00%
Total runs:
35
Run Growth:
13
Growth Rate:
37.14%
Total runs:
34
Run Growth:
14
Growth Rate:
41.18%
Total runs:
34
Run Growth:
14
Growth Rate:
41.18%
Total runs:
33
Run Growth:
11
Growth Rate:
33.33%
Total runs:
32
Run Growth:
16
Growth Rate:
50.00%
Total runs:
29
Run Growth:
-3
Growth Rate:
-10.34%
Total runs:
26
Run Growth:
10
Growth Rate:
38.46%
Total runs:
26
Run Growth:
-34
Growth Rate:
-125.93%
Total runs:
25
Run Growth:
5
Growth Rate:
20.00%
Total runs:
25
Run Growth:
2
Growth Rate:
8.00%
Total runs:
24
Run Growth:
5
Growth Rate:
20.83%
Total runs:
24
Run Growth:
4
Growth Rate:
17.39%
Total runs:
23
Run Growth:
16
Growth Rate:
69.57%
Total runs:
23
Run Growth:
8
Growth Rate:
34.78%
Total runs:
22
Run Growth:
2
Growth Rate:
9.09%
Total runs:
22
Run Growth:
8
Growth Rate:
36.36%
Total runs:
21
Run Growth:
3
Growth Rate:
15.00%
Total runs:
21
Run Growth:
1
Growth Rate:
4.76%
Total runs:
20
Run Growth:
8
Growth Rate:
44.44%
Total runs:
20
Run Growth:
4
Growth Rate:
21.05%
Total runs:
19
Run Growth:
-1
Growth Rate:
-5.56%
Total runs:
19
Run Growth:
7
Growth Rate:
36.84%
Total runs:
19
Run Growth:
-1
Growth Rate:
-5.26%
Total runs:
19
Run Growth:
8
Growth Rate:
42.11%
Total runs:
19
Run Growth:
8
Growth Rate:
42.11%
Total runs:
18
Run Growth:
-1
Growth Rate:
-5.56%
Total runs:
18
Run Growth:
3
Growth Rate:
17.65%
Total runs:
17
Run Growth:
0
Growth Rate:
0.00%
Total runs:
17
Run Growth:
-1
Growth Rate:
-5.56%
Total runs:
15
Run Growth:
5
Growth Rate:
33.33%
Total runs:
14
Run Growth:
-3
Growth Rate:
-21.43%
Total runs:
14
Run Growth:
0
Growth Rate:
0.00%
Total runs:
13
Run Growth:
-4
Growth Rate:
-30.77%
Total runs:
12
Run Growth:
-10
Growth Rate:
-83.33%