@wuyefeilin Yeah I'm aware of that, I used deploy.yaml as my config for infer.py. My problem is there's a significant difference in prediction quality as shown above between using predict.py...
No I did not change the code anywhere. [Google Drive Folder](https://drive.google.com/drive/folders/12q-KBBJFvfx77dcrqI2H2p1dcxcKRrQs?usp=sharing) Folder contains two zip files : Before exporting and after exporting, with their config files.
Hi @wuyefeilin any idea why this is happening?
```python export.py --config configs/modnet/modnet-hrnet_w18-iter19_1.yml --save_dir deploy/models/iter19_1 --model_path train_runs/iter19_1/iter_60000/model.pdparams ``` This is my config ``` batch_size: 8 iters: 100000 train_dataset: type: MattingDataset dataset_root: train_file: train.txt transforms: - type: LoadImages - type:...
Could it be because in train_transforms its just `Resize` whereas in val its `ResizeByShort` ?
@cosmic-cortex Hello, can you please help me out here? TIA