End of training
Browse files
README.md
CHANGED
|
@@ -14,6 +14,30 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# detr-resnet-50_finetuned_cppe5
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -38,17 +62,19 @@ The following hyperparameters were used during training:
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 42 |
- num_epochs: 2
|
| 43 |
-
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
-
- Transformers 4.
|
| 52 |
-
- Pytorch 2.
|
| 53 |
-
- Datasets 2.
|
| 54 |
- Tokenizers 0.19.1
|
|
|
|
| 14 |
# detr-resnet-50_finetuned_cppe5
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.9677
|
| 19 |
+
- Map: 0.0546
|
| 20 |
+
- Map 50: 0.103
|
| 21 |
+
- Map 75: 0.0504
|
| 22 |
+
- Map Small: 0.0092
|
| 23 |
+
- Map Medium: 0.0513
|
| 24 |
+
- Map Large: 0.053
|
| 25 |
+
- Mar 1: 0.099
|
| 26 |
+
- Mar 10: 0.2024
|
| 27 |
+
- Mar 100: 0.2506
|
| 28 |
+
- Mar Small: 0.1343
|
| 29 |
+
- Mar Medium: 0.1925
|
| 30 |
+
- Mar Large: 0.2414
|
| 31 |
+
- Map Coverall: 0.233
|
| 32 |
+
- Mar 100 Coverall: 0.7017
|
| 33 |
+
- Map Face Shield: 0.0
|
| 34 |
+
- Mar 100 Face Shield: 0.0
|
| 35 |
+
- Map Gloves: 0.0047
|
| 36 |
+
- Mar 100 Gloves: 0.2792
|
| 37 |
+
- Map Goggles: 0.0
|
| 38 |
+
- Mar 100 Goggles: 0.0
|
| 39 |
+
- Map Mask: 0.0352
|
| 40 |
+
- Mar 100 Mask: 0.272
|
| 41 |
|
| 42 |
## Model description
|
| 43 |
|
|
|
|
| 62 |
- seed: 42
|
| 63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 64 |
- lr_scheduler_type: linear
|
|
|
|
| 65 |
- num_epochs: 2
|
|
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
|
| 70 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
|
| 71 |
+
| No log | 1.0 | 107 | 2.0994 | 0.0445 | 0.0869 | 0.04 | 0.0045 | 0.0347 | 0.0464 | 0.0794 | 0.1672 | 0.2137 | 0.0881 | 0.1491 | 0.221 | 0.199 | 0.6589 | 0.0 | 0.0 | 0.0019 | 0.2107 | 0.0 | 0.0 | 0.0217 | 0.1989 |
|
| 72 |
+
| No log | 2.0 | 214 | 1.9677 | 0.0546 | 0.103 | 0.0504 | 0.0092 | 0.0513 | 0.053 | 0.099 | 0.2024 | 0.2506 | 0.1343 | 0.1925 | 0.2414 | 0.233 | 0.7017 | 0.0 | 0.0 | 0.0047 | 0.2792 | 0.0 | 0.0 | 0.0352 | 0.272 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
+
- Transformers 4.42.4
|
| 78 |
+
- Pytorch 2.4.0
|
| 79 |
+
- Datasets 2.21.0
|
| 80 |
- Tokenizers 0.19.1
|