Model save

README.md

@@ -15,29 +15,29 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8017
-- Map: 0.047
-- Map 50: 0.0888
-- Map 75: 0.0427
-- Map Small: 0.0067
-- Map Medium: 0.034
-- Map Large: 0.0524
-- Mar 1: 0.1182
-- Mar 10: 0.225
-- Mar 100: 0.2678
-- Mar Small: 0.1479
-- Mar Medium: 0.2094
-- Mar Large: 0.2727
-- Map Coverall: 0.1803
-- Mar 100 Coverall: 0.7033
+- Loss: 2.0634
+- Map: 0.0322
+- Map 50: 0.0667
+- Map 75: 0.0283
+- Map Small: 0.0054
+- Map Medium: 0.0151
+- Map Large: 0.04
+- Mar 1: 0.0872
+- Mar 10: 0.1999
+- Mar 100: 0.2514
+- Mar Small: 0.1233
+- Mar Medium: 0.222
+- Mar Large: 0.2663
+- Map Coverall: 0.1354
+- Mar 100 Coverall: 0.6728
 - Map Face Shield: 0.0
 - Mar 100 Face Shield: 0.0
-- Map Gloves: 0.022
-- Mar 100 Gloves: 0.282
+- Map Gloves: 0.0147
+- Mar 100 Gloves: 0.2185
 - Map Goggles: 0.0
 - Mar 100 Goggles: 0.0
-- Map Mask: 0.0326
-- Mar 100 Mask: 0.3534
+- Map Mask: 0.0109
+- Mar 100 Mask: 0.3656
 
 ## Model description
 
@@ -68,8 +68,8 @@ The following hyperparameters were used during training:
 
 | 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
-| No log        | 1.0   | 107  | 1.8852          | 0.0427 | 0.0861 | 0.037  | 0.0077    | 0.0297     | 0.0465    | 0.1018 | 0.2043 | 0.2509  | 0.1371    | 0.1959     | 0.257     | 0.1722       | 0.6939           | 0.0             | 0.0                 | 0.0125     | 0.2            | 0.0         | 0.0             | 0.0286   | 0.3608       |
-| No log        | 2.0   | 214  | 1.8017          | 0.047  | 0.0888 | 0.0427 | 0.0067    | 0.034      | 0.0524    | 0.1182 | 0.225  | 0.2678  | 0.1479    | 0.2094     | 0.2727    | 0.1803       | 0.7033           | 0.0             | 0.0                 | 0.022      | 0.282          | 0.0         | 0.0             | 0.0326   | 0.3534       |
+| No log        | 1.0   | 107  | 2.1727          | 0.0118 | 0.0291 | 0.0091 | 0.0052    | 0.004      | 0.0209    | 0.0375 | 0.1434 | 0.2106  | 0.0949    | 0.161      | 0.2354    | 0.0441       | 0.6311           | 0.0001          | 0.0065              | 0.0069     | 0.0961         | 0.0         | 0.0             | 0.0077   | 0.3196       |
+| No log        | 2.0   | 214  | 2.0634          | 0.0322 | 0.0667 | 0.0283 | 0.0054    | 0.0151     | 0.04      | 0.0872 | 0.1999 | 0.2514  | 0.1233    | 0.222      | 0.2663    | 0.1354       | 0.6728           | 0.0             | 0.0                 | 0.0147     | 0.2185         | 0.0         | 0.0             | 0.0109   | 0.3656       |
 
 
 ### Framework versions