-
Hello
The efficient D2 model is being used.
I'm going to run the assessment with that code.
An error has occurred.
code:
python model_main_tf2.py --model_dir=woo/dev3/Data/train/d2/model_66…
-
Hello,
When reading a parquet file with specifed dtypes and a column full of NaNs, tf.data.IODataset.from_parquet crashes.
I'm guessing this is somehow related to how data types are deduced or how N…
-
I'm comparing it to SciPy and it is clearly too slow. It can be 100 times slower on CPU, which makes it quite unusable. My GPU improves the times but it is still very slow. I show you my benchmarks an…
-
The function diagonal out of best.models.pomdp_sparse_utils import takes a substantial amount to process. This is currently taking 95% percent of the time for solving LP problems.
-
I am trying to convert FSDv2 to ONNX (and next to TensorRT), but there is an error:
RuntimeError: ONNX export failed on an operator with unrecognized namespace torch_scatter::scatter_max. If you ar…
-
http://openaccess.thecvf.com/content_CVPR_2019/papers/Simeoni_Local_Features_and_Visual_Words_Emerge_in_Activations_CVPR_2019_paper.pdf
-
### 🐛 Describe the bug
I have the strangest bug that I will try my best to explain. Note that the error only occurs when I use the GPU, and when using CPU works as expected with no errors. Note that …
-
Add `nn.functional.linear()` with autograd for sparse tensor when input is sparse, while weights and bias are dense.
- autograd for `torch.sparse.addmm(D, S, D) -> D`
- add `torch.sparse.matmul(S,…
-
Hi, I am getting an error while trying to run deep_unsupervised_embedding on my project. I suspect there is some mismatch between the expected and received input shape for the CensNetConv network but …
-
Hi.
I did a test with demo.ipynb. And it worked.
But I got a problem with coco.py.
I want to train with coco dataset in 2014.
I followed your procedure like :
# Train a new model starting from …