missing eval in DefaultPredictor of detectron2_modify

DefaultPredictor of detectron2_modify, only disable parameters grad, but remain model in training, this cause wrong logic when using Mask2Former as criterion.

solution: restore the model.eval() as in original detectron2:
https://github.com/facebookresearch/detectron2/blob/0ae803b1449cd2d3f8fa1b7c0f59356db10b3083/detectron2/engine/defaults.py#L280-L285

another bug: it's loading the first char of a path string

SportsSloMo/SportsSloMo_EBME/core/dataset.py

Lines 186 to 187 in 78f31a9

    
           # Load Segmentation Masks 
        
           seg = np.load(seg_path_target[0], allow_pickle=True)

solution: remove [0]

other problems:
the readme says pip install -e to install detectron2, this will make our own tools unable to import. for now, need to use this pr facebookresearch/detectron2#5283

there is also missing symbol link of Mask2Former in SportsSloMo_EBME, it's no said in readme, neither tracked in git repo.

the shell command in readme is not perfect, it's common that command needs to be run in parent or sub dir.

	# Load Segmentation Masks
	seg = np.load(seg_path_target[0], allow_pickle=True)