Evalution coco object detection

1

please how to get accuracy and also save the results according to coco object detection


[{"image_id": int, "category_id": int,"bbox": [x,y,width,height],"score": float,}]

here is the training

# Training
for epoch in range(config.num_epochs):
    print(f"Epoch: {epoch}/{config.num_epochs}")
    model.train()
    i = 0
    for imgs, annotations in data_loader:
        i += 1
        imgs = list(img.to(device) for img in imgs)
        annotations = [{k: v.to(device) for k, v in t.items()} for t in annotations]
        loss_dict = model(imgs, annotations)
        print(loss_dict)
        # detections = y.data

        losses = sum(loss for loss in loss_dict.values())

        optimizer.zero_grad()
        losses.backward()
        optimizer.step()

        print(f"Iteration: {i}/{len_dataloader}, Loss: {losses}")
2

The object detection tutorial should give you a sample code for the model evaluation including the AP and AR calculation.