initial commit

AUTHORS.rst

@@ -0,0 +1,13 @@
+=======
+Credits
+=======
+
+Development Lead
+----------------
+
+* Full name of the author <Email of the author>
+
+Contributors
+------------
+
+None yet. Why not be the first?

README.md

@@ -1,13 +1,23 @@
 ---
-title: Table Caption Extraction
-emoji: 🌖
-colorFrom: indigo
-colorTo: pink
+title: Table Extraction (Table Transformer + PaddleOCR)
+emoji: 🚀
+colorFrom: blue
+colorTo: yellow
 sdk: streamlit
-sdk_version: 1.31.1
+sdk_version: 1.21.0
 app_file: app.py
 pinned: false
-license: mit
 ---
+# huggingface-space
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Imported from https://huggingface.co/spaces/jurgendn/table-extraction with some adjustment.
+
+Current pipeline:
+
+Table detection: https://huggingface.co/microsoft/table-transformer-detection
+
+Table recognition: https://huggingface.co/microsoft/table-transformer-structure-recognition
+
+OCR: https://github.com/pbcquoc/vietocr
+
+OCR-new: https://github.com/PaddlePaddle/PaddleOCR

app.py

@@ -0,0 +1,740 @@
+import asyncio
+import string
+import random
+from collections import Counter
+from itertools import count, tee
+import base64
+
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import streamlit as st
+import torch
+from PIL import Image
+from transformers import DetrImageProcessor, TableTransformerForObjectDetection
+from paddleocr import PaddleOCR
+
+ocr = PaddleOCR(use_angle_cls=True, lang="en", use_gpu=False, ocr_version='PP-OCRv3')
+
+st.set_option('deprecation.showPyplotGlobalUse', False)
+st.set_page_config(layout='wide')
+st.title("Table Detection and Table Structure Recognition")
+st.write(
+    "Implemented by MSFT team: https://github.com/microsoft/table-transformer")
+
+table_detection_model = TableTransformerForObjectDetection.from_pretrained(
+    "microsoft/table-transformer-detection")
+
+table_recognition_model = TableTransformerForObjectDetection.from_pretrained(
+    "microsoft/table-transformer-structure-recognition")
+
+def reload_ocr(vlang):
+    global ocr 
+    ocr = PaddleOCR(use_angle_cls=True, lang=vlang, use_gpu=False, ocr_version='PP-OCRv4')
+
+
+def PIL_to_cv(pil_img):
+    return cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
+
+
+def cv_to_PIL(cv_img):
+    return Image.fromarray(cv2.cvtColor(cv_img, cv2.COLOR_BGR2RGB))
+
+
+async def pytess(cell_pil_img, threshold: float = 0.5):
+    cell_pil_img = TableExtractionPipeline.add_padding(pil_img=cell_pil_img, top=20, right=10, bottom=20, left=10, color=(255, 255, 255))
+    result = ocr.ocr(np.asarray(cell_pil_img), cls=True)[0]
+    
+    #Debug
+    # filename = str(random.random())
+    # cell_pil_img.save("dump/" + filename + ".png")
+    # print(filename)
+    # print(result)
+    
+    text = ""
+    if result != None:
+        txts = [line[1][0] for line in result]
+        text = " ".join(txts)
+    return text
+
+
+def sharpen_image(pil_img):
+
+    img = PIL_to_cv(pil_img)
+    sharpen_kernel = np.array([[-1, -1, -1], [-1, 9, -1], [-1, -1, -1]])
+
+    sharpen = cv2.filter2D(img, -1, sharpen_kernel)
+    pil_img = cv_to_PIL(sharpen)
+    return pil_img
+
+
+def uniquify(seq, suffs=count(1)):
+    """Make all the items unique by adding a suffix (1, 2, etc).
+    Credit: https://stackoverflow.com/questions/30650474/python-rename-duplicates-in-list-with-progressive-numbers-without-sorting-list
+    `seq` is mutable sequence of strings.
+    `suffs` is an optional alternative suffix iterable.
+    """
+    not_unique = [k for k, v in Counter(seq).items() if v > 1]
+
+    suff_gens = dict(zip(not_unique, tee(suffs, len(not_unique))))
+    for idx, s in enumerate(seq):
+        try:
+            suffix = str(next(suff_gens[s]))
+        except KeyError:
+            continue
+        else:
+            seq[idx] += suffix
+
+    return seq
+
+
+def binarizeBlur_image(pil_img):
+    image = PIL_to_cv(pil_img)
+    thresh = cv2.threshold(image, 150, 255, cv2.THRESH_BINARY_INV)[1]
+
+    result = cv2.GaussianBlur(thresh, (5, 5), 0)
+    result = 255 - result
+    return cv_to_PIL(result)
+
+
+def td_postprocess(pil_img):
+    '''
+    Removes gray background from tables
+    '''
+    img = PIL_to_cv(pil_img)
+
+    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+    mask = cv2.inRange(hsv, (0, 0, 100),
+                       (255, 5, 255))  # (0, 0, 100), (255, 5, 255)
+    nzmask = cv2.inRange(hsv, (0, 0, 5),
+                         (255, 255, 255))  # (0, 0, 5), (255, 255, 255))
+    nzmask = cv2.erode(nzmask, np.ones((3, 3)))  # (3,3)
+    mask = mask & nzmask
+
+    new_img = img.copy()
+    new_img[np.where(mask)] = 255
+
+    return cv_to_PIL(new_img)
+
+
+# def super_res(pil_img):
+#     # requires opencv-contrib-python installed without the opencv-python
+#     sr = dnn_superres.DnnSuperResImpl_create()
+#     image = PIL_to_cv(pil_img)
+#     model_path = "./LapSRN_x8.pb"
+#     model_name = model_path.split('/')[1].split('_')[0].lower()
+#     model_scale = int(model_path.split('/')[1].split('_')[1].split('.')[0][1])
+
+#     sr.readModel(model_path)
+#     sr.setModel(model_name, model_scale)
+#     final_img = sr.upsample(image)
+#     final_img = cv_to_PIL(final_img)
+
+#     return final_img
+
+
+def table_detector(image, THRESHOLD_PROBA):
+    '''
+    Table detection using DEtect-object TRansformer pre-trained on 1 million tables
+
+    '''
+
+    feature_extractor = DetrImageProcessor(do_resize=True,
+                                           size=800,
+                                           max_size=800)
+    encoding = feature_extractor(image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = table_detection_model(**encoding)
+
+    probas = outputs.logits.softmax(-1)[0, :, :-1]
+    keep = probas.max(-1).values > THRESHOLD_PROBA
+
+    target_sizes = torch.tensor(image.size[::-1]).unsqueeze(0)
+    postprocessed_outputs = feature_extractor.post_process(
+        outputs, target_sizes)
+    bboxes_scaled = postprocessed_outputs[0]['boxes'][keep]
+
+    return (probas[keep], bboxes_scaled)
+
+
+def table_struct_recog(image, THRESHOLD_PROBA):
+    '''
+    Table structure recognition using DEtect-object TRansformer pre-trained on 1 million tables
+    '''
+
+    feature_extractor = DetrImageProcessor(do_resize=True,
+                                           size=1000,
+                                           max_size=1000)
+    encoding = feature_extractor(image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = table_recognition_model(**encoding)
+
+    probas = outputs.logits.softmax(-1)[0, :, :-1]
+    keep = probas.max(-1).values > THRESHOLD_PROBA
+
+    target_sizes = torch.tensor(image.size[::-1]).unsqueeze(0)
+    postprocessed_outputs = feature_extractor.post_process(
+        outputs, target_sizes)
+    bboxes_scaled = postprocessed_outputs[0]['boxes'][keep]
+
+    return (probas[keep], bboxes_scaled)
+
+
+class TableExtractionPipeline():
+
+    colors = ["red", "blue", "green", "yellow", "orange", "violet"]
+
+    # colors = ["red", "blue", "green", "red", "red", "red"]
+
+    @staticmethod
+    def add_padding(pil_img,
+                    top,
+                    right,
+                    bottom,
+                    left,
+                    color=(255, 255, 255)):
+        '''
+        Image padding as part of TSR pre-processing to prevent missing table edges
+        '''
+        width, height = pil_img.size
+        new_width = width + right + left
+        new_height = height + top + bottom
+        result = Image.new(pil_img.mode, (new_width, new_height), color)
+        result.paste(pil_img, (left, top))
+        return result
+
+    @staticmethod
+    def dynamic_delta(xmin, ymin, xmax, ymax, delta_xmin, delta_ymin, delta_xmax, delta_ymax, pil_img):
+        offset_x = (xmax - xmin) * 0.05
+        offset_y = (ymax - ymin) * 0.05
+
+        w_img, h_img = pil_img.size
+
+        doxmin = xmin - (delta_xmin + offset_x) 
+        if (doxmin < 0):
+            doxmin = 0
+
+        doymin = ymin - (delta_ymin + offset_y)
+        if (doymin < 0):
+            doymin = 0
+
+        doxmax = xmax + (delta_xmax + offset_x)
+        if (doxmax > w_img):
+            doxmax = w_img
+
+        doymax = ymax + (delta_ymax + offset_y)
+        if (doymax > h_img):
+            doymax = h_img
+
+
+        return doxmin, doymin, doxmax, doymax
+    
+    @staticmethod
+    def get_cxy(pil_img, xmin, ymin, xmax, ymax, offset):
+        '''
+        get the possible position of table caption
+        '''
+        w_img, h_img = pil_img.size
+        c_xmin = xmin
+        c_xmax = xmax
+        
+        delta_x = xmax - xmin
+        
+        if delta_x / w_img > 0.5: # full page
+            c_xmin = 0
+            c_xmax = w_img
+        else:
+            cx_dist = c_xmax-c_xmin
+            delta_dist = w_img * 0.4 #0.4 is from 0.5 assumed that paper has padding around 0.1 of total width. In assumption that the paper is 2 column
+            print("cx_dist: " + str(cx_dist))
+            print("delta_dist: " + str(delta_dist))
+            if cx_dist < delta_dist:
+                d_off = int((delta_dist - cx_dist) / 2)
+                print("d_off: " + str(d_off))
+                c_xmin = c_xmin - d_off
+                if c_xmin < 0:
+                    c_xmin = 0
+                c_xmax = c_xmax + d_off
+                if c_xmax > w_img:
+                    c_xmax = w_img
+
+
+        if offset < 0:
+            c_ymin = ymin + offset
+            c_ymax = ymin
+            if c_ymin < 0:
+                c_ymin = 0
+        else:
+            c_ymin = ymax
+            c_ymax = ymax + offset
+            if c_ymax > h_img:
+                c_ymax = h_img
+
+        return c_xmin, c_ymin, c_xmax, c_ymax
+
+    def plot_results_detection(self, c1, model, pil_img, prob, boxes,
+                               delta_xmin, delta_ymin, delta_xmax, delta_ymax):
+        '''
+        crop_tables and plot_results_detection must have same co-ord shifts because 1 only plots the other one updates co-ordinates 
+        '''
+        # st.write('img_obj')
+        # st.write(pil_img)
+        plt.imshow(pil_img)
+        ax = plt.gca()
+
+        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):
+            cl = p.argmax()
+            xmin, ymin, xmax, ymax = self.dynamic_delta(xmin, ymin, xmax, ymax, delta_xmin, delta_ymin, delta_xmax, delta_ymax, pil_img)
+            ax.add_patch(
+                plt.Rectangle((xmin, ymin),
+                              xmax - xmin,
+                              ymax - ymin,
+                              fill=False,
+                              color='red',
+                              linewidth=3))
+            text = f'{model.config.id2label[cl.item()]}: {p[cl]:0.2f}'
+            ax.text(xmin - 20,
+                    ymin - 50,
+                    text,
+                    fontsize=10,
+                    bbox=dict(facecolor='yellow', alpha=0.5))
+
+            # Caption possibility (bottom)
+            offset = 200
+            c_xmin, c_ymin, c_xmax, c_ymax = self.get_cxy(pil_img, xmin, ymin, xmax, ymax, offset)
+
+            ax.add_patch(
+                plt.Rectangle((c_xmin, c_ymin),
+                              c_xmax - c_xmin,
+                              c_ymax - c_ymin,
+                              fill=False,
+                              color='blue',
+                              linewidth=1))
+            
+            # Caption possibility (top)
+            offset = -200
+            c_xmin, c_ymin, c_xmax, c_ymax = self.get_cxy(pil_img, xmin, ymin, xmax, ymax, offset)
+
+            ax.add_patch(
+                plt.Rectangle((c_xmin, c_ymin),
+                              c_xmax - c_xmin,
+                              c_ymax - c_ymin,
+                              fill=False,
+                              color='green',
+                              linewidth=1))
+
+        plt.axis('off')
+        c1.pyplot()
+
+    def crop_tables(self, pil_img, prob, boxes, delta_xmin, delta_ymin,
+                    delta_xmax, delta_ymax):
+        '''
+        crop_tables and plot_results_detection must have same co-ord shifts because 1 only plots the other one updates co-ordinates 
+        '''
+        cropped_img_list = []
+
+        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):
+            xmin, ymin, xmax, ymax = self.dynamic_delta(xmin, ymin, xmax, ymax, delta_xmin, delta_ymin, delta_xmax, delta_ymax, pil_img)
+            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
+            cropped_img_list.append(cropped_img)
+
+        return cropped_img_list
+    
+    def crop_caption(self, pil_img, prob, boxes, delta_xmin, delta_ymin,
+                    delta_xmax, delta_ymax):
+        '''
+        crop_tables and plot_results_detection must have same co-ord shifts because 1 only plots the other one updates co-ordinates 
+        '''
+        
+        cropped_caption_list = []
+
+        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):
+            xmin, ymin, xmax, ymax = self.dynamic_delta(xmin, ymin, xmax, ymax, delta_xmin, delta_ymin, delta_xmax, delta_ymax, pil_img)
+            
+            # Caption possibility (top)
+            offset = -200
+            c_xmin, c_ymin, c_xmax, c_ymax = self.get_cxy(pil_img, xmin, ymin, xmax, ymax, offset)
+            cropped_caption = pil_img.crop((c_xmin, c_ymin, c_xmax, c_ymax))
+            cropped_caption_list.append(cropped_caption)
+
+            # Caption possibility (bottom)
+            offset = 200
+            c_xmin, c_ymin, c_xmax, c_ymax = self.get_cxy(pil_img, xmin, ymin, xmax, ymax, offset)
+            cropped_caption = pil_img.crop((c_xmin, c_ymin, c_xmax, c_ymax))
+            cropped_caption_list.append(cropped_caption)
+
+        return cropped_caption_list
+
+    def generate_structure(self, c2, model, pil_img, prob, boxes,
+                           expand_rowcol_bbox_top, expand_rowcol_bbox_bottom):
+        '''
+        Co-ordinates are adjusted here by 3 'pixels'
+        To plot table pillow image and the TSR bounding boxes on the table
+        '''
+        # st.write('img_obj')
+        # st.write(pil_img)
+        plt.figure(figsize=(32, 20))
+        plt.imshow(pil_img)
+        ax = plt.gca()
+        rows = {}
+        cols = {}
+        idx = 0
+
+        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):
+
+            xmin, ymin, xmax, ymax = xmin, ymin, xmax, ymax
+            cl = p.argmax()
+            class_text = model.config.id2label[cl.item()]
+            text = f'{class_text}: {p[cl]:0.2f}'
+            # or (class_text == 'table column')
+            if (class_text
+                    == 'table row') or (class_text
+                                        == 'table projected row header') or (
+                                            class_text == 'table column'):
+                ax.add_patch(
+                    plt.Rectangle((xmin, ymin),
+                                  xmax - xmin,
+                                  ymax - ymin,
+                                  fill=False,
+                                  color=self.colors[cl.item()],
+                                  linewidth=2))
+                ax.text(xmin - 10,
+                        ymin - 10,
+                        text,
+                        fontsize=5,
+                        bbox=dict(facecolor='yellow', alpha=0.5))
+
+            if class_text == 'table row':
+                rows['table row.' +
+                     str(idx)] = (xmin, ymin - expand_rowcol_bbox_top, xmax,
+                                  ymax + expand_rowcol_bbox_bottom)
+            if class_text == 'table column':
+                cols['table column.' +
+                     str(idx)] = (xmin, ymin - expand_rowcol_bbox_top, xmax,
+                                  ymax + expand_rowcol_bbox_bottom)
+
+            idx += 1
+
+        plt.axis('on')
+        c2.pyplot()
+        return rows, cols
+
+    def sort_table_featuresv2(self, rows: dict, cols: dict):
+        # Sometimes the header and first row overlap, and we need the header bbox not to have first row's bbox inside the headers bbox
+        rows_ = {
+            table_feature: (xmin, ymin, xmax, ymax)
+            for table_feature, (
+                xmin, ymin, xmax,
+                ymax) in sorted(rows.items(), key=lambda tup: tup[1][1])
+        }
+        cols_ = {
+            table_feature: (xmin, ymin, xmax, ymax)
+            for table_feature, (
+                xmin, ymin, xmax,
+                ymax) in sorted(cols.items(), key=lambda tup: tup[1][0])
+        }
+
+        return rows_, cols_
+
+    def individual_table_featuresv2(self, pil_img, rows: dict, cols: dict):
+
+        for k, v in rows.items():
+            xmin, ymin, xmax, ymax = v
+            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
+            rows[k] = xmin, ymin, xmax, ymax, cropped_img
+
+        for k, v in cols.items():
+            xmin, ymin, xmax, ymax = v
+            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
+            cols[k] = xmin, ymin, xmax, ymax, cropped_img
+
+        return rows, cols
+
+    def object_to_cellsv2(self, master_row: dict, cols: dict,
+                          expand_rowcol_bbox_top, expand_rowcol_bbox_bottom,
+                          padd_left):
+        '''Removes redundant bbox for rows&columns and divides each row into cells from columns
+        Args:
+
+        Returns:
+
+        
+        '''
+        cells_img = {}
+        header_idx = 0
+        row_idx = 0
+        previous_xmax_col = 0
+        new_cols = {}
+        new_master_row = {}
+        previous_ymin_row = 0
+        new_cols = cols
+        new_master_row = master_row
+        ## Below 2 for loops remove redundant bounding boxes ###
+        # for k_col, v_col in cols.items():
+        #     xmin_col, _, xmax_col, _, col_img = v_col
+        #     if (np.isclose(previous_xmax_col, xmax_col, atol=5)) or (xmin_col >= xmax_col):
+        #         print('Found a column with double bbox')
+        #         continue
+        #     previous_xmax_col = xmax_col
+        #     new_cols[k_col] = v_col
+
+        # for k_row, v_row in master_row.items():
+        #     _, ymin_row, _, ymax_row, row_img = v_row
+        #     if (np.isclose(previous_ymin_row, ymin_row, atol=5)) or (ymin_row >= ymax_row):
+        #         print('Found a row with double bbox')
+        #         continue
+        #     previous_ymin_row = ymin_row
+        #     new_master_row[k_row] = v_row
+        ######################################################
+        for k_row, v_row in new_master_row.items():
+
+            _, _, _, _, row_img = v_row
+            xmax, ymax = row_img.size
+            xa, ya, xb, yb = 0, 0, 0, ymax
+            row_img_list = []
+            # plt.imshow(row_img)
+            # st.pyplot()
+            for idx, kv in enumerate(new_cols.items()):
+                k_col, v_col = kv
+                xmin_col, _, xmax_col, _, col_img = v_col
+                xmin_col, xmax_col = xmin_col - padd_left - 10, xmax_col - padd_left
+                xa = xmin_col
+                xb = xmax_col
+                if idx == 0:
+                    xa = 0
+                if idx == len(new_cols) - 1:
+                    xb = xmax
+                xa, ya, xb, yb = xa, ya, xb, yb
+
+                row_img_cropped = row_img.crop((xa, ya, xb, yb))
+                row_img_list.append(row_img_cropped)
+
+            cells_img[k_row + '.' + str(row_idx)] = row_img_list
+            row_idx += 1
+
+        return cells_img, len(new_cols), len(new_master_row) - 1
+
+    def clean_dataframe(self, df):
+        '''
+        Remove irrelevant symbols that appear with tesseractOCR
+        '''
+        # df.columns = [col.replace('|', '') for col in df.columns]
+
+        for col in df.columns:
+
+            df[col] = df[col].str.replace("'", '', regex=True)
+            df[col] = df[col].str.replace('"', '', regex=True)
+            df[col] = df[col].str.replace(']', '', regex=True)
+            df[col] = df[col].str.replace('[', '', regex=True)
+            df[col] = df[col].str.replace('{', '', regex=True)
+            df[col] = df[col].str.replace('}', '', regex=True)
+        return df
+
+    @st.cache
+    def convert_df(self, df):
+        csv = df.to_csv(index=False, encoding='utf-8-sig')  # utf-8-sig to handle BOM for Excel
+        return csv.encode('utf-8')
+
+    def create_dataframe(self, c3, cell_ocr_res: list, max_cols: int,
+                         max_rows: int):
+        '''Create dataframe using list of cell values of the table, also checks for valid header of dataframe
+        Args:
+            cell_ocr_res: list of strings, each element representing a cell in a table
+            max_cols, max_rows: number of columns and rows
+        Returns:
+            dataframe : final dataframe after all pre-processing 
+        '''
+
+        headers = cell_ocr_res[:max_cols]
+        new_headers = uniquify(headers,
+                               (f' {x!s}' for x in string.ascii_lowercase))
+        counter = 0
+
+        cells_list = cell_ocr_res[max_cols:]
+        df = pd.DataFrame("", index=range(0, max_rows), columns=new_headers)
+
+        cell_idx = 0
+        for nrows in range(max_rows):
+            for ncols in range(max_cols):
+                df.iat[nrows, ncols] = str(cells_list[cell_idx])
+                cell_idx += 1
+
+        ## To check if there are duplicate headers if result of uniquify+col == col
+        ## This check removes headers when all headers are empty or if median of header word count is less than 6
+        for x, col in zip(string.ascii_lowercase, new_headers):
+            if f' {x!s}' == col:
+                counter += 1
+        header_char_count = [len(col) for col in new_headers]
+
+        # if (counter == len(new_headers)) or (statistics.median(header_char_count) < 6):
+        #     st.write('woooot')
+        #     df.columns = uniquify(df.iloc[0], (f' {x!s}' for x in string.ascii_lowercase))
+        #     df = df.iloc[1:,:]
+
+        df = self.clean_dataframe(df)
+
+        c3.dataframe(df)
+        csv = self.convert_df(df)
+
+        try:
+            numkey = str(df.iloc[0, 0])
+        except IndexError:
+            numkey = str(0)
+
+        # Create a download link with filename and extension
+        filename = f"table_{numkey}.csv"  # Adjust the filename as needed
+        b64_csv = base64.b64encode(csv).decode()  # Encode CSV data to base64
+        href = f'<a href="data:file/csv;base64,{b64_csv}" download="{filename}">Download {filename}</a>'
+        c3.markdown(href, unsafe_allow_html=True)
+
+        return df
+
+    async def start_process(self, image_path: str, TD_THRESHOLD, TSR_THRESHOLD,
+                            OCR_THRESHOLD, padd_top, padd_left, padd_bottom,
+                            padd_right, delta_xmin, delta_ymin, delta_xmax,
+                            delta_ymax, expand_rowcol_bbox_top,
+                            expand_rowcol_bbox_bottom):
+        '''
+        Initiates process of generating pandas dataframes from raw pdf-page images
+
+        '''
+        image = Image.open(image_path).convert("RGB")
+        probas, bboxes_scaled = table_detector(image,
+                                               THRESHOLD_PROBA=TD_THRESHOLD)
+
+        if bboxes_scaled.nelement() == 0:
+            st.write('No table found in the pdf-page image')
+            return ''
+
+        # try:
+        # st.write('Document: '+image_path.split('/')[-1])
+        c1, c2, c3 = st.columns((1, 1, 1))
+
+        self.plot_results_detection(c1, table_detection_model, image, probas,
+                                    bboxes_scaled, delta_xmin, delta_ymin,
+                                    delta_xmax, delta_ymax)
+        cropped_img_list = self.crop_tables(image, probas, bboxes_scaled,
+                                            delta_xmin, delta_ymin, delta_xmax,
+                                            delta_ymax)
+        
+        cropped_caption_list = self.crop_caption(image, probas, bboxes_scaled,
+                                            delta_xmin, delta_ymin, delta_xmax,
+                                            delta_ymax)
+        
+        # for p, (xmin, ymin, xmax, ymax) in zip(probas, bboxes_scaled.tolist()):
+        #     print(p.argmax())
+        #     print(xmin, ymin, xmax, ymax)
+
+        sequential_caption_img_list = []
+        for idx, caption_img in enumerate(cropped_caption_list):
+            if idx%2 == 0: # top
+                print("top")
+            else: # bottom
+                print("bottom")
+            plt.imshow(caption_img)
+            c2.pyplot()
+            sequential_caption_img_list.append(pytess(cell_pil_img=caption_img, threshold=OCR_THRESHOLD))
+
+        caption_ocr_res = await asyncio.gather(*sequential_caption_img_list)
+        flag_caption_pos = 0 # 0=top, 1=bottom
+        for idx, caption_text in enumerate(caption_ocr_res):
+            if caption_text == "" or "table" not in caption_text.lower():
+                if idx%2==0:
+                    flag_caption_pos=1
+                break
+
+        for idx, caption_text in enumerate(caption_ocr_res):
+            if idx%2==flag_caption_pos:
+                c3.text(str(idx) + "_" + caption_text)
+
+
+        # for idx, unpadded_table in enumerate(cropped_img_list):
+
+        #     table = self.add_padding(unpadded_table, padd_top, padd_right,
+        #                              padd_bottom, padd_left)
+        #     # table = super_res(table)
+        #     # table = binarizeBlur_image(table)
+        #     # table = sharpen_image(table) # Test sharpen image next
+        #     # table = td_postprocess(table)
+
+        #     # table.save("result"+str(idx)+".png")
+
+        #     probas, bboxes_scaled = table_struct_recog(
+        #         table, THRESHOLD_PROBA=TSR_THRESHOLD)
+        #     rows, cols = self.generate_structure(c2, table_recognition_model,
+        #                                          table, probas, bboxes_scaled,
+        #                                          expand_rowcol_bbox_top,
+        #                                          expand_rowcol_bbox_bottom)
+        #     # st.write(len(rows), len(cols))
+        #     rows, cols = self.sort_table_featuresv2(rows, cols)
+        #     master_row, cols = self.individual_table_featuresv2(
+        #         table, rows, cols)
+
+        #     cells_img, max_cols, max_rows = self.object_to_cellsv2(
+        #         master_row, cols, expand_rowcol_bbox_top,
+        #         expand_rowcol_bbox_bottom, padd_left)
+
+        #     sequential_cell_img_list = []
+        #     for k, img_list in cells_img.items():
+        #         for img in img_list:
+        #             # img = super_res(img)
+        #             # img = sharpen_image(img) # Test sharpen image next
+        #             # img = binarizeBlur_image(img)
+        #             # img = self.add_padding(img, 10,10,10,10)
+        #             # plt.imshow(img)
+        #             # c3.pyplot()
+        #             sequential_cell_img_list.append(
+        #                 pytess(cell_pil_img=img, threshold=OCR_THRESHOLD))
+
+        #     cell_ocr_res = await asyncio.gather(*sequential_cell_img_list)
+
+        #     self.create_dataframe(c3, cell_ocr_res, max_cols, max_rows)
+        #     st.write(
+        #         'Errors in OCR is due to either quality of the image or performance of the OCR'
+        #     )
+        # except:
+        #     st.write('Either incorrectly identified table or no table, to debug remove try/except')
+        # break
+        # break
+
+
+if __name__ == "__main__":
+
+    st_up, st_lang = st.columns((1, 1))
+    img_name = st_up.file_uploader("Upload an image with table(s)")
+    lang = st_lang.selectbox('Language', ('en', 'japan'))
+    reload_ocr(lang)
+
+    st1, st2, st3 = st.columns((1, 1, 1))
+    TD_th = st1.slider('Table detection threshold', 0.0, 1.0, 0.8)
+    TSR_th = st2.slider('Table structure recognition threshold', 0.0, 1.0, 0.7)
+    OCR_th = st3.slider("Text Probs Threshold", 0.0, 1.0, 0.5)
+
+    st1, st2, st3, st4 = st.columns((1, 1, 1, 1))
+
+    padd_top = st1.slider('Padding top', 0, 200, 90)
+    padd_left = st2.slider('Padding left', 0, 200, 40)
+    padd_right = st3.slider('Padding right', 0, 200, 40)
+    padd_bottom = st4.slider('Padding bottom', 0, 200, 90)
+
+    te = TableExtractionPipeline()
+    # for img in image_list:
+    if img_name is not None:
+        asyncio.run(
+            te.start_process(img_name,
+                             TD_THRESHOLD=TD_th,
+                             TSR_THRESHOLD=TSR_th,
+                             OCR_THRESHOLD=OCR_th,
+                             padd_top=padd_top,
+                             padd_left=padd_left,
+                             padd_bottom=padd_bottom,
+                             padd_right=padd_right,
+                             delta_xmin=10, # add offset to the left of the table
+                             delta_ymin=3, # add offset to the bottom of the table
+                             delta_xmax=10, # add offset to the right of the table
+                             delta_ymax=3, # add offset to the top of the table
+                             expand_rowcol_bbox_top=0,
+                             expand_rowcol_bbox_bottom=0))

components/callbacks.py

@@ -0,0 +1,4 @@
+# Define callbacks here
+from pytorch_lightning.callbacks import EarlyStopping
+
+early_stopping = EarlyStopping(monitor="loss", min_delta=0, patience=3)

components/data_module.py

@@ -0,0 +1,81 @@
+from typing import Callable, List, Optional, Union
+
+import torch
+from pytorch_lightning import LightningDataModule
+from torch.utils.data import DataLoader, Dataset
+
+
+class SampleDataset(Dataset):
+
+    def __init__(self,
+                 x: Union[List, torch.Tensor],
+                 y: Union[List, torch.Tensor],
+                 transforms: Optional[Callable] = None) -> None:
+        super(SampleDataset, self).__init__()
+        self.x = x
+        self.y = y
+
+        if transforms is None:
+            # Replace None with some default transforms
+            # If image, could be an Resize and ToTensor
+            self.transforms = lambda x: x
+        else:
+            self.transforms = transforms
+
+    def __len__(self):
+        return len(self.x)
+
+    def __getitem__(self, index: int):
+        x = self.x[index]
+        y = self.y[index]
+
+        x = self.transforms(x)
+        return x, y
+
+
+class SampleDataModule(LightningDataModule):
+
+    def __init__(self,
+                 x: Union[List, torch.Tensor],
+                 y: Union[List, torch.Tensor],
+                 transforms: Optional[Callable] = None,
+                 val_ratio: float = 0,
+                 batch_size: int = 32) -> None:
+        super(SampleDataModule, self).__init__()
+        assert 0 <= val_ratio < 1
+        assert isinstance(batch_size, int)
+        self.x = x
+        self.y = y
+
+        self.transforms = transforms
+        self.val_ratio = val_ratio
+        self.batch_size = batch_size
+
+        self.setup()
+        self.prepare_data()
+
+    def setup(self, stage: Optional[str] = None) -> None:
+        pass
+
+    def prepare_data(self) -> None:
+        n_samples: int = len(self.x)
+        train_size: int = n_samples - int(n_samples * self.val_ratio)
+
+        self.train_dataset = SampleDataset(x=self.x[:train_size],
+                                           y=self.y[:train_size],
+                                           transforms=self.transforms)
+        if train_size < n_samples:
+            self.val_dataset = SampleDataset(x=self.x[train_size:],
+                                             y=self.y[train_size:],
+                                             transforms=self.transforms)
+        else:
+            self.val_dataset = SampleDataset(x=self.x[-self.batch_size:],
+                                             y=self.y[-self.batch_size:],
+                                             transforms=self.transforms)
+
+    def train_dataloader(self) -> DataLoader:
+        return DataLoader(dataset=self.train_dataset,
+                          batch_size=self.batch_size)
+
+    def val_dataloader(self) -> DataLoader:
+        return DataLoader(dataset=self.val_dataset, batch_size=self.batch_size)

config.py

@@ -0,0 +1,3 @@
+from dynaconf import Dynaconf
+
+CFG = Dynaconf(envvar_prefix="DYNACONF", settings_files=["config/config.yaml"])

docker-compose.yml

@@ -0,0 +1,23 @@
+version: "3.7"
+
+services:
+  model_name:
+    build:
+      context: .
+      dockerfile: .docker/Dockerfile
+    container_name: model_name
+    ports:
+      - "8996:8996"
+    env_file:
+      - ./.env
+    volumes:
+      - ./data:/home/working/data:ro
+
+    # This part is used to enable GPU support
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [ gpu ]

models/base_model/classification.py

@@ -0,0 +1,63 @@
+from abc import abstractmethod
+from typing import Any, Dict, List
+
+import torch
+from pytorch_lightning import LightningModule
+from torch import Tensor
+
+
+class LightningClassification(LightningModule):
+
+    @abstractmethod
+    def __init__(self, *args, **kwargs) -> None:
+        super(LightningClassification, self).__init__(*args, **kwargs)
+        self.train_batch_output: List[Dict] = []
+        self.validation_batch_output: List[Dict] = []
+        self.log_value_list: List[str] = ['loss', 'f1', 'precision', 'recall']
+
+    @abstractmethod
+    def forward(self, *args, **kwargs) -> Any:
+        pass
+
+    @abstractmethod
+    def configure_optimizers(self):
+        pass
+
+    @abstractmethod
+    def loss(self, input: Tensor, target: Tensor, **kwargs) -> Tensor:
+        pass
+
+    @abstractmethod
+    def training_step(self, batch, batch_idx):
+        pass
+
+    def __average(self, key: str, outputs: List[Dict]) -> Tensor:
+        target_arr = torch.Tensor([val[key] for val in outputs]).float()
+        return target_arr.mean()
+
+    @torch.no_grad()
+    def on_train_epoch_start(self) -> None:
+        self.train_batch_output = []
+
+    @torch.no_grad()
+    def on_train_epoch_end(self) -> None:
+        for key in self.log_value_list:
+            val = self.__average(key=key, outputs=self.train_batch_output)
+            log_name = f"training/{key}"
+            self.log(name=log_name, value=val)
+
+    @abstractmethod
+    @torch.no_grad()
+    def validation_step(self, batch, batch_idx):
+        pass
+
+    @torch.no_grad()
+    def on_validation_epoch_start(self) -> None:
+        self.validation_batch_output = []
+
+    @torch.no_grad()
+    def on_validation_epoch_end(self) -> None:
+        for key in self.log_value_list:
+            val = self.__average(key=key, outputs=self.validation_batch_output)
+            log_name = f"val/{key}"
+            self.log(name=log_name, value=val)

models/base_model/regression.py

@@ -0,0 +1,55 @@
+from abc import abstractmethod
+from typing import Any, Dict, List
+
+import torch
+from pytorch_lightning import LightningModule
+from torch import Tensor
+
+
+class LightningRegression(LightningModule):
+
+    @abstractmethod
+    def __init__(self, *args, **kwargs) -> None:
+        super(LightningRegression, self).__init__(*args, **kwargs)
+        self.train_step_output: List[Dict] = []
+        self.validation_step_output: List[Dict] = []
+        self.log_value_list: List[str] = ['loss', 'mse', 'mape']
+
+    @abstractmethod
+    def forward(self, *args, **kwargs) -> Any:
+        pass
+
+    @abstractmethod
+    def configure_optimizers(self):
+        pass
+
+    @abstractmethod
+    def loss(self, input: Tensor, output: Tensor, **kwargs):
+        return 0
+
+    @abstractmethod
+    def training_step(self, batch, batch_idx):
+        pass
+
+    def __average(self, key: str, outputs: List[Dict]) -> Tensor:
+        target_arr = torch.Tensor([val[key] for val in outputs]).float()
+        return target_arr.mean()
+
+    @torch.no_grad()
+    def on_train_epoch_end(self) -> None:
+        for key in self.log_value_list:
+            val = self.__average(key=key, outputs=self.train_step_output)
+            log_name = f"training/{key}"
+            self.log(name=log_name, value=val)
+
+    @torch.no_grad()
+    @abstractmethod
+    def validation_step(self, batch, batch_idx):
+        pass
+
+    @torch.no_grad()
+    def validation_epoch_end(self, outputs):
+        for key in self.log_value_list:
+            val = self.__average(key=key, outputs=self.validation_step_output)
+            log_name = f"training/{key}"
+            self.log(name=log_name, value=val)

models/metrics/classification.py

@@ -0,0 +1,44 @@
+from typing import Dict
+
+import torch
+from torchmetrics import functional as FM
+
+
+def classification_metrics(
+        preds: torch.Tensor,
+        target: torch.Tensor,
+        num_classes: int,
+        average: str = 'macro',
+        task: str = 'multiclass') -> Dict[str, torch.Tensor]:
+    """
+    get_classification_metrics
+    Return some metrics evaluation the classification task
+
+    Parameters
+    ----------
+    preds : torch.Tensor
+        logits, probs
+    target : torch.Tensor
+        targets label
+
+    Returns
+    -------
+    Dict[str, torch.Tensor]
+        _description_
+    """
+    f1 = FM.f1_score(preds=preds,
+                     target=target,
+                     num_classes=num_classes,
+                     task=task,
+                     average=average)
+    recall = FM.recall(preds=preds,
+                       target=target,
+                       num_classes=num_classes,
+                       task=task,
+                       average=average)
+    precision = FM.precision(preds=preds,
+                             target=target,
+                             num_classes=num_classes,
+                             task=task,
+                             average=average)
+    return dict(f1=f1, precision=precision, recall=recall)

models/metrics/regression.py

@@ -0,0 +1,28 @@
+from typing import Dict
+
+import torch
+from torchmetrics import functional as FM
+
+
+def regression_metrics(preds: torch.Tensor,
+                       target: torch.Tensor) -> Dict[str, torch.Tensor]:
+    """
+    get_classification_metrics
+    Return some metrics evaluation the classification task
+
+    Parameters
+    ----------
+    preds : torch.Tensor
+        logits, probs
+    target : torch.Tensor
+        targets label
+
+    Returns
+    -------
+    Dict[str, torch.Tensor]
+        _description_
+    """
+    mse: torch.Tensor = FM.mean_squared_error(preds=preds, target=target)
+    mape: torch.Tensor = FM.mean_absolute_percentage_error(preds=preds,
+                                                           target=target)
+    return dict(mse=mse, mape=mape)

models/model_lit.py

@@ -0,0 +1,50 @@
+from torch import Tensor, nn, optim
+from torch.nn import functional as F
+
+from .base_model.classification import LightningClassification
+from .metrics.classification import classification_metrics
+from .modules.sample_torch_module import UselessLayer
+
+
+class UselessClassification(LightningClassification):
+
+    def __init__(self, n_classes: int, lr: float, **kwargs) -> None:
+        super(UselessClassification).__init__()
+        self.save_hyperparameters()
+        self.n_classes = n_classes
+        self.lr = lr
+        self.main = nn.Sequential(UselessLayer(), nn.GELU())
+
+    def forward(self, x: Tensor) -> Tensor:
+        return self.main(x)
+
+    def loss(self, input: Tensor, target: Tensor) -> Tensor:
+        return F.mse_loss(input=input, target=target)
+
+    def configure_optimizers(self):
+        optimizer = optim.Adam(params=self.parameters(), lr=self.lr)
+        return optimizer
+
+    def training_step(self, batch, batch_idx):
+        x, y = batch
+
+        logits = self.forward(x)
+        loss = self.loss(input=x, target=y)
+        metrics = classification_metrics(preds=logits,
+                                         target=y,
+                                         num_classes=self.n_classes)
+
+        self.train_batch_output.append({'loss': loss, **metrics})
+        return loss
+
+    def validation_step(self, batch, batch_idx):
+        x, y = batch
+
+        logits = self.forward(x)
+        loss = self.loss(input=x, target=y)
+        metrics = classification_metrics(preds=logits,
+                                         target=y,
+                                         num_classes=self.n_classes)
+
+        self.validation_batch_output.append({'loss': loss, **metrics})
+        return loss

models/modules/sample_torch_module.py

@@ -0,0 +1,12 @@
+from torch import Tensor, nn
+
+
+class UselessLayer(nn.Module):
+
+    def __init__(self) -> None:
+        super(UselessLayer, self).__init__()
+        self.seq = nn.Identity()
+
+    def forward(self, x: Tensor) -> Tensor:
+        x = self.seq(x)
+        return x

requirements.txt

@@ -0,0 +1,10 @@
+timm==0.9.2
+torch --index-url https://download.pytorch.org/whl/cpu
+torchvision --index-url https://download.pytorch.org/whl/cpu
+torchaudio --index-url https://download.pytorch.org/whl/cpu
+streamlit==1.21.0
+pandas
+transformers==4.29.1
+Pillow==10.0.1
+paddlepaddle
+paddleocr

test_pdf2img.py

@@ -0,0 +1,16 @@
+import os  
+from pdf2image import convert_from_path  
+  
+# Set the PDF file path  
+pdf_path = 'test.pdf'  
+  
+# Convert the first page of the PDF to a JPEG image  
+first = 14
+last = 14
+images = convert_from_path(pdf_path, dpi=300, first_page=first, last_page=last, poppler_path=r"C:\poppler-23.07.0\Library\bin")  
+  
+# Save the image file  
+image_path = os.path.splitext(pdf_path)[0]
+
+for index, image in enumerate(images):
+    image.save(image_path + "p" + str(index+first) + '.jpg', 'JPEG')  

tests/test_resource.py

@@ -0,0 +1,4 @@
+def test_cuda():
+    from torch.cuda import is_available
+    assert is_available()
+