-
I'm following the `train_a_new_model_on_a_new_dataset_from_scratch.ipynb` and used `python3.11 -m venv venv && source venv/bin/activate` for virtual env.
I noticed that the `corenet` doesn't have …
-
Here is the code that i'm using -
```
import cv2
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visu…
-
Hi,
When I try to run the demo, the first line has error.
http://localhost:8888/lab/tree/trt_pose/tasks/human_pose
May I know which part I maybe missing? I am using nano.
Based on the error, I f…
-
Which of the following tensor shape of output features is correct?
Take batch=N, input =512 , R=4, C=80 (COCO ) as an example：
（N，128，128，80，2，2）? or （N，128，128，80 + 2 + 2) ?
-
I preprocess my own data, and when predicting keypoints, the output is .jpg images instead of a .npy files.
I cloned a specific repository using the link provided in the Dockerfile, using the comma…
-
### 🐛 Describe the bug
torchbench_amp_bf16_training
xpu train detectron2_fcos_r_50_fpn
Traceback (most recent call last):
File "/home/sdp/actions-runner/_work/torch-xpu-ops/pytorch/benc…
-
Hi, it has been 4 months since you last updated the code. However, the lvis related dataset files have not been updated. Moreover, I only find the train annotation jsons, but I don't find the val anno…
-
### What happens?
When using a UDF in C++, which manipulates string values, if `duckdb::string_t` is passed a string which contains `\r`, `\v`, etc, the resulting query crashes with error:
```json…
-
I created my own dataset in COCO-style. So i have the annotation-files for my trainset, validationset, testset and for all my images.
I can use the prediction to see how the Ground Truth looks like …
-
**Here is my code. However, the result is not 1.**
def eval_map(ann_json):
with open(ann_json, "r") as f:
data = json.load(f)
for aa in data["annotations"]:
aa["score"] …