uisikdag
/

weed_resnet_balanced

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

uisikdag commited on Mar 9, 2023

Commit

c9fad26

•

1 Parent(s): 55cb01e

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8678571428571429
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/resnet-152](https://huggingface.co/microsoft/resnet-152) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4372
-- Accuracy: 0.8679
 ## Model description
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.4335        | 1.0   | 69   | 2.4087          | 0.2375   |
-| 2.3043        | 2.0   | 138  | 2.2215          | 0.3339   |
-| 1.8342        | 3.0   | 207  | 1.6984          | 0.5786   |
-| 1.4059        | 4.0   | 276  | 1.1954          | 0.6804   |
-| 1.0081        | 5.0   | 345  | 0.8756          | 0.7482   |
-| 0.8916        | 6.0   | 414  | 0.6818          | 0.8232   |
-| 0.7313        | 7.0   | 483  | 0.5369          | 0.8482   |
-| 0.6677        | 8.0   | 552  | 0.5223          | 0.8554   |
-| 0.6206        | 9.0   | 621  | 0.4609          | 0.8732   |
-| 0.6543        | 10.0  | 690  | 0.4372          | 0.8679   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.7766666666666666
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [microsoft/resnet-152](https://huggingface.co/microsoft/resnet-152) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.2397
+- Accuracy: 0.7767
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.4803        | 0.99  | 37   | 2.4724          | 0.1133   |
+| 2.4464        | 1.99  | 74   | 2.4305          | 0.2967   |
+| 2.3843        | 2.99  | 111  | 2.3658          | 0.4233   |
+| 2.3018        | 3.99  | 148  | 2.2287          | 0.5067   |
+| 2.1075        | 4.99  | 185  | 2.0144          | 0.5967   |
+| 1.8743        | 5.99  | 222  | 1.7228          | 0.65     |
+| 1.7114        | 6.99  | 259  | 1.5487          | 0.6833   |
+| 1.5345        | 7.99  | 296  | 1.3920          | 0.7267   |
+| 1.4471        | 8.99  | 333  | 1.2914          | 0.7333   |
+| 1.3994        | 9.99  | 370  | 1.2397          | 0.7767   |
 ### Framework versions