Update examples

VikParuchuri · Jan 24, 2025 · 989c697 · 989c697
1 parent 7ab4e92
commit 989c697
Show file tree

Hide file tree

Showing 40 changed files with 310 additions and 309 deletions.
diff --git a/README.md b/README.md
@@ -3,9 +3,9 @@
 Marker converts PDFs and images to markdown, JSON, and HTML quickly and accurately.
 
 - Supports a range of documents in all languages
-- Removes headers/footers/other artifacts
-- Formats tables, forms, equations, links, and code blocks
+- Formats tables, forms, equations, links, references, and code blocks
 - Extracts and saves images along with the markdown
+- Removes headers/footers/other artifacts
 - Easily extensible with your own formatting and logic
 - Optionally boost accuracy with an LLM
 - Works on GPU, CPU, or MPS
@@ -16,7 +16,7 @@ Marker is a pipeline of deep learning models:
 
 - Extract text, OCR if necessary (heuristics, [surya](https://github.com/VikParuchuri/surya))
 - Detect page layout and find reading order ([surya](https://github.com/VikParuchuri/surya))
-- Clean and format each block (heuristics, [texify](https://github.com/VikParuchuri/texify). [tabled](https://github.com/VikParuchuri/tabled))
+- Clean and format each block (heuristics, [texify](https://github.com/VikParuchuri/texify), [surya](https://github.com/VikParuchuri/surya))
 - Optionally use an LLM to improve quality
 - Combine blocks and postprocess complete text
 

diff --git a/data/examples/markdown/multicolcnn/multicolcnn.md b/data/examples/markdown/multicolcnn/multicolcnn.md
@@ -123,9 +123,9 @@ Without perspective maps, we generate label density maps for this dataset in the
 
 When perspective maps are used, however, we follow the procedure as described in [\[27\]](#page-8-7), which involves estimating a "crowd density distribution kernel" as the sum of two 2D Gaussians: a symmetric Gaussian for the head and an ellipsoid Gaussian for the body. These are scaled by the perspective map M provided, where M(x) gives the number of pixels that represents a meter at pixel x [\[27\]](#page-8-7). Note that the meaning of this perspective map is distinct from the meaning of the perspective map provided for the UCSD dataset. Using this information, the density contribution from a person with head pixel x is given by the following sum of normalized Gaussians:
 
-$$D_{\bf x} = \frac{1}{||Z||} \left( \mathcal{N}_h(\bf x, \sigma_h) + \mathcal{N}_b(\bf x_b, \Sigma_b) \right) \tag{5}$$
+$$D_{\bf x}=\frac{1}{||Z||}\left(\mathcal{N}_{h}(\bf x,\sigma_{h}) + \mathcal{N}_{b}(\bf x_{b},\Sigma_{b})\right)\tag{5}$$
 
-where $x_b$ is the center of the body, which is 0.875 meters down from the head on average, and can be determined from the perspective map $M$ and the head center x [27]. We sum these Gaussians for each person to pro-
+where $x_b$ is the center of the body, which is 0.875 meters down from the head on average, and can be determined from the perspective map $M$ and the head center x [27]. We sum these Gaussians for each person to produce
 
 | Method       | MAE    |
 |--------------|--------|
@@ -156,12 +156,12 @@ Our network performs very well on the TRANCOS dataset. Indeed, as confirmed by t
 
 Results are shown in Table [3](#page-6-0) and Figure [3.](#page-6-1) We see that the "original" split as defined by the creators of the dataset in [\[5\]](#page-8-17) and used in [\[28\]](#page-9-0) gives us somewhat worse results for counting on this dataset. Results were consistent over multiple trainings. Again, including the perspective map does not seem to increase performance on this dataset. Despite this, we see in Table [3](#page-6-0) and Figure [3](#page-6-1) that the results are comparable to the state of the art. In fact, for two of the splits, our proposed network beats the state of the art. For the upscale split, the AMDCN is the state of the art by a large relative margin. This is compelling because it shows that accurate perspective-free counting can be achieved without
 
-| Method                            | GAME(L=0) | GAME(L=1)  | GAME(L=2)  | GAME(L=3)  |
-|-----------------------------------|-----------|------------|------------|------------|
-| AMDCN[18]                         | 9.7710.99 | 13.1613.75 | 15.0016.69 | 15.8719.32 |
-| [15] + SIFTfrom [14]              | 13.76     | 16.72      | 20.72      | 24.36      |
-| [13] + RGBNorm + Filtersfrom [14] | 17.68     | 19.97      | 23.54      | 25.84      |
-| HOG-2from [14]                    | 13.29     | 18.05      | 23.65      | 28.41      |
+| Method                                      | GAME<br/>(L=0) | GAME<br/>(L=1)  | GAME<br/>(L=2)  | GAME<br/>(L=3)  |
+|---------------------------------------------|----------------|-----------------|-----------------|-----------------|
+| AMDCN<br/>[18]                              | 9.77<br/>10.99 | 13.16<br/>13.75 | 15.00<br/>16.69 | 15.87<br/>19.32 |
+| [15] + SIFT<br/>from [14]                   | 13.76          | 16.72           | 20.72           | 24.36           |
+| [13] + RGB<br/>Norm + Filters<br/>from [14] | 17.68          | 19.97           | 23.54           | 25.84           |
+| HOG-2<br/>from [14]                         | 13.29          | 18.05           | 23.65           | 28.41           |
 
 <span id="page-5-2"/>Table 2. Mean absolute error of various methods on TRANCOS traffic
 

diff --git a/data/examples/markdown/multicolcnn/multicolcnn_meta.json b/data/examples/markdown/multicolcnn/multicolcnn_meta.json
@@ -712,7 +712,7 @@
       "block_metadata": {
         "llm_request_count": 9,
         "llm_error_count": 1,
-        "llm_tokens_used": 8870
+        "llm_tokens_used": 8867
       }
     },
     {
@@ -763,7 +763,7 @@
       "block_metadata": {
         "llm_request_count": 3,
         "llm_error_count": 0,
-        "llm_tokens_used": 3037
+        "llm_tokens_used": 3041
       }
     },
     {

diff --git a/data/examples/markdown/thinkpython/_page_109_Figure_1.png b/data/examples/markdown/thinkpython/_page_109_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_116_Figure_1.jpeg b/data/examples/markdown/thinkpython/_page_116_Figure_1.jpeg
diff --git a/data/examples/markdown/thinkpython/_page_116_Figure_1.png b/data/examples/markdown/thinkpython/_page_116_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_116_Figure_3.png b/data/examples/markdown/thinkpython/_page_116_Figure_3.png
diff --git a/data/examples/markdown/thinkpython/_page_127_Figure_1.png b/data/examples/markdown/thinkpython/_page_127_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_128_Figure_1.png b/data/examples/markdown/thinkpython/_page_128_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_165_Figure_1.jpeg b/data/examples/markdown/thinkpython/_page_165_Figure_1.jpeg
diff --git a/data/examples/markdown/thinkpython/_page_165_Figure_1.png b/data/examples/markdown/thinkpython/_page_165_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_167_Figure_1.png b/data/examples/markdown/thinkpython/_page_167_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_169_Figure_1.png b/data/examples/markdown/thinkpython/_page_169_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_190_Figure_1.png b/data/examples/markdown/thinkpython/_page_190_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_195_Figure_1.png b/data/examples/markdown/thinkpython/_page_195_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_205_Figure_1.png b/data/examples/markdown/thinkpython/_page_205_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_230_Figure_1.png b/data/examples/markdown/thinkpython/_page_230_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_233_Figure_1.png b/data/examples/markdown/thinkpython/_page_233_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_233_Figure_3.png b/data/examples/markdown/thinkpython/_page_233_Figure_3.png
diff --git a/data/examples/markdown/thinkpython/_page_234_Figure_1.png b/data/examples/markdown/thinkpython/_page_234_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_235_Figure_1.png b/data/examples/markdown/thinkpython/_page_235_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_236_Figure_1.png b/data/examples/markdown/thinkpython/_page_236_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_236_Figure_3.png b/data/examples/markdown/thinkpython/_page_236_Figure_3.png
diff --git a/data/examples/markdown/thinkpython/_page_237_Figure_1.png b/data/examples/markdown/thinkpython/_page_237_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_238_Figure_1.png b/data/examples/markdown/thinkpython/_page_238_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_23_Figure_1.png b/data/examples/markdown/thinkpython/_page_23_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_23_Figure_3.png b/data/examples/markdown/thinkpython/_page_23_Figure_3.png
diff --git a/data/examples/markdown/thinkpython/_page_33_Figure_1.jpeg b/data/examples/markdown/thinkpython/_page_33_Figure_1.jpeg
diff --git a/data/examples/markdown/thinkpython/_page_33_Figure_1.png b/data/examples/markdown/thinkpython/_page_33_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_46_Figure_1.png b/data/examples/markdown/thinkpython/_page_46_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_60_Figure_1.png b/data/examples/markdown/thinkpython/_page_60_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_60_Figure_3.png b/data/examples/markdown/thinkpython/_page_60_Figure_3.png
diff --git a/data/examples/markdown/thinkpython/_page_67_Figure_1.png b/data/examples/markdown/thinkpython/_page_67_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_71_Figure_1.png b/data/examples/markdown/thinkpython/_page_71_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_78_Figure_1.png b/data/examples/markdown/thinkpython/_page_78_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_85_Figure_1.png b/data/examples/markdown/thinkpython/_page_85_Figure_1.png
diff --git a/data/examples/markdown/thinkpython/_page_99_Figure_1.jpeg b/data/examples/markdown/thinkpython/_page_99_Figure_1.jpeg
diff --git a/data/examples/markdown/thinkpython/_page_99_Figure_1.png b/data/examples/markdown/thinkpython/_page_99_Figure_1.png