Update README.md
Browse files
README.md
CHANGED
@@ -90,7 +90,7 @@ pipeline_tag: image-segmentation
|
|
90 |
</div>
|
91 |
<br>
|
92 |
|
93 |
-
<div style="border:
|
94 |
<h1>FLAIR-INC_RVBIE_resnet34_unet_15cl_norm model</h1>
|
95 |
<p>The general characteristics of this specific model <strong>FLAIR-INC_RVBIE_resnet34_unet_15cl_norm</strong> are :</p>
|
96 |
<ul style="list-style-type:disc;">
|
@@ -224,15 +224,11 @@ The FLAIR-INC_RVBIE_resnet34_unet_15cl_norm model was trained on a HPC/AI resour
|
|
224 |
FLAIR-INC_RVBIE_resnet34_unet_15cl_norm was obtained for num_epoch=76 with corresponding val_loss=0.56.
|
225 |
|
226 |
|
227 |
-
<div style="
|
228 |
-
<div style="width: 45%;">
|
229 |
<p>TRAIN loss</p>
|
230 |
-
<img src="train_loss_FLAIR-INC_RGBIE_resnet34_unet_15cl_norm.png" alt="drawing" style="width:
|
231 |
-
</div>
|
232 |
-
<div style="width: 45%;">
|
233 |
<p>VALIDATION loss</p>
|
234 |
-
<img src="val_loss_FLAIR-INC_RGBIE_resnet34_unet_15cl_norm.png" alt="drawing" style="width:
|
235 |
-
</div>
|
236 |
</div>
|
237 |
|
238 |
|
@@ -287,18 +283,15 @@ The following illustration gives the resulting confusion matrix :
|
|
287 |
* Right : normalised acording to rows, rows sum at 100% and the **recall** is on the diagonal of the matrix
|
288 |
|
289 |
|
290 |
-
<div style="
|
291 |
-
|
292 |
-
<
|
293 |
-
<
|
294 |
-
|
295 |
-
<div style="width: 45%;">
|
296 |
-
<p>Normalised Confusion Matrix (recall)</p>
|
297 |
-
<img src="FLAIR-INC_RVBIE_resnet34_unet_15cl_norm_cm-recall.png" alt="drawing" style="width: 100%;"/>
|
298 |
-
</div>
|
299 |
</div>
|
300 |
|
301 |
|
|
|
302 |
### Results
|
303 |
|
304 |
Samples of results
|
|
|
90 |
</div>
|
91 |
<br>
|
92 |
|
93 |
+
<div style="border:1px solid black; padding:25px; background-color:#FDFFF4 ; padding-top:10px; padding-bottom:1px;">
|
94 |
<h1>FLAIR-INC_RVBIE_resnet34_unet_15cl_norm model</h1>
|
95 |
<p>The general characteristics of this specific model <strong>FLAIR-INC_RVBIE_resnet34_unet_15cl_norm</strong> are :</p>
|
96 |
<ul style="list-style-type:disc;">
|
|
|
224 |
FLAIR-INC_RVBIE_resnet34_unet_15cl_norm was obtained for num_epoch=76 with corresponding val_loss=0.56.
|
225 |
|
226 |
|
227 |
+
<div style="position: relative;">
|
|
|
228 |
<p>TRAIN loss</p>
|
229 |
+
<img src="train_loss_FLAIR-INC_RGBIE_resnet34_unet_15cl_norm.png" alt="drawing" style="width: 60%;"/>
|
|
|
|
|
230 |
<p>VALIDATION loss</p>
|
231 |
+
<img src="val_loss_FLAIR-INC_RGBIE_resnet34_unet_15cl_norm.png" alt="drawing" style="width: 60%;"/>
|
|
|
232 |
</div>
|
233 |
|
234 |
|
|
|
283 |
* Right : normalised acording to rows, rows sum at 100% and the **recall** is on the diagonal of the matrix
|
284 |
|
285 |
|
286 |
+
<div style="position: relative;">
|
287 |
+
<p>Normalized Confusion Matrix (precision)</p>
|
288 |
+
<img src="FLAIR-INC_RVBIE_resnet34_unet_15cl_norm_cm-precision.png" alt="drawing" style="width: 70%;"/>
|
289 |
+
<p>Normalized Confusion Matrix (recall)</p>
|
290 |
+
<img src="FLAIR-INC_RVBIE_resnet34_unet_15cl_norm_cm-recall.png" alt="drawing" style="width: 70%;"/>
|
|
|
|
|
|
|
|
|
291 |
</div>
|
292 |
|
293 |
|
294 |
+
|
295 |
### Results
|
296 |
|
297 |
Samples of results
|