File size: 3,815 Bytes
526a660 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | # Table Transformer Detection with Transformers
This page is the Transformers contract of the Table Transformer Detection MIC and also a usage example. [doc-builder](https://github.com/huggingface/doc-builder/blob/main/docs/runnable-code-blocks.md) renders the `runnable` blocks below as documentation, and its pytest plugin runs them as written against `microsoft/table-transformer-detection`. The MIC runner runs the same blocks against each slim fixture and each checkpoint in [`integration.json`](../../integration.json). Lines marked `# doc-builder: hide` only matter there: they swap in the pinned checkpoint or variant and print the result record.
## Detect tables in synthetic images
```py runnable:table_detection
import torch
from transformers import AutoModelForObjectDetection, AutoProcessor, set_seed
import json # doc-builder: hide
import os # doc-builder: hide
import numpy as np
from PIL import Image
model_id = "microsoft/table-transformer-detection"
model_id = os.environ.get("MIC_MODEL", model_id) # doc-builder: hide
variant = json.loads(os.environ.get("MIC_MODEL_KWARGS", "{}")) # doc-builder: hide
device = "cuda" if torch.cuda.is_available() else "cpu"
set_seed(0)
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForObjectDetection.from_pretrained(model_id).to(device)
if variant: # doc-builder: hide
model = AutoModelForObjectDetection.from_pretrained(model_id, **variant).to(device)
# Two distinct synthetic images
np.random.seed(0)
img1 = Image.fromarray(np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8))
img2 = Image.fromarray(np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8))
inputs = processor(images=[img1, img2], return_tensors="pt").to(device)
model.eval()
with torch.no_grad(), torch.autocast(device, dtype=model.dtype, enabled=model.dtype != torch.float32):
outputs = model(**inputs)
# Compact probes: top-3 scores and first 2 boxes for image 0
scores = outputs.logits[0][:3].float()
boxes = outputs.pred_boxes[0][:2].float()
print(f"scores: {scores.tolist()}")
print(f"boxes: {boxes.tolist()}")
```
## One training step
```py runnable:table_detection:2
# Training targets: one box per image
labels = [
{"class_labels": torch.tensor([0], device=device), "boxes": torch.tensor([[0.1, 0.1, 0.5, 0.5]], device=device)},
{"class_labels": torch.tensor([1], device=device), "boxes": torch.tensor([[0.2, 0.2, 0.6, 0.6]], device=device)},
]
labels = [{k: v.to(device) for k, v in item.items()} for item in labels]
model.train()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
with torch.autocast(device, dtype=model.dtype, enabled=model.dtype != torch.float32):
loss = model(pixel_values=inputs["pixel_values"], labels=labels).loss
loss.backward()
before = {name: p.detach().clone() for name, p in model.named_parameters()} # doc-builder: hide
optimizer.step()
print(f"loss: {loss.item():.4f}")
if os.environ.get("MIC_RUNNER"): # doc-builder: hide
named = dict(model.named_parameters())
checked = tuple(n for n, p in named.items() if p.grad is not None and torch.count_nonzero(p.grad) > 0)[:2]
result = {
"runtime": {
"device": next(model.parameters()).device.type,
"dtype": str(next(model.parameters()).dtype).removeprefix("torch."),
"attn_implementation": model.config._attn_implementation,
},
"inference_scores": scores.tolist(),
"inference_boxes": boxes.tolist(),
"training": {
"loss": loss.item(),
"gradients": {n: bool(named[n].grad is not None and torch.count_nonzero(named[n].grad) > 0 and torch.isfinite(named[n].grad).all()) for n in checked},
"updated": any(not torch.equal(p, before[n]) for n, p in named.items()),
},
}
print(json.dumps(result))
```
|