Closed ved-genmo closed 2 days ago
Hi @ved-genmo :wave:;
The fast checkpoints are only available on the main branch (v0.9.0a0) yet as mentioned with the last release notes :) So you could use the main branch or wait until we have released v0.9.0 (planned for next month)
Best regards, Felix
Bug description
doctr cannot find the weights for the FAST series of models, so it uses default initialization, which causes arbitrary results.
Code snippet to reproduce the bug
Error traceback
No traceback.
Environment
DocTR version: v0.8.1 TensorFlow version: 2.15.1 PyTorch version: N/A (torchvision N/A) OpenCV version: 4.5.5 OS: Debian GNU/Linux 12 (bookworm) Python version: 3.10.0 Is CUDA available (TensorFlow): No Is CUDA available (PyTorch): N/A CUDA runtime version: No CUDA GPU models and configuration: No CUDA Nvidia driver version: No CUDA cuDNN version: No CUDA
Deep Learning backend
is_tf_available: True is_torch_available: False