Duplicate from fl399/matcha_chartqa

Co-authored-by: Fangyu Liu <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: MatCha ChartQA
+emoji: 📊
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+duplicated_from: fl399/matcha_chartqa
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
+import requests
+from PIL import Image
+import torch
+
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/20294671002019.png', 'chart_example.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/multi_col_1081.png', 'chart_example_2.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/18143564004789.png', 'chart_example_3.png')
+torch.hub.download_url_to_file('https://sharkcoder.com/files/article/matplotlib-bar-plot.png', 'chart_example_4.png')
+
+
+model_name = "google/matcha-chartqa"
+model = Pix2StructForConditionalGeneration.from_pretrained(model_name)
+processor = Pix2StructProcessor.from_pretrained(model_name)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def filter_output(output):
+    return output.replace("<0x0A>", "")
+
+def chart_qa(image, question):
+    inputs = processor(images=image, text=question, return_tensors="pt").to(device)
+    predictions = model.generate(**inputs, max_new_tokens=512)
+    return filter_output(processor.decode(predictions[0], skip_special_tokens=True))
+
+   
+image = gr.inputs.Image(type="pil", label="Chart")
+question = gr.inputs.Textbox(label="Question")
+answer = gr.outputs.Textbox(label="Model Output")
+examples = [["chart_example.png", "Which country has the second highest death rate?"],
+            ["chart_example_2.png", "What is the B2B sales in 2017?"],
+            ["chart_example_3.png", "Which country has the lowest CPA received across all times?"],
+            ["chart_example_4.png", "How much revenue did Furious 7 make?"]]
+
+title = "Interactive demo: Chart QA with MatCha🍵"
+description = "Gradio Demo for the [MatCha](https://arxiv.org/abs/2212.09662) model, fine-tuned on the [ChartQA](https://paperswithcode.com/dataset/chartqa) dataset. To use it, simply upload your image and click 'submit', or click one of the examples to load them. \n Quick links: [[paper]](https://arxiv.org/abs/2212.09662) [[google-ai blog]](https://ai.googleblog.com/2023/05/foundation-models-for-reasoning-on.html) [[code]](https://github.com/google-research/google-research/tree/master/deplot)"
+
+interface = gr.Interface(fn=chart_qa, 
+                         inputs=[image, question], 
+                         outputs=answer, 
+                         examples=examples, 
+                         title=title,
+                         description=description,
+                         theme='gradio/soft',
+                         enable_queue=True)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio==3.26.0
+torch
+git+https://github.com/huggingface/transformers