Instructions to use harness-race/opencode-r3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harness-race/opencode-r3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="harness-race/opencode-r3")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("harness-race/opencode-r3") model = AutoModelForObjectDetection.from_pretrained("harness-race/opencode-r3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload train_detr.py with huggingface_hub
Browse files- train_detr.py +2 -1
train_detr.py
CHANGED
|
@@ -218,7 +218,8 @@ for epoch in range(1, ARGS.epochs+1):
|
|
| 218 |
model.train()
|
| 219 |
ep_loss = 0.0; ep_ce = 0.0; ep_bbox = 0.0; ep_giou = 0.0; nb = 0
|
| 220 |
for images, anns, sizes, idx in tqdm(train_dl, desc="epoch %d"%epoch):
|
| 221 |
-
|
|
|
|
| 222 |
pv = enc["pixel_values"].to(device); pm = enc["pixel_mask"].to(device)
|
| 223 |
labels = [{k: v.to(device) for k,v in l.items()} for l in enc.get("labels")]
|
| 224 |
out = model(pixel_values=pv, pixel_mask=pm, labels=labels)
|
|
|
|
| 218 |
model.train()
|
| 219 |
ep_loss = 0.0; ep_ce = 0.0; ep_bbox = 0.0; ep_giou = 0.0; nb = 0
|
| 220 |
for images, anns, sizes, idx in tqdm(train_dl, desc="epoch %d"%epoch):
|
| 221 |
+
anns_pp = [{"image_id": int(idx[k]), "annotations": anns[k]} for k in range(len(images))]
|
| 222 |
+
enc = processor(images=images, annotations=anns_pp, return_tensors="pt")
|
| 223 |
pv = enc["pixel_values"].to(device); pm = enc["pixel_mask"].to(device)
|
| 224 |
labels = [{k: v.to(device) for k,v in l.items()} for l in enc.get("labels")]
|
| 225 |
out = model(pixel_values=pv, pixel_mask=pm, labels=labels)
|