0
Jump into concepts and practice - no test required
Recommended
import torchvision from torchvision.models.detection import fasterrcnn_resnet50_fpn from torchvision.transforms import functional as F import torch from torch.utils.data import DataLoader, Dataset import cv2 import numpy as np class TableDataset(Dataset): def __init__(self, images, targets, transforms=None): self.images = images self.targets = targets self.transforms = transforms def __len__(self): return len(self.images) def __getitem__(self, idx): img = self.images[idx] target = self.targets[idx] img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) img = F.to_tensor(img) if self.transforms: img = self.transforms(img) return img, target # Load pretrained Faster R-CNN model model = fasterrcnn_resnet50_fpn(pretrained=True) num_classes = 2 # background and table in_features = model.roi_heads.box_predictor.cls_score.in_features model.roi_heads.box_predictor = torchvision.models.detection.faster_rcnn.FastRCNNPredictor(in_features, num_classes) # Adjust anchor sizes to better fit tables model.rpn.anchor_generator.sizes = ((32, 64, 128, 256, 512),) # Example training loop snippet optimizer = torch.optim.SGD(model.parameters(), lr=0.005, momentum=0.9, weight_decay=0.0005) num_epochs = 15 # Assume train_loader and val_loader are defined with TableDataset for epoch in range(num_epochs): model.train() for images, targets in train_loader: images = list(image.to(device) for image in images) targets = [{k: v.to(device) for k, v in t.items()} for t in targets] loss_dict = model(images, targets) losses = sum(loss for loss in loss_dict.values()) optimizer.zero_grad() losses.backward() optimizer.step() # Post-processing: adjust NMS threshold model.roi_heads.nms_thresh = 0.3 # Evaluate on validation set to compute precision and recall # (Evaluation code omitted for brevity but includes IoU matching and metric calculation)
Before: Precision 85%, Recall 60%
After: Precision 82%, Recall 81%
table extraction from images in computer vision?cells_text?
import cv2
import pytesseract
image = cv2.imread('table.png', 0)
_, thresh = cv2.threshold(image, 128, 255, cv2.THRESH_BINARY_INV)
contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cells_text = []
for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
cell_img = image[y:y+h, x:x+w]
text = pytesseract.image_to_string(cell_img, config='--psm 6')
cells_text.append(text.strip())
print(type(cells_text))cells_text is initialized as an empty list and text from each detected cell is appended to it.cells_textcells_text collects multiple strings in a list, its type remains list.