-
The training seem to be ok. T**he final epoch acc: 0.988281** **, _but the best metric, acc: 0.0_**
What's wrong with that?
I used my custom dataset and I adjust dict.txt
- System Environment：goog…
-
### Problem description
I want to run the famous [minGPT](https://github.com/karpathy/minGPT) , but i can't, the repository size is 1MB
### What steps will reproduce the bug?
```bash
pkg ins…
-
test.py
```
import torch
print(torch.cuda.is_available())
```
I'm working on my torch project as a package but as soon as I introduce the torch into the package he gets the following erro…
-
```tex
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc
save_epoch_step: 3
# evaluation is run e…
-
### System Info
Colab Configuration:
- `transformers` version: 4.30.0.dev0
- Platform: Linux-5.15.107+-x86_64-with-glibc2.31
- Python version: 3.10.11
- Huggingface_hub version: 0.14.1
- Safet…
-
### System Info
My System Info:
- `transformers` version: 4.30.0.dev0
- Platform: Linux-5.15.107+-x86_64-with-glibc2.31
- Python version: 3.10.11
- Huggingface_hub version: 0.14.1
- Safetensors …
-
# Summary
Hi,
We have issues compiling on aarch64 machines on both Neoverse-V1 and Neoverse-N1.
The compilation crashes while compiling `oneDNN/src/cpu/jit_utils/jit_utils.cpp`.
Issue seems to hav…
-
I think in tokenize function, if it's tokenizing words, it should add space_character to tokens too. Otherwise, in predict function, it will assume '' for spaces and the predictions doesn't have space…
-
Hello and thank you for your SimpleHTR and CTCWordBeamSearch Repos.
The latter I am trying to use with my code, but I am stuck with the ValueError mentioned in the title:
ValueError: the number o…
-
**TensorRT**
```
1、git clone https://github.com/NVIDIA/TensorRT
2、cd TensorRT
3、./docker/build.sh --file docker/ubuntu-18.04.Dockerfile --tag tensorrt-ubuntu18.04-cuda11.4
4、./docker/launch.sh --…