Update README.md

README.md

@@ -91,12 +91,12 @@ pipeline_tag: image-segmentation
 <br>
 
 <div style="border:1px solid black; padding:25px; background-color:#FDFFF4 ; padding-top:10px; padding-bottom:1px;">
-  <h1>FLAIR-INC_rgbie_15cl_resnet34-unet</h1> 
-  <p>The general characteristics of this specific model <strong>FLAIR-INC_rgbie_15cl_resnet34-unet</strong> are :</p>
+  <h1>FLAIR-INC_rgb_15cl_mitb5-unet</h1> 
+  <p>The general characteristics of this specific model <strong>FLAIR-INC_rgb_15cl_mitb5-unet</strong> are :</p>
   <ul style="list-style-type:disc;">
     <li>Trained with the FLAIR-INC dataset</li>
-    <li>RGBIE images (true colours + infrared + elevation)</li>
-    <li>U-Net with a Resnet-34 encoder</li>
+    <li>RGB images (true colours)</li>
+    <li>U-Net with a mitb5 encoder</li>
     <li>15 class nomenclature : [building, pervious surface, impervious surface, bare soil, water, coniferous, deciduous, brushwood, vineyard, herbaceous, agricultural land, plowed land, swimming pool, snow, greenhouse]</li>
   </ul>
 </div>
@@ -119,17 +119,13 @@ The product called ([BD ORTHO®](https://geoservices.ign.fr/bdortho)) has its ow
 Consequently, the model’s prediction would improve if the user images are similar to the original ones.
 
 _**Radiometry of input images**_ :
-The BD ORTHO input images are distributed in 8-bit encoding format per channel. When traning the model, input normalization was performed (see section **Trainingg Details**). 
+The BD ORTHO input images are distributed in 8-bit encoding format per channel. When traning the model, input normalization was performed (see section **Training Details**). 
 It is recommended that the user apply the same type of input normalization while inferring the model.
 
 _**Multi-domain model**_ :
 The FLAIR-INC dataset that was used for training is composed of 75 radiometric domains. In the case of aerial images, domain shifts are frequent and are mainly due to : the date of acquisition of the aerial survey (from april to november), the spatial domain (equivalent to a french department administrative division) and downstream radiometric processing.
 By construction (sampling 75 domains) the model is robust to these shifts, and can be applied to any images of the ([BD ORTHO® product](https://geoservices.ign.fr/bdortho)).
 
-_**Specification for the Elevation channel**_ :
-The fifth dimension of the RGBIE images is the Elevation (height of building and vegetation). This information is encoded in a 8-bit encoding format. 
-When decoded to [0,255] ints, a difference of 1 should coresponds to 0.2 meters step of elevation difference.   
-
 
 _**Land Cover classes of prediction**_ :
 The orginial class nomenclature of the FLAIR Dataset encompasses 19 classes (See the [FLAIR dataset](https://huggingface.co/datasets/IGNF/FLAIR) page for details).
@@ -141,15 +137,15 @@ As a result, the logits produced by the model are of size 19x1, but classes n°
 ## Bias, Risks, Limitations and Recommendations
 
 _**Using the model on input images with other spatial resolution**_ :
-The FLAIR-INC_rgbie_15cl_resnet34-unet model was trained with fixed scale conditions. All patches used for training are derived from aerial images with 0.2 meters spatial resolution. Only flip and rotate augmentations were performed during the training process.  
+The FLAIR-INC_rgb_15cl_mitb5-unet model was trained with fixed scale conditions. All patches used for training are derived from aerial images with 0.2 meters spatial resolution. Only flip and rotate augmentations were performed during the training process.  
 No data augmentation method concerning scale change was used during training. The user should pay attention that generalization issues can occur while applying this model to images that have different spatial resolutions.
 
 _**Using the model for other remote sensing sensors**_ :
-The FLAIR-INC_rgbie_15cl_resnet34-unet model was trained with aerial images of the ([BD ORTHO® product](https://geoservices.ign.fr/bdortho)) that encopass very specific radiometric image processing. 
+The FLAIR-INC_rgb_15cl_mitb5-unet model was trained with aerial images of the ([BD ORTHO® product](https://geoservices.ign.fr/bdortho)) that encopass very specific radiometric image processing. 
 Using the model on other type of aerial images or satellite images may imply the use of transfer learning or domain adaptation techniques.
 
 _**Using the model on other spatial areas**_ :
-The FLAIR-INC_rgbie_15cl_resnet34-unet model was trained on patches reprensenting the French Metropolitan territory. 
+The FLAIR-INC_rgb_15cl_mitb5-unet model was trained on patches reprensenting the French Metropolitan territory. 
 The user should be aware that applying the model to other type of landscapes may imply a drop in model metrics.  
 
 ---
@@ -166,7 +162,7 @@ Fine-tuning and prediction tasks are detailed in the README file.
 
 ### Training Data
 
-218 400 patches of 512 x 512 pixels were used to train the **FLAIR-INC_RVBIE_resnet34_unet_15cl_norm** model. 
+218 400 patches of 512 x 512 pixels were used to train the **FLAIR-INC_rgb_15cl_mitb5-unet** model. 
 The train/validation split was performed patchwise to obtain a 80% / 20% distribution between train and validation. 
 Annotation was performed at the _zone_ level (~100 patches per _zone_). Spatial independancy between patches is guaranted as patches from the same _zone_ were assigned to the same set (TRAIN or VALIDATION). 
 The following number of patches were used for train and validation :
@@ -204,8 +200,8 @@ Statistics of the TRAIN+VALIDATION set :
   * HorizontalFlip(p=0.5)
   * RandomRotate90(p=0.5)
 * Input normalization (mean=0 | std=1):
-  * norm_means: [105.08, 110.87, 101.82, 106.38, 53.26]
-  * norm_stds: [52.17, 45.38, 44, 39.69, 79.3]
+  * norm_means: [105.08, 110.87, 101.82]
+  * norm_stds: [52.17, 45.38, 44]
 * Seed: 2022
 * Batch size: 10
 * Number of epochs : 200
@@ -218,7 +214,7 @@ Statistics of the TRAIN+VALIDATION set :
 
 #### Speeds, Sizes, Times
 
-The FLAIR-INC_rgbie_15cl_resnet34-unet model was trained on a HPC/AI resources provided by GENCI-IDRIS (Grant 2022-A0131013803). 
+The FLAIR-INC_rgb_15cl_mitb5-unet model was trained on a HPC/AI resources provided by GENCI-IDRIS (Grant 2022-A0131013803). 
 16 V100 GPUs were used ( 4 nodes, 4 GPUS per node). With this configuration the approximate learning time is 6 minutes per epoch.
 
 FLAIR-INC_rgbie_15cl_resnet34-unet was obtained for num_epoch=76 with corresponding val_loss=0.56. 
@@ -248,37 +244,34 @@ As a result the _Snow_ class is absent from the TEST set.
 
 #### Metrics
 
-With the evaluation protocol, the **FLAIR-INC_RVBIE_resnet34_unet_15cl_norm** have been evaluated to **OA= 76.37%** and **mIoU=58.63%**. 
+With the evaluation protocol, the **FLAIR-INC_rgb_15cl_mitb5-unetm** have been evaluated to **OA= 75.87%** and **mIoU=53.44%**. 
 The _snow_ class is discarded from the average metrics.
 
 The following table give the class-wise metrics :
 
-| Modalities              |   IoU (%)    | Fscore (%)  | Precision (%)  | Recall (%)  |
+| Classes              |   IoU (%)    | Fscore (%)  | Precision (%)  | Recall (%)  |
 | ----------------------- | ----------|---------|---------|---------|
-| building        	      |  82.63    |  90.49  |  90.26  |  90.72  |
-| pervious surface        |  53.24    |  69.48  |  68.97  |  70.00  |
-| impervious surface      |  74.17	  |  85.17  |  86.28  |  84.09  |
-| bare soil               |  60.40	  |  75.31  |  80.49  |  70.75  |
-| water                   |  87.59    |  93.38  |  93.16  |  93.61  |
-| coniferous        	  |  46.35    |  63.34  |  63.52  |  63.16  |
-| deciduous               |  67.45    |  80.56  |  77.44  |  83.94  |
-| brushwood               |  30.23	  |  46.43  |  63.55  |  36.58  |
-| vineyard                |  82.93	  |  90.67  |  91.35  |  89.99  |
-| herbaceous vegetation   |  55.03    |  70.99  |  70.59  |  71.40  |
-| agricultural land       |  52.01    |  68.43  |  59.18  |  81.12  |
-| plowed land             |  40.84    |  57.99  |  68.28  |  50.40  |
-| swimming_pool           |  48.44    |  65.27  |  81.62  |  54.37  |
-| _snow_                    |  _00.00_    |  _00.00_  |  _00.00_  |  _00.00_  |
-| greenhouse              |  39.45    |  56.57  |  45.52  |  74.72  |
+|  building   		    |   77.933   |   87.598   |   87.358   |   87.839   |
+|  pervious_surface   	|   55.060    |   71.018   |   73.758   |   68.474   |
+|  impervious_surface   |   71.639   |   83.477   |   82.315   |   84.671   |
+|  bare_soil   	        |   63.670    |   77.803   |   78.465   |   77.152   |
+|  water   		        |   85.011   |   91.899   |   90.641   |   93.192   |
+|  coniferous   	    |   58.907   |   74.140   |   77.911   |   70.717   |
+|  deciduous   	        |   69.909   |   82.290   |   78.461   |   86.511   |
+|  brushwood   	        |   29.254   |   45.266   |   59.845   |   36.398   |
+|  vineyard   		    |   77.993   |   87.636   |   84.002   |   91.599   |
+|  herbaceous   	    |   50.343   |   66.971   |   71.301   |   63.136   |
+|  agricultural_land    |   58.801   |   74.056   |   66.961   |   82.832   |
+|  plowed_land   	    |   42.202   |   59.355   |   65.114   |   54.532   |
+|  swimming_pool   	    |   0.000    |   0.000    |   0.000   |   0.000   |
+|  snow   		        |   _0.000_   |   _0.000_   |   _0.000_   |   _0.000_   |
+|  greenhouse   	    |   60.884   |   75.687   |   66.62   |   87.609   |
 | **average**             |  **58.63**    |  **72.44**  |  **74.3**  |  **72.49**  |
 
 
 
 
 
-
-
-
 The following illustration gives the resulting confusion matrix :
 * Top : normalised acording to columns, columns sum at 100% and the **precision** is on the diagonal of the matrix
 * Bottom : normalised acording to rows, rows sum at 100% and the **recall** is on the diagonal of the matrix