mujerry commited on
Commit
45a37a1
·
verified ·
1 Parent(s): 8f74a83

Log hyper-parameters, metric curves, and model state for deeplabv3plus-1024_run_2026-06-27_15-02

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ performance_curves.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: mit
4
+ tags:
5
+ - semantic-segmentation
6
+ - pytorch
7
+ - deeplabv3plus
8
+ - resnet34
9
+ - agricultural-cv
10
+ model-index:
11
+ - name: deeplabv3plus-1024_run_2026-06-27_15-02
12
+ results:
13
+ - task:
14
+ type: semantic-segmentation
15
+ name: Corm Segmentation
16
+ metrics:
17
+ - type: mean_iou
18
+ value: 0.9413518003361036
19
+ name: Best Val Mean IoU
20
+ - type: damage_iou
21
+ value: 0.8581994876991125
22
+ name: Best Val Damage-Class IoU
23
+ - type: corm_iou
24
+ value: 0.9676700661101357
25
+ name: Best Val Corm-Class IoU
26
+ ---
27
+
28
+ # DeepLabV3+ Corm & Damage Semantic Segmentation Model
29
+
30
+ This repository contains weights, performance curves, and hyperparameter logs for experiment `deeplabv3plus-1024_run_2026-06-27_15-02`.
31
+
32
+ ## Model Summary
33
+ - **Architecture Type:** DeepLabV3+ (SMP wrapper)
34
+ - **Backbone Encoder:** `resnet34`
35
+ - **Pretrained Weights:** `imagenet`
36
+ - **Input Channels:** 3
37
+ - **Number of Classes:** 3 (0: background, 1: damage, 2: corm)
38
+ - **Training Resolution:** `1024x1024`
39
+ - **Loss Optimizer configuration:** `CrossEntropy`
40
+
41
+ ## Metrics Curves
42
+ Below are the training performance plots generated for this run:
43
+ ![Performance Curves](performance_curves.png)
checkpoint-13134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a5fc256b440b0305a19528ca1d8b0643cc6ba5d1e23d6486601970d7bc4f09
3
+ size 89865828
checkpoint-13134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7c2ae47768ab78d33ce65b95f85f79e0bdd5473c91c261aed5ae12e2c6b2a7
3
+ size 179625803
checkpoint-13134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8e64ba6bca52049556e043ce60de9de3cc4102688ac5e8c8205e4ef82ec9b8
3
+ size 14645
checkpoint-13134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd37e423e6757992fcd068a87dfd56e75ee1ee9bcdd6541a60ba23d069d4822
3
+ size 1465
checkpoint-13134/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05451be1b5c65142c74bb78fe97a154a4def5c9fa9339b7957e20a744d54c66
3
+ size 5329
checkpoint-13200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1774a10da8b333e65d89d4ea2aa95c5bb09277b0fc1216022c2eba4fb2998c82
3
+ size 89865828
checkpoint-13200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c43802b8c6defd7f3d6d5be01c34843cf0423ce139d085dc7ab8635a5164f8
3
+ size 179625803
checkpoint-13200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d85f054af2d1fbf8c6a4c083629d6e7d6db1616c43990db202f555dd9fefce9
3
+ size 14645
checkpoint-13200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4187364dd6359e816c88a216cbd14f44180ad2216aebcd6ccc82794eaeddd4
3
+ size 1465
checkpoint-13200/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05451be1b5c65142c74bb78fe97a154a4def5c9fa9339b7957e20a744d54c66
3
+ size 5329
checkpoint-8052/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327fd0b4788bfd20ef08fd56138a8572865a311531abb69f4618770fffa1a98d
3
+ size 89865828
checkpoint-8052/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7262a14f8729da9930fd3735a9b629aa847001845f220adafe649c85149be838
3
+ size 179625803
checkpoint-8052/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b62a2acac5a8b664e19e2aae13162ed4b38b5bb16e9c71c29989262b67cfe5
3
+ size 14645
checkpoint-8052/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38759e8b9b97cf159ada428115950fb8d974d596fae0d4209dcdd09afcb4437
3
+ size 1465
checkpoint-8052/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8052/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05451be1b5c65142c74bb78fe97a154a4def5c9fa9339b7957e20a744d54c66
3
+ size 5329
config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "DeepLabV3Plus",
3
+ "encoder_name": "resnet34",
4
+ "encoder_weights": "imagenet",
5
+ "in_channels": 3,
6
+ "classes": 3,
7
+ "input_resolution": "1024x1024",
8
+ "loss_type": "CrossEntropy"
9
+ }
performance_curves.png ADDED

Git LFS Details

  • SHA256: 538a1ac0fe402f18a6195d1ba4a0a784084e4cfe8accf31113e222ce98e2a84d
  • Pointer size: 131 Bytes
  • Size of remote file: 176 kB
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0b8c6112de3256e21453cd18d754f2b289a384fe88eb534e685cb842481811
3
+ size 89937719
training_metrics.csv ADDED
The diff for this file is too large to render. See raw diff