Traceback (most recent call last):
File "prune_val.py", line 360, in
main(opt)
File "prune_val.py", line 340, in main
device=opt.device, save_json=False, plots=False)
File "/usr/local/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
return func(*args, **kwargs)
File "prune_val.py", line 124, in run
model = attempt_load(weights, map_location=device) # load FP32 model
File "/home/yolov5-v6/models/experimental.py", line 96, in attempt_load
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
AttributeError: 'collections.OrderedDict' object has no attribute 'float'
Traceback (most recent call last): File "prune_val.py", line 360, in
main(opt)
File "prune_val.py", line 340, in main
device=opt.device, save_json=False, plots=False)
File "/usr/local/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
return func(*args, **kwargs)
File "prune_val.py", line 124, in run
model = attempt_load(weights, map_location=device) # load FP32 model
File "/home/yolov5-v6/models/experimental.py", line 96, in attempt_load
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
AttributeError: 'collections.OrderedDict' object has no attribute 'float'
use method:
python prune_val.py --img-size 512 --batch-size 64 --data ./data/PFD.yaml --weights "./weights/prune_0.4_keep_0.01_best.pt" --task speed --verbose --half
I suspect that prune_val.py does not make changes to the pruning model