Update pre-trained models

README.md

@@ -6,8 +6,8 @@ This implementation has been tested on the CamVid and Cityscapes datasets. Curre
 
 |                               Dataset                                | Classes <sup>1</sup> | Input resolution | Batch size | Epochs |   Mean IoU (%)    | GPU memory (GiB) | Training time (hours)<sup>2</sup> |
 | :------------------------------------------------------------------: | :------------------: | :--------------: | :--------: | :----: | :---------------: | :--------------: | :-------------------------------: |
-| [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/) |          11          |     480x360      |     10     |  300   | 51.08<sup>3</sup> |       4.2        |                 1                 |
-|          [Cityscapes](https://www.cityscapes-dataset.com/)           |          19          |     1024x512     |     4      |  300   | 59.03<sup>4</sup> |       5.4        |                20                 |
+| [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/) |          11          |     480x360      |     10     |  300   | 52.1<sup>3</sup> |       4.2        |                 1                 |
+|          [Cityscapes](https://www.cityscapes-dataset.com/)           |          19          |     1024x512     |     4      |  300   | 59.5<sup>4</sup> |       5.4        |                20                 |
 
 <sup>1</sup> When referring to the number of classes, the void/unlabeled class is always excluded.<br/>
 <sup>2</sup> These are just for reference. Implementation, datasets, and hardware changes can lead to very different results. Reference hardware: Nvidia GTX 1070 and an AMD Ryzen 5 3600 3.6GHz. You can also train for 100 epochs or so and get similar mean IoU (± 2%).<br/>

save/ENet_CamVid/ENet_summary.txt

@@ -1,7 +1,7 @@
 ARGUMENTS
 batch_size: 10
 dataset: camvid
-dataset_dir: ../Datasets/CamVid/
+dataset_dir: ../CamVid/
 device: cuda
 epochs: 300
 height: 360
@@ -21,5 +21,5 @@ width: 480
 workers: 4
 
 BEST VALIDATION
-Epoch: 260
-Mean IoU: 0.6407776379897647
+Epoch: 280
+Mean IoU: 0.6518655444842216

save/ENet_Cityscapes/ENet_summary.txt

@@ -1,7 +1,7 @@
 ARGUMENTS
 batch_size: 4
 dataset: cityscapes
-dataset_dir: ../Datasets/Cityscapes/1024x512/
+dataset_dir: ../Cityscapes/1024x512/
 device: cuda
 epochs: 300
 height: 512
@@ -14,12 +14,12 @@ mode: train
 name: ENet
 print_step: False
 resume: False
-save_dir: save/new_cityscapes/
+save_dir: save/cityscapes_2/
 weighing: ENet
 weight_decay: 0.0002
 width: 1024
 workers: 4
 
 BEST VALIDATION
-Epoch: 230
-Mean IoU: 0.5921075030966009
+Epoch: 250
+Mean IoU: 0.5949690267526815

save/README.md

@@ -2,20 +2,20 @@
 
 |                               Dataset                                | Classes <sup>1</sup> | Input resolution | Batch size | Epochs |   Mean IoU (%)    | GPU memory (GiB) | Training time (hours)<sup>2</sup> |
 | :------------------------------------------------------------------: | :------------------: | :--------------: | :--------: | :----: | :---------------: | :--------------: | :-------------------------------: |
-| [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/) |          11          |     480x360      |     10     |  300   | 51.08<sup>3</sup> |       4.2        |                 1                 |
-|          [Cityscapes](https://www.cityscapes-dataset.com/)           |          19          |     1024x512     |     4      |  300   | 59.03<sup>4</sup> |       5.4        |                20                 |
+| [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/) |          11          |     480x360      |     10     |  300   | 52.1<sup>3</sup> |       4.2        |                 1                 |
+|          [Cityscapes](https://www.cityscapes-dataset.com/)           |          19          |     1024x512     |     4      |  300   | 59.5<sup>4</sup> |       5.4        |                20                 |
 
 ## Per-class IoU: CamVid<sup>3</sup>
 
 |         |  Sky  | Building | Pole  | Road  | Pavement | Tree  | Sign Symbol | Fence |  Car  | Pedestrian | Bicyclist |
 | :-----: | :---: | :------: | :---: | :---: | :------: | :---: | :---------: | :---: | :---: | :--------: | :-------: |
-| IoU (%) | 89.8  |   68.2   | 19.9  | 90.1  |   71.6   | 62.7  |    17.8     | 15.1  | 65.9  |    25.8    |   34.3    |
+| IoU (%) | 90.2  |   68.6   | 22.6  | 91.5  |   73.2   | 63.6  |    19.3     | 16.7  | 65.1  |    27.2    |   35.0    |
 
 ## Per-class IoU: Cityscapes<sup>4</sup>
 
 |         | Road  | Sidewalk | Building | Wall  | Fence | Pole  | Traffic light | Traffic Sign | Vegetation | Terrain |  Sky  | Person | Rider |  Car  | Truck |  Bus  | Train | Motorcycle | Bicycle |
 | :-----: | :---: | :------: | :------: | :---: | :---: | :---: | :-----------: | :----------: | :--------: | :-----: | :---: | :----: | :---: | :---: | :---: | :---: | :---: | :--------: | :-----: |
-| IoU (%) | 96.1  |   73.9   |   86.0   | 39.5  | 41.8  | 45.6  |     43.6      |     54.9     |    88.1    |  53.5   | 90.1  |  62.5  | 41.4  | 88.3  | 41.3  | 56.9  | 34.6  |    24.1    |  59.6   |
+| IoU (%) | 96.1  |   73.3   |   85.8   | 44.1  | 40.5  | 45.3  |     42.5      |     53.9     |    87.9    |  53.5   | 90.1  |  62.3  | 44.3  | 87.6  | 46.6  | 58.2  | 34.8  |    25.8    |  57.9   |
 
 <sup>1</sup> When referring to the number of classes, the void/unlabeled class is always excluded.<br/>
 <sup>2</sup> These are just for reference. Implementation, datasets, and hardware changes can lead to very different results. Reference hardware: Nvidia GTX 1070 and an AMD Ryzen 5 3600 3.6GHz. You can also train for 100 epochs or so and get similar mean IoU (± 2%).<br/>