Instructions to use susnato/detr-resnet-50_finetuned_plant_disease_detection_processed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use susnato/detr-resnet-50_finetuned_plant_disease_detection_processed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="susnato/detr-resnet-50_finetuned_plant_disease_detection_processed")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("susnato/detr-resnet-50_finetuned_plant_disease_detection_processed") model = AutoModelForObjectDetection.from_pretrained("susnato/detr-resnet-50_finetuned_plant_disease_detection_processed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -41,23 +41,92 @@ The following hyperparameters were used during training:
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_ratio: 0.2
|
| 44 |
-
- num_epochs:
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| 5.
|
| 52 |
-
| 4.
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
|
|
|
| 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: 0.6402
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_ratio: 0.2
|
| 44 |
+
- num_epochs: 15
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 5.2965 | 0.19 | 50 | 4.4784 |
|
| 52 |
+
| 4.7649 | 0.38 | 100 | 4.3439 |
|
| 53 |
+
| 4.4907 | 0.57 | 150 | 4.0077 |
|
| 54 |
+
| 4.3973 | 0.76 | 200 | 3.2143 |
|
| 55 |
+
| 3.4084 | 0.95 | 250 | 2.6818 |
|
| 56 |
+
| 2.7091 | 1.14 | 300 | 2.3603 |
|
| 57 |
+
| 2.4601 | 1.33 | 350 | 1.9004 |
|
| 58 |
+
| 2.1096 | 1.52 | 400 | 1.5639 |
|
| 59 |
+
| 1.6941 | 1.7 | 450 | 1.3240 |
|
| 60 |
+
| 1.4949 | 1.89 | 500 | 1.1247 |
|
| 61 |
+
| 1.2246 | 2.08 | 550 | 1.0421 |
|
| 62 |
+
| 1.4479 | 2.27 | 600 | 1.1546 |
|
| 63 |
+
| 1.1327 | 2.46 | 650 | 1.1098 |
|
| 64 |
+
| 1.1184 | 2.65 | 700 | 0.8950 |
|
| 65 |
+
| 1.0516 | 2.84 | 750 | 0.8601 |
|
| 66 |
+
| 1.2556 | 3.03 | 800 | 0.8575 |
|
| 67 |
+
| 1.1216 | 3.22 | 850 | 0.8314 |
|
| 68 |
+
| 1.1027 | 3.41 | 900 | 1.0676 |
|
| 69 |
+
| 1.0815 | 3.6 | 950 | 0.9716 |
|
| 70 |
+
| 1.2254 | 3.79 | 1000 | 1.0091 |
|
| 71 |
+
| 0.9896 | 3.98 | 1050 | 0.7600 |
|
| 72 |
+
| 1.0736 | 4.17 | 1100 | 0.8907 |
|
| 73 |
+
| 1.2462 | 4.36 | 1150 | 0.7506 |
|
| 74 |
+
| 0.9959 | 4.55 | 1200 | 0.7623 |
|
| 75 |
+
| 1.0895 | 4.73 | 1250 | 0.7570 |
|
| 76 |
+
| 1.0736 | 4.92 | 1300 | 0.8248 |
|
| 77 |
+
| 1.1015 | 5.11 | 1350 | 0.8682 |
|
| 78 |
+
| 1.1423 | 5.3 | 1400 | 0.8340 |
|
| 79 |
+
| 1.0906 | 5.49 | 1450 | 0.8372 |
|
| 80 |
+
| 0.9333 | 5.68 | 1500 | 0.8420 |
|
| 81 |
+
| 1.1347 | 5.87 | 1550 | 0.8718 |
|
| 82 |
+
| 0.9407 | 6.06 | 1600 | 0.8270 |
|
| 83 |
+
| 0.8138 | 6.25 | 1650 | 0.8241 |
|
| 84 |
+
| 0.8731 | 6.44 | 1700 | 0.8013 |
|
| 85 |
+
| 1.0146 | 6.63 | 1750 | 0.7704 |
|
| 86 |
+
| 0.8847 | 6.82 | 1800 | 0.8885 |
|
| 87 |
+
| 1.0283 | 7.01 | 1850 | 0.8804 |
|
| 88 |
+
| 1.0359 | 7.2 | 1900 | 0.7907 |
|
| 89 |
+
| 0.987 | 7.39 | 1950 | 0.7997 |
|
| 90 |
+
| 1.0279 | 7.58 | 2000 | 0.9095 |
|
| 91 |
+
| 0.9027 | 7.77 | 2050 | 0.6823 |
|
| 92 |
+
| 0.927 | 7.95 | 2100 | 0.6728 |
|
| 93 |
+
| 1.0499 | 8.14 | 2150 | 0.6537 |
|
| 94 |
+
| 0.9774 | 8.33 | 2200 | 0.6455 |
|
| 95 |
+
| 0.9171 | 8.52 | 2250 | 0.6456 |
|
| 96 |
+
| 1.0002 | 8.71 | 2300 | 0.6723 |
|
| 97 |
+
| 0.9052 | 8.9 | 2350 | 0.6554 |
|
| 98 |
+
| 0.9029 | 9.09 | 2400 | 0.7272 |
|
| 99 |
+
| 1.0247 | 9.28 | 2450 | 0.6997 |
|
| 100 |
+
| 0.8296 | 9.47 | 2500 | 0.6661 |
|
| 101 |
+
| 1.0659 | 9.66 | 2550 | 0.7914 |
|
| 102 |
+
| 1.0226 | 9.85 | 2600 | 0.7823 |
|
| 103 |
+
| 0.9419 | 10.04 | 2650 | 0.7709 |
|
| 104 |
+
| 0.9008 | 10.23 | 2700 | 0.8114 |
|
| 105 |
+
| 0.826 | 10.42 | 2750 | 0.7042 |
|
| 106 |
+
| 0.7957 | 10.61 | 2800 | 0.7764 |
|
| 107 |
+
| 1.0086 | 10.8 | 2850 | 0.8362 |
|
| 108 |
+
| 1.0076 | 10.98 | 2900 | 0.8048 |
|
| 109 |
+
| 0.9613 | 11.17 | 2950 | 0.6945 |
|
| 110 |
+
| 0.9155 | 11.36 | 3000 | 0.7011 |
|
| 111 |
+
| 0.9436 | 11.55 | 3050 | 0.6524 |
|
| 112 |
+
| 0.9134 | 11.74 | 3100 | 0.6582 |
|
| 113 |
+
| 0.817 | 11.93 | 3150 | 0.6678 |
|
| 114 |
+
| 0.8545 | 12.12 | 3200 | 0.6520 |
|
| 115 |
+
| 0.9801 | 12.31 | 3250 | 0.7813 |
|
| 116 |
+
| 0.8566 | 12.5 | 3300 | 0.7205 |
|
| 117 |
+
| 0.8966 | 12.69 | 3350 | 0.6326 |
|
| 118 |
+
| 0.8705 | 12.88 | 3400 | 0.6577 |
|
| 119 |
+
| 0.8193 | 13.07 | 3450 | 0.6391 |
|
| 120 |
+
| 0.8099 | 13.26 | 3500 | 0.6658 |
|
| 121 |
+
| 0.921 | 13.45 | 3550 | 0.6535 |
|
| 122 |
+
| 0.7915 | 13.64 | 3600 | 0.6576 |
|
| 123 |
+
| 1.1439 | 13.83 | 3650 | 0.6593 |
|
| 124 |
+
| 0.8702 | 14.02 | 3700 | 0.6519 |
|
| 125 |
+
| 0.73 | 14.2 | 3750 | 0.6403 |
|
| 126 |
+
| 0.8306 | 14.39 | 3800 | 0.6393 |
|
| 127 |
+
| 0.8678 | 14.58 | 3850 | 0.6405 |
|
| 128 |
+
| 1.0003 | 14.77 | 3900 | 0.6407 |
|
| 129 |
+
| 1.023 | 14.96 | 3950 | 0.6402 |
|
| 130 |
|
| 131 |
|
| 132 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 166518476
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d64cf3f7ac3b9551f8169aa24cda660f2cb4ada3ab11accd25107f430f563d87
|
| 3 |
size 166518476
|
runs/Nov26_03-10-59_susnato-desktop/events.out.tfevents.1700948461.susnato-desktop.27893.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f88483c22083926ac547554f9581f67577f71af6806d35bf4be158a11e8172
|
| 3 |
+
size 40586
|