Commit
•
7452863
1
Parent(s):
8cc30b1
update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,24 +4,9 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- imagefolder
|
| 7 |
-
metrics:
|
| 8 |
-
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: delivery_truck_classification
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Image Classification
|
| 14 |
-
type: image-classification
|
| 15 |
-
dataset:
|
| 16 |
-
name: imagefolder
|
| 17 |
-
type: imagefolder
|
| 18 |
-
config: default
|
| 19 |
-
split: train
|
| 20 |
-
args: default
|
| 21 |
-
metrics:
|
| 22 |
-
- name: Accuracy
|
| 23 |
-
type: accuracy
|
| 24 |
-
value: 0.9259259259259259
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,8 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
-
|
| 35 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
@@ -62,55 +52,9 @@ The following hyperparameters were used during training:
|
|
| 62 |
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
- num_epochs: 40
|
| 64 |
|
| 65 |
-
### Training results
|
| 66 |
-
|
| 67 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
-
| No log | 0.8 | 3 | 1.8673 | 0.2222 |
|
| 70 |
-
| No log | 1.8 | 6 | 1.7421 | 0.2593 |
|
| 71 |
-
| No log | 2.8 | 9 | 1.5910 | 0.4259 |
|
| 72 |
-
| No log | 3.8 | 12 | 1.4371 | 0.5 |
|
| 73 |
-
| No log | 4.8 | 15 | 1.2871 | 0.5741 |
|
| 74 |
-
| No log | 5.8 | 18 | 1.1511 | 0.5741 |
|
| 75 |
-
| 1.8164 | 6.8 | 21 | 0.9363 | 0.7222 |
|
| 76 |
-
| 1.8164 | 7.8 | 24 | 0.7903 | 0.7778 |
|
| 77 |
-
| 1.8164 | 8.8 | 27 | 0.6839 | 0.7593 |
|
| 78 |
-
| 1.8164 | 9.8 | 30 | 0.5661 | 0.7778 |
|
| 79 |
-
| 1.8164 | 10.8 | 33 | 0.4638 | 0.8519 |
|
| 80 |
-
| 1.8164 | 11.8 | 36 | 0.4015 | 0.8704 |
|
| 81 |
-
| 1.8164 | 12.8 | 39 | 0.3809 | 0.8704 |
|
| 82 |
-
| 0.8525 | 13.8 | 42 | 0.3214 | 0.9074 |
|
| 83 |
-
| 0.8525 | 14.8 | 45 | 0.3114 | 0.8704 |
|
| 84 |
-
| 0.8525 | 15.8 | 48 | 0.3026 | 0.8889 |
|
| 85 |
-
| 0.8525 | 16.8 | 51 | 0.2970 | 0.8889 |
|
| 86 |
-
| 0.8525 | 17.8 | 54 | 0.2597 | 0.8889 |
|
| 87 |
-
| 0.8525 | 18.8 | 57 | 0.2792 | 0.8889 |
|
| 88 |
-
| 0.4831 | 19.8 | 60 | 0.3209 | 0.8704 |
|
| 89 |
-
| 0.4831 | 20.8 | 63 | 0.2929 | 0.9074 |
|
| 90 |
-
| 0.4831 | 21.8 | 66 | 0.2419 | 0.9259 |
|
| 91 |
-
| 0.4831 | 22.8 | 69 | 0.2496 | 0.9074 |
|
| 92 |
-
| 0.4831 | 23.8 | 72 | 0.2953 | 0.9074 |
|
| 93 |
-
| 0.4831 | 24.8 | 75 | 0.3094 | 0.8889 |
|
| 94 |
-
| 0.4831 | 25.8 | 78 | 0.2792 | 0.9259 |
|
| 95 |
-
| 0.3889 | 26.8 | 81 | 0.2522 | 0.9259 |
|
| 96 |
-
| 0.3889 | 27.8 | 84 | 0.2451 | 0.9259 |
|
| 97 |
-
| 0.3889 | 28.8 | 87 | 0.2541 | 0.9074 |
|
| 98 |
-
| 0.3889 | 29.8 | 90 | 0.2718 | 0.9074 |
|
| 99 |
-
| 0.3889 | 30.8 | 93 | 0.2738 | 0.9074 |
|
| 100 |
-
| 0.3889 | 31.8 | 96 | 0.2639 | 0.9259 |
|
| 101 |
-
| 0.3889 | 32.8 | 99 | 0.2561 | 0.9259 |
|
| 102 |
-
| 0.3407 | 33.8 | 102 | 0.2497 | 0.9259 |
|
| 103 |
-
| 0.3407 | 34.8 | 105 | 0.2501 | 0.9259 |
|
| 104 |
-
| 0.3407 | 35.8 | 108 | 0.2455 | 0.9259 |
|
| 105 |
-
| 0.3407 | 36.8 | 111 | 0.2381 | 0.9259 |
|
| 106 |
-
| 0.3407 | 37.8 | 114 | 0.2340 | 0.9259 |
|
| 107 |
-
| 0.3407 | 38.8 | 117 | 0.2321 | 0.9259 |
|
| 108 |
-
| 0.3112 | 39.8 | 120 | 0.2315 | 0.9259 |
|
| 109 |
-
|
| 110 |
-
|
| 111 |
### Framework versions
|
| 112 |
|
| 113 |
-
- Transformers 4.
|
| 114 |
-
- Pytorch 1.
|
| 115 |
-
- Datasets 2.
|
| 116 |
- Tokenizers 0.13.2
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- imagefolder
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: delivery_truck_classification
|
| 9 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.1655
|
| 20 |
+
- eval_accuracy: 0.9492
|
| 21 |
+
- eval_runtime: 3.0476
|
| 22 |
+
- eval_samples_per_second: 19.36
|
| 23 |
+
- eval_steps_per_second: 0.656
|
| 24 |
+
- epoch: 0.94
|
| 25 |
+
- step: 4
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 52 |
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
- num_epochs: 40
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
+
- Transformers 4.25.1
|
| 58 |
+
- Pytorch 1.13.1+cu117
|
| 59 |
+
- Datasets 2.8.0
|
| 60 |
- Tokenizers 0.13.2
|