Training in progress epoch 0

README.md

@@ -15,18 +15,18 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: nan
-- Validation Loss: nan
-- Validation Mean Iou: 0.0425
-- Validation Mean Accuracy: 1.0
-- Validation Overall Accuracy: 1.0
-- Validation Accuracy Unlabeled: 1.0
-- Validation Accuracy Objeto Interes: nan
-- Validation Accuracy Agua: nan
-- Validation Iou Unlabeled: 0.0425
-- Validation Iou Objeto Interes: nan
-- Validation Iou Agua: nan
-- Epoch: 1
+- Train Loss: 0.6580
+- Validation Loss: 0.6718
+- Validation Mean Iou: 0.4196
+- Validation Mean Accuracy: 0.6281
+- Validation Overall Accuracy: 0.8767
+- Validation Accuracy Unlabeled: 0.0254
+- Validation Accuracy Objeto Interes: 0.9466
+- Validation Accuracy Agua: 0.9124
+- Validation Iou Unlabeled: 0.0232
+- Validation Iou Objeto Interes: 0.3345
+- Validation Iou Agua: 0.9012
+- Epoch: 0
 
 ## Model description
 
@@ -52,8 +52,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Accuracy Unlabeled | Validation Accuracy Objeto Interes | Validation Accuracy Agua | Validation Iou Unlabeled | Validation Iou Objeto Interes | Validation Iou Agua | Epoch |
 |:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:-----------------------------:|:----------------------------------:|:------------------------:|:------------------------:|:-----------------------------:|:-------------------:|:-----:|
-| nan        | nan             | 0.0425              | 1.0                      | 1.0                         | 1.0                           | nan                                | nan                      | 0.0425                   | nan                           | nan                 | 0     |
-| nan        | nan             | 0.0425              | 1.0                      | 1.0                         | 1.0                           | nan                                | nan                      | 0.0425                   | nan                           | nan                 | 1     |
+| 0.6580     | 0.6718          | 0.4196              | 0.6281                   | 0.8767                      | 0.0254                        | 0.9466                             | 0.9124                   | 0.0232                   | 0.3345                        | 0.9012              | 0     |
 
 
 ### Framework versions

preprocessor_config.json

@@ -1,8 +1,8 @@
 {
   "do_normalize": true,
   "do_reduce_labels": false,
-  "do_rescale": false,
-  "do_resize": false,
+  "do_rescale": true,
+  "do_resize": true,
   "image_mean": [
     0.485,
     0.456,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa12aba4742e7e3cede1fc187f04e30b2864dc846d87b5b6281334d5336702d4
+oid sha256:9e028bedcbc7fc8e7bda54188bf6aacb7b67bc284ae843d4c60f4adeb2ffa33b
 size 54991500