Error:: Model Update and Model Evaluation about compressai HOT 3 CLOSED

Hi,

• Can you provide a bit more information on your setup?
  • Can you run python3 -m torch.utils.collect_env
  • report the compressai package version
  • which model are you training?
• The *_best_loss.pth.ar is a copy of the checkpoint with the minimum loss achieved with the example training script (see here).
• since you are using your own trained model, you should use the checkpoint argument in the evaluation script.

from compressai.

Hi Jean, thank you for answering.

1. When I ran: python3 -m torch.utils.collect_env, I got:

Collecting environment information...
PyTorch version: 1.8.1+cu101
Is debug build: False
CUDA used to build PyTorch: 10.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 18.04.5 LTS (x86_64)
GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Clang version: 6.0.0-1ubuntu2 (tags/RELEASE_600/final)
CMake version: version 3.12.0

Python version: 3.7 (64-bit runtime)
Is CUDA available: True
CUDA runtime version: Could not collect
GPU models and configuration: GPU 0: Tesla T4
Nvidia driver version: 460.32.03
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.5
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.0.4
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.0.4
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] numpy==1.19.5
[pip3] pytorch-msssim==0.2.1
[pip3] torch==1.8.1+cu101
[pip3] torchsummary==1.5.1
[pip3] torchtext==0.9.1
[pip3] torchvision==0.9.1+cu101
[conda] Could not collect

I guess that it is important say I was using colab to do some tests, but this week, I'm gonna use a computer with GPU and conda environment.

2. The compressai package version is 1.1.5.
3. I'm using bmshj2018-factorized, with my selected images.
   Thank you.

from compressai.

you need to pass the correct architecture to compressai.utils.update_model, otherwise torch.load will fail.

from compressai.