* Acc@1 0.092 (99.908) Acc@5 0.338 (99.662) #33
Description
/home/anaconda3/bin/conda run -n kat --no-capture-output python /home/kat/validate.py /home/imagenet/ --model kat_tiny_patch16_224 --checkpoint kat_tiny_patch16_224_1f3ad3b2e69821f3d412f2924cf159a0e266f142d739cb68f68f796f5a0fe289.pth -b 512
/home/rational_kat_cu/kat_rational/kat_1dgroup.py:10: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
/home/rational_kat_cu/kat_rational/kat_1dgroup.py:32: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, grad_output):
Validating in float32. AMP not enabled.
Loaded state_dict from checkpoint 'kat_tiny_patch16_224_1f3ad3b2e69821f3d412f2924cf159a0e266f142d739cb68f68f796f5a0fe289.pth'
Model kat_tiny_patch16_224 created, param count: 5718328
Data processing configuration for current model + dataset:
input_size: (3, 224, 224)
interpolation: bicubic
mean: (0.485, 0.456, 0.406)
std: (0.229, 0.224, 0.225)
crop_pct: 0.875
crop_mode: center
Test: [ 0/98] Time: 1.702s (1.702s, 300.89/s) Loss: 9.5117 (9.5117) Acc@1: 0.000 ( 0.000) Acc@5: 0.586 ( 0.586)
Test: [ 10/98] Time: 0.099s (0.414s, 1235.78/s) Loss: 9.5943 (9.5137) Acc@1: 0.000 ( 0.036) Acc@5: 0.000 ( 0.231)
Test: [ 20/98] Time: 0.102s (0.403s, 1271.90/s) Loss: 9.5652 (9.5066) Acc@1: 0.000 ( 0.084) Acc@5: 0.000 ( 0.279)
Test: [ 30/98] Time: 0.100s (0.368s, 1390.58/s) Loss: 9.5710 (9.5108) Acc@1: 0.000 ( 0.082) Acc@5: 0.391 ( 0.290)
Test: [ 40/98] Time: 0.100s (0.373s, 1372.38/s) Loss: 9.5144 (9.5206) Acc@1: 0.000 ( 0.091) Acc@5: 0.977 ( 0.305)
Test: [ 50/98] Time: 0.101s (0.358s, 1431.60/s) Loss: 9.4829 (9.5188) Acc@1: 0.195 ( 0.096) Acc@5: 0.391 ( 0.310)
Test: [ 60/98] Time: 0.132s (0.362s, 1414.92/s) Loss: 9.4237 (9.5226) Acc@1: 0.391 ( 0.096) Acc@5: 0.977 ( 0.320)
Test: [ 70/98] Time: 0.144s (0.355s, 1441.42/s) Loss: 9.5024 (9.5218) Acc@1: 0.000 ( 0.088) Acc@5: 0.195 ( 0.319)
Test: [ 80/98] Time: 0.377s (0.361s, 1416.44/s) Loss: 9.5698 (9.5249) Acc@1: 0.000 ( 0.094) Acc@5: 0.586 ( 0.333)
Test: [ 90/98] Time: 0.103s (0.355s, 1443.01/s) Loss: 9.4263 (9.5242) Acc@1: 0.391 ( 0.094) Acc@5: 0.781 ( 0.335)
- Acc@1 0.092 (99.908) Acc@5 0.338 (99.662)
--result
{
"model": "kat_tiny_patch16_224",
"top1": 0.092,
"top1_err": 99.908,
"top5": 0.338,
"top5_err": 99.662,
"param_count": 5.72,
"img_size": 224,
"crop_pct": 0.875,
"interpolation": "bicubic"
}
thank for your sharing work. I already downloaded the checkpoint“'kat_tiny_patch16_224_1f3ad3b2e69821f3d412f2924cf159a0e266f142d739cb68f68f796f5a0fe289.pth'”，but when i run validate.py with param" /home/imagenet/ --model kat_tiny_patch16_224 --checkpoint kat_tiny_patch16_224_1f3ad3b2e69821f3d412f2924cf159a0e266f142d739cb68f68f796f5a0fe289.pth -b 512 "
the result is very terrible