Hugging Face's logo

samitizerxu
/
segformer-b3-from-scratch-final

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
samitizerxu commited on
Commit
85b81aa
•
1 Parent(s): dc533d2

End of training

Browse files
Files changed (4) hide show
  1. README.md +379 -198
  2. config.json +69 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md CHANGED
@@ -1,201 +1,382 @@
1
  ---
2
- library_name: transformers
3
- tags: []
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
200
-
201
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - vision
4
+ - image-segmentation
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: segformer-b3-from-scratch-final
8
+ results: []
9
  ---
10
 
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # segformer-b3-from-scratch-final
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the samitizerxu/kelp_data_rgbagg_swin_nir_int_cleaned dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Iou Kelp: 0.0073
19
+ - Loss: 0.9864
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - num_epochs: 60
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Iou Kelp | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
50
+ | 0.9993 | 0.18 | 100 | 0.0069 | 0.9867 |
51
+ | 0.9945 | 0.37 | 200 | 0.0076 | 0.9855 |
52
+ | 0.9991 | 0.55 | 300 | 0.0069 | 0.9867 |
53
+ | 0.999 | 0.74 | 400 | 0.0066 | 0.9870 |
54
+ | 0.9959 | 0.92 | 500 | 0.0071 | 0.9864 |
55
+ | 0.9965 | 1.11 | 600 | 0.0066 | 0.9871 |
56
+ | 0.9764 | 1.29 | 700 | 0.0066 | 0.9871 |
57
+ | 0.9951 | 1.48 | 800 | 0.0066 | 0.9871 |
58
+ | 0.9999 | 1.66 | 900 | 0.0066 | 0.9870 |
59
+ | 0.9878 | 1.85 | 1000 | 0.0066 | 0.9871 |
60
+ | 0.9978 | 2.03 | 1100 | 0.0066 | 0.9871 |
61
+ | 0.975 | 2.21 | 1200 | 0.0069 | 0.9868 |
62
+ | 0.9957 | 2.4 | 1300 | 0.0073 | 0.9859 |
63
+ | 0.9914 | 2.58 | 1400 | 0.0079 | 0.9860 |
64
+ | 0.9928 | 2.77 | 1500 | 0.0074 | 0.9859 |
65
+ | 0.9994 | 2.95 | 1600 | 0.0004 | 0.9863 |
66
+ | 0.995 | 3.14 | 1700 | 0.0101 | 0.9860 |
67
+ | 0.9963 | 3.32 | 1800 | 0.0 | 0.9872 |
68
+ | 0.9972 | 3.51 | 1900 | 0.0074 | 0.9858 |
69
+ | 0.9959 | 3.69 | 2000 | 0.0076 | 0.9859 |
70
+ | 0.9941 | 3.87 | 2100 | 0.0073 | 0.9859 |
71
+ | 0.992 | 4.06 | 2200 | 0.0002 | 0.9951 |
72
+ | 0.9903 | 4.24 | 2300 | 0.0073 | 0.9859 |
73
+ | 0.9989 | 4.43 | 2400 | 0.0066 | 0.9871 |
74
+ | 0.9999 | 4.61 | 2500 | 0.0073 | 0.9866 |
75
+ | 0.9946 | 4.8 | 2600 | 0.0073 | 0.9859 |
76
+ | 0.9959 | 4.98 | 2700 | 0.0073 | 0.9859 |
77
+ | 0.9971 | 5.17 | 2800 | 0.0079 | 0.9863 |
78
+ | 0.9949 | 5.35 | 2900 | 0.0074 | 0.9859 |
79
+ | 0.9846 | 5.54 | 3000 | 0.0073 | 0.9859 |
80
+ | 0.9941 | 5.72 | 3100 | 0.0074 | 0.9859 |
81
+ | 0.9867 | 5.9 | 3200 | 0.0074 | 0.9858 |
82
+ | 0.9857 | 6.09 | 3300 | 0.0074 | 0.9861 |
83
+ | 0.9986 | 6.27 | 3400 | 0.0074 | 0.9859 |
84
+ | 0.9927 | 6.46 | 3500 | 0.0074 | 0.9860 |
85
+ | 0.998 | 6.64 | 3600 | 0.0075 | 0.9858 |
86
+ | 0.9971 | 6.83 | 3700 | 0.0074 | 0.9859 |
87
+ | 0.9951 | 7.01 | 3800 | 0.0074 | 0.9859 |
88
+ | 0.9998 | 7.2 | 3900 | 0.0074 | 0.9861 |
89
+ | 0.995 | 7.38 | 4000 | 0.0075 | 0.9858 |
90
+ | 0.9912 | 7.56 | 4100 | 0.0072 | 0.9861 |
91
+ | 0.9995 | 7.75 | 4200 | 0.0074 | 0.9858 |
92
+ | 0.9934 | 7.93 | 4300 | 0.0074 | 0.9860 |
93
+ | 0.9885 | 8.12 | 4400 | 0.0074 | 0.9860 |
94
+ | 0.9937 | 8.3 | 4500 | 0.0075 | 0.9857 |
95
+ | 0.9954 | 8.49 | 4600 | 0.0075 | 0.9857 |
96
+ | 0.9794 | 8.67 | 4700 | 0.0074 | 0.9858 |
97
+ | 0.9967 | 8.86 | 4800 | 0.0075 | 0.9857 |
98
+ | 0.9954 | 9.04 | 4900 | 0.0074 | 0.9862 |
99
+ | 0.9966 | 9.23 | 5000 | 0.0074 | 0.9859 |
100
+ | 0.9953 | 9.41 | 5100 | 0.0074 | 0.9859 |
101
+ | 0.9961 | 9.59 | 5200 | 0.0074 | 0.9859 |
102
+ | 0.993 | 9.78 | 5300 | 0.0075 | 0.9858 |
103
+ | 0.9993 | 9.96 | 5400 | 0.0070 | 0.9870 |
104
+ | 0.995 | 10.15 | 5500 | 0.0032 | 0.9933 |
105
+ | 0.9945 | 10.33 | 5600 | 0.0061 | 0.9884 |
106
+ | 0.9738 | 10.52 | 5700 | 0.0069 | 0.9866 |
107
+ | 0.9983 | 10.7 | 5800 | 0.0067 | 0.9869 |
108
+ | 0.9975 | 10.89 | 5900 | 0.0076 | 0.9854 |
109
+ | 0.9925 | 11.07 | 6000 | 0.0086 | 0.9839 |
110
+ | 0.9821 | 11.25 | 6100 | 0.0092 | 0.9822 |
111
+ | 0.9972 | 11.44 | 6200 | 0.0107 | 0.9787 |
112
+ | 0.9802 | 11.62 | 6300 | 0.0109 | 0.9781 |
113
+ | 1.0 | 11.81 | 6400 | 0.0076 | 0.9854 |
114
+ | 0.9922 | 11.99 | 6500 | 0.0108 | 0.9793 |
115
+ | 0.9915 | 12.18 | 6600 | 0.0108 | 0.9799 |
116
+ | 0.9963 | 12.36 | 6700 | 0.0075 | 0.9857 |
117
+ | 0.9966 | 12.55 | 6800 | 0.0075 | 0.9859 |
118
+ | 0.9978 | 12.73 | 6900 | 0.0069 | 0.9870 |
119
+ | 0.9847 | 12.92 | 7000 | 0.0074 | 0.9860 |
120
+ | 0.9972 | 13.1 | 7100 | 0.0072 | 0.9862 |
121
+ | 0.9868 | 13.28 | 7200 | 0.0071 | 0.9865 |
122
+ | 0.9961 | 13.47 | 7300 | 0.0072 | 0.9864 |
123
+ | 0.9845 | 13.65 | 7400 | 0.0071 | 0.9865 |
124
+ | 0.9974 | 13.84 | 7500 | 0.0074 | 0.9862 |
125
+ | 0.9906 | 14.02 | 7600 | 0.0076 | 0.9847 |
126
+ | 0.9999 | 14.21 | 7700 | 0.0075 | 0.9860 |
127
+ | 0.9821 | 14.39 | 7800 | 0.0074 | 0.9860 |
128
+ | 0.9976 | 14.58 | 7900 | 0.0105 | 0.9795 |
129
+ | 0.9871 | 14.76 | 8000 | 0.0103 | 0.9803 |
130
+ | 0.991 | 14.94 | 8100 | 0.0102 | 0.9805 |
131
+ | 0.9903 | 15.13 | 8200 | 0.0104 | 0.9799 |
132
+ | 0.995 | 15.31 | 8300 | 0.0074 | 0.9861 |
133
+ | 0.9981 | 15.5 | 8400 | 0.0073 | 0.9863 |
134
+ | 0.9985 | 15.68 | 8500 | 0.0073 | 0.9863 |
135
+ | 0.9973 | 15.87 | 8600 | 0.0074 | 0.9862 |
136
+ | 0.989 | 16.05 | 8700 | 0.0073 | 0.9863 |
137
+ | 0.9938 | 16.24 | 8800 | 0.0074 | 0.9860 |
138
+ | 0.9951 | 16.42 | 8900 | 0.0106 | 0.9786 |
139
+ | 0.9921 | 16.61 | 9000 | 0.0092 | 0.9824 |
140
+ | 0.9971 | 16.79 | 9100 | 0.0083 | 0.9846 |
141
+ | 0.9846 | 16.97 | 9200 | 0.0087 | 0.9838 |
142
+ | 0.9849 | 17.16 | 9300 | 0.0095 | 0.9820 |
143
+ | 0.9851 | 17.34 | 9400 | 0.0096 | 0.9818 |
144
+ | 0.9902 | 17.53 | 9500 | 0.0099 | 0.9811 |
145
+ | 0.9889 | 17.71 | 9600 | 0.0075 | 0.9860 |
146
+ | 0.9782 | 17.9 | 9700 | 0.0075 | 0.9908 |
147
+ | 0.999 | 18.08 | 9800 | 0.0074 | 0.9862 |
148
+ | 0.9878 | 18.27 | 9900 | 0.0073 | 0.9862 |
149
+ | 0.999 | 18.45 | 10000 | 0.0074 | 0.9862 |
150
+ | 1.0 | 18.63 | 10100 | 0.0074 | 0.9861 |
151
+ | 0.9951 | 18.82 | 10200 | 0.0075 | 0.9859 |
152
+ | 0.9892 | 19.0 | 10300 | 0.0073 | 0.9861 |
153
+ | 0.9853 | 19.19 | 10400 | 0.0074 | 0.9859 |
154
+ | 0.9959 | 19.37 | 10500 | 0.0074 | 0.9859 |
155
+ | 0.9999 | 19.56 | 10600 | 0.0073 | 0.9861 |
156
+ | 0.9872 | 19.74 | 10700 | 0.0074 | 0.9859 |
157
+ | 0.9939 | 19.93 | 10800 | 0.0074 | 0.9861 |
158
+ | 0.9924 | 20.11 | 10900 | 0.0073 | 0.9862 |
159
+ | 0.9993 | 20.3 | 11000 | 0.0074 | 0.9860 |
160
+ | 0.9934 | 20.48 | 11100 | 0.0075 | 0.9858 |
161
+ | 0.9976 | 20.66 | 11200 | 0.0074 | 0.9859 |
162
+ | 0.9878 | 20.85 | 11300 | 0.0074 | 0.9859 |
163
+ | 0.9955 | 21.03 | 11400 | 0.0074 | 0.9859 |
164
+ | 0.9878 | 21.22 | 11500 | 0.0075 | 0.9859 |
165
+ | 0.999 | 21.4 | 11600 | 0.0074 | 0.9859 |
166
+ | 0.9945 | 21.59 | 11700 | 0.0074 | 0.9861 |
167
+ | 0.994 | 21.77 | 11800 | 0.0075 | 0.9859 |
168
+ | 0.9848 | 21.96 | 11900 | 0.0075 | 0.9859 |
169
+ | 0.9998 | 22.14 | 12000 | 0.0075 | 0.9859 |
170
+ | 0.9826 | 22.32 | 12100 | 0.0075 | 0.9859 |
171
+ | 0.999 | 22.51 | 12200 | 0.0074 | 0.9861 |
172
+ | 0.9941 | 22.69 | 12300 | 0.0073 | 0.9863 |
173
+ | 0.9933 | 22.88 | 12400 | 0.0074 | 0.9862 |
174
+ | 0.9935 | 23.06 | 12500 | 0.0074 | 0.9862 |
175
+ | 0.9992 | 23.25 | 12600 | 0.0073 | 0.9863 |
176
+ | 0.9943 | 23.43 | 12700 | 0.0073 | 0.9863 |
177
+ | 0.9777 | 23.62 | 12800 | 0.0075 | 0.9858 |
178
+ | 0.9977 | 23.8 | 12900 | 0.0073 | 0.9862 |
179
+ | 0.9925 | 23.99 | 13000 | 0.0074 | 0.9861 |
180
+ | 0.9866 | 24.17 | 13100 | 0.0073 | 0.9863 |
181
+ | 0.9979 | 24.35 | 13200 | 0.0073 | 0.9862 |
182
+ | 0.9819 | 24.54 | 13300 | 0.0073 | 0.9864 |
183
+ | 0.966 | 24.72 | 13400 | 0.0073 | 0.9864 |
184
+ | 0.998 | 24.91 | 13500 | 0.0073 | 0.9863 |
185
+ | 0.9969 | 25.09 | 13600 | 0.0073 | 0.9863 |
186
+ | 0.9881 | 25.28 | 13700 | 0.0073 | 0.9863 |
187
+ | 0.9701 | 25.46 | 13800 | 0.0073 | 0.9864 |
188
+ | 0.9963 | 25.65 | 13900 | 0.0073 | 0.9863 |
189
+ | 0.9885 | 25.83 | 14000 | 0.0073 | 0.9863 |
190
+ | 0.9904 | 26.01 | 14100 | 0.0073 | 0.9864 |
191
+ | 0.9976 | 26.2 | 14200 | 0.0074 | 0.9862 |
192
+ | 0.995 | 26.38 | 14300 | 0.0073 | 0.9863 |
193
+ | 0.9886 | 26.57 | 14400 | 0.0073 | 0.9864 |
194
+ | 0.9735 | 26.75 | 14500 | 0.0073 | 0.9863 |
195
+ | 0.988 | 26.94 | 14600 | 0.0073 | 0.9864 |
196
+ | 0.9854 | 27.12 | 14700 | 0.0073 | 0.9864 |
197
+ | 0.9947 | 27.31 | 14800 | 0.0073 | 0.9864 |
198
+ | 0.9944 | 27.49 | 14900 | 0.0073 | 0.9864 |
199
+ | 0.9935 | 27.68 | 15000 | 0.0073 | 0.9862 |
200
+ | 0.9887 | 27.86 | 15100 | 0.0073 | 0.9863 |
201
+ | 0.9958 | 28.04 | 15200 | 0.0073 | 0.9862 |
202
+ | 0.9994 | 28.23 | 15300 | 0.0073 | 0.9863 |
203
+ | 0.9953 | 28.41 | 15400 | 0.0073 | 0.9868 |
204
+ | 0.9798 | 28.6 | 15500 | 0.0073 | 0.9863 |
205
+ | 0.9867 | 28.78 | 15600 | 0.0073 | 0.9863 |
206
+ | 0.9903 | 28.97 | 15700 | 0.0073 | 0.9863 |
207
+ | 0.9943 | 29.15 | 15800 | 0.0073 | 0.9864 |
208
+ | 0.9725 | 29.34 | 15900 | 0.0072 | 0.9864 |
209
+ | 0.9987 | 29.52 | 16000 | 0.0073 | 0.9864 |
210
+ | 0.9871 | 29.7 | 16100 | 0.0072 | 0.9864 |
211
+ | 0.992 | 29.89 | 16200 | 0.0072 | 0.9864 |
212
+ | 0.996 | 30.07 | 16300 | 0.0073 | 0.9864 |
213
+ | 0.9998 | 30.26 | 16400 | 0.0073 | 0.9864 |
214
+ | 0.9964 | 30.44 | 16500 | 0.0074 | 0.9859 |
215
+ | 0.9992 | 30.63 | 16600 | 0.0075 | 0.9858 |
216
+ | 0.9946 | 30.81 | 16700 | 0.0074 | 0.9861 |
217
+ | 0.9911 | 31.0 | 16800 | 0.0075 | 0.9859 |
218
+ | 0.9878 | 31.18 | 16900 | 0.0075 | 0.9859 |
219
+ | 0.9826 | 31.37 | 17000 | 0.0075 | 0.9859 |
220
+ | 0.9894 | 31.55 | 17100 | 0.0075 | 0.9859 |
221
+ | 0.9887 | 31.73 | 17200 | 0.0075 | 0.9860 |
222
+ | 0.9962 | 31.92 | 17300 | 0.0073 | 0.9862 |
223
+ | 0.9937 | 32.1 | 17400 | 0.0073 | 0.9863 |
224
+ | 0.9828 | 32.29 | 17500 | 0.0073 | 0.9863 |
225
+ | 0.993 | 32.47 | 17600 | 0.0073 | 0.9864 |
226
+ | 0.9975 | 32.66 | 17700 | 0.0073 | 0.9864 |
227
+ | 0.994 | 32.84 | 17800 | 0.0073 | 0.9864 |
228
+ | 0.9894 | 33.03 | 17900 | 0.0073 | 0.9862 |
229
+ | 0.9938 | 33.21 | 18000 | 0.0073 | 0.9863 |
230
+ | 0.9711 | 33.39 | 18100 | 0.0073 | 0.9863 |
231
+ | 0.9896 | 33.58 | 18200 | 0.0073 | 0.9864 |
232
+ | 0.9907 | 33.76 | 18300 | 0.0073 | 0.9864 |
233
+ | 0.9934 | 33.95 | 18400 | 0.0073 | 0.9864 |
234
+ | 0.9723 | 34.13 | 18500 | 0.0073 | 0.9864 |
235
+ | 0.9842 | 34.32 | 18600 | 0.0073 | 0.9864 |
236
+ | 0.9955 | 34.5 | 18700 | 0.0073 | 0.9864 |
237
+ | 0.9824 | 34.69 | 18800 | 0.0073 | 0.9864 |
238
+ | 0.9949 | 34.87 | 18900 | 0.0073 | 0.9864 |
239
+ | 0.9943 | 35.06 | 19000 | 0.0073 | 0.9864 |
240
+ | 0.9992 | 35.24 | 19100 | 0.0073 | 0.9864 |
241
+ | 0.9843 | 35.42 | 19200 | 0.0073 | 0.9864 |
242
+ | 0.9785 | 35.61 | 19300 | 0.0073 | 0.9864 |
243
+ | 0.9999 | 35.79 | 19400 | 0.0073 | 0.9864 |
244
+ | 0.9727 | 35.98 | 19500 | 0.0073 | 0.9864 |
245
+ | 0.9949 | 36.16 | 19600 | 0.0073 | 0.9864 |
246
+ | 0.9949 | 36.35 | 19700 | 0.0073 | 0.9864 |
247
+ | 0.9887 | 36.53 | 19800 | 0.0073 | 0.9864 |
248
+ | 0.9736 | 36.72 | 19900 | 0.0073 | 0.9864 |
249
+ | 0.9966 | 36.9 | 20000 | 0.0073 | 0.9864 |
250
+ | 0.9984 | 37.08 | 20100 | 0.0073 | 0.9864 |
251
+ | 0.993 | 37.27 | 20200 | 0.0073 | 0.9864 |
252
+ | 0.9998 | 37.45 | 20300 | 0.0073 | 0.9864 |
253
+ | 0.9972 | 37.64 | 20400 | 0.0073 | 0.9864 |
254
+ | 0.986 | 37.82 | 20500 | 0.0073 | 0.9864 |
255
+ | 0.9914 | 38.01 | 20600 | 0.0073 | 0.9864 |
256
+ | 0.9954 | 38.19 | 20700 | 0.0073 | 0.9864 |
257
+ | 0.9764 | 38.38 | 20800 | 0.0073 | 0.9864 |
258
+ | 0.9953 | 38.56 | 20900 | 0.0073 | 0.9864 |
259
+ | 0.9837 | 38.75 | 21000 | 0.0073 | 0.9864 |
260
+ | 0.9665 | 38.93 | 21100 | 0.0073 | 0.9864 |
261
+ | 0.9964 | 39.11 | 21200 | 0.0073 | 0.9864 |
262
+ | 0.9935 | 39.3 | 21300 | 0.0073 | 0.9864 |
263
+ | 0.9466 | 39.48 | 21400 | 0.0073 | 0.9864 |
264
+ | 0.9853 | 39.67 | 21500 | 0.0073 | 0.9864 |
265
+ | 0.9678 | 39.85 | 21600 | 0.0073 | 0.9864 |
266
+ | 0.995 | 40.04 | 21700 | 0.0073 | 0.9864 |
267
+ | 0.9987 | 40.22 | 21800 | 0.0073 | 0.9864 |
268
+ | 0.9935 | 40.41 | 21900 | 0.0073 | 0.9864 |
269
+ | 0.991 | 40.59 | 22000 | 0.0073 | 0.9864 |
270
+ | 0.999 | 40.77 | 22100 | 0.0073 | 0.9864 |
271
+ | 0.9985 | 40.96 | 22200 | 0.0073 | 0.9864 |
272
+ | 0.9954 | 41.14 | 22300 | 0.0073 | 0.9864 |
273
+ | 0.9894 | 41.33 | 22400 | 0.0073 | 0.9864 |
274
+ | 0.9851 | 41.51 | 22500 | 0.0073 | 0.9864 |
275
+ | 0.9882 | 41.7 | 22600 | 0.0073 | 0.9864 |
276
+ | 0.9999 | 41.88 | 22700 | 0.0073 | 0.9864 |
277
+ | 0.9901 | 42.07 | 22800 | 0.0073 | 0.9864 |
278
+ | 0.9853 | 42.25 | 22900 | 0.0073 | 0.9864 |
279
+ | 0.9868 | 42.44 | 23000 | 0.0073 | 0.9864 |
280
+ | 0.9973 | 42.62 | 23100 | 0.0073 | 0.9864 |
281
+ | 0.9979 | 42.8 | 23200 | 0.0073 | 0.9865 |
282
+ | 0.9867 | 42.99 | 23300 | 0.0073 | 0.9864 |
283
+ | 0.9994 | 43.17 | 23400 | 0.0073 | 0.9864 |
284
+ | 0.9984 | 43.36 | 23500 | 0.0073 | 0.9865 |
285
+ | 0.9974 | 43.54 | 23600 | 0.0073 | 0.9865 |
286
+ | 0.9999 | 43.73 | 23700 | 0.0073 | 0.9864 |
287
+ | 0.9669 | 43.91 | 23800 | 0.0073 | 0.9864 |
288
+ | 0.9925 | 44.1 | 23900 | 0.0073 | 0.9864 |
289
+ | 0.9961 | 44.28 | 24000 | 0.0073 | 0.9864 |
290
+ | 0.9815 | 44.46 | 24100 | 0.0073 | 0.9864 |
291
+ | 0.9968 | 44.65 | 24200 | 0.0073 | 0.9864 |
292
+ | 0.9964 | 44.83 | 24300 | 0.0073 | 0.9864 |
293
+ | 0.9929 | 45.02 | 24400 | 0.0073 | 0.9864 |
294
+ | 0.9712 | 45.2 | 24500 | 0.0073 | 0.9864 |
295
+ | 0.9884 | 45.39 | 24600 | 0.0073 | 0.9864 |
296
+ | 0.9897 | 45.57 | 24700 | 0.0073 | 0.9864 |
297
+ | 0.9862 | 45.76 | 24800 | 0.0073 | 0.9865 |
298
+ | 0.9768 | 45.94 | 24900 | 0.0073 | 0.9865 |
299
+ | 0.9965 | 46.13 | 25000 | 0.0073 | 0.9865 |
300
+ | 0.9996 | 46.31 | 25100 | 0.0073 | 0.9864 |
301
+ | 0.9887 | 46.49 | 25200 | 0.0073 | 0.9864 |
302
+ | 0.9991 | 46.68 | 25300 | 0.0073 | 0.9864 |
303
+ | 0.984 | 46.86 | 25400 | 0.0073 | 0.9864 |
304
+ | 0.983 | 47.05 | 25500 | 0.0073 | 0.9864 |
305
+ | 0.9997 | 47.23 | 25600 | 0.0073 | 0.9864 |
306
+ | 0.9923 | 47.42 | 25700 | 0.0073 | 0.9865 |
307
+ | 0.9962 | 47.6 | 25800 | 0.0073 | 0.9864 |
308
+ | 0.9747 | 47.79 | 25900 | 0.0073 | 0.9864 |
309
+ | 0.9981 | 47.97 | 26000 | 0.0073 | 0.9864 |
310
+ | 0.9936 | 48.15 | 26100 | 0.0073 | 0.9864 |
311
+ | 0.9976 | 48.34 | 26200 | 0.0073 | 0.9864 |
312
+ | 0.9601 | 48.52 | 26300 | 0.0073 | 0.9865 |
313
+ | 0.9881 | 48.71 | 26400 | 0.0073 | 0.9864 |
314
+ | 0.9919 | 48.89 | 26500 | 0.0073 | 0.9864 |
315
+ | 0.9748 | 49.08 | 26600 | 0.0073 | 0.9864 |
316
+ | 0.9862 | 49.26 | 26700 | 0.0073 | 0.9864 |
317
+ | 0.9935 | 49.45 | 26800 | 0.0073 | 0.9864 |
318
+ | 0.9402 | 49.63 | 26900 | 0.0073 | 0.9864 |
319
+ | 0.9982 | 49.82 | 27000 | 0.0073 | 0.9864 |
320
+ | 0.9619 | 50.0 | 27100 | 0.0073 | 0.9864 |
321
+ | 0.9935 | 50.18 | 27200 | 0.0073 | 0.9864 |
322
+ | 0.9962 | 50.37 | 27300 | 0.0073 | 0.9864 |
323
+ | 0.9888 | 50.55 | 27400 | 0.0073 | 0.9864 |
324
+ | 0.9956 | 50.74 | 27500 | 0.0073 | 0.9864 |
325
+ | 0.9981 | 50.92 | 27600 | 0.0073 | 0.9864 |
326
+ | 0.9992 | 51.11 | 27700 | 0.0073 | 0.9865 |
327
+ | 0.9613 | 51.29 | 27800 | 0.0073 | 0.9864 |
328
+ | 0.9721 | 51.48 | 27900 | 0.0072 | 0.9865 |
329
+ | 0.9938 | 51.66 | 28000 | 0.0073 | 0.9865 |
330
+ | 0.9998 | 51.85 | 28100 | 0.0073 | 0.9864 |
331
+ | 0.9981 | 52.03 | 28200 | 0.0073 | 0.9864 |
332
+ | 0.9793 | 52.21 | 28300 | 0.0073 | 0.9864 |
333
+ | 0.9962 | 52.4 | 28400 | 0.0073 | 0.9864 |
334
+ | 0.9728 | 52.58 | 28500 | 0.0073 | 0.9864 |
335
+ | 0.9965 | 52.77 | 28600 | 0.0073 | 0.9864 |
336
+ | 0.9937 | 52.95 | 28700 | 0.0073 | 0.9864 |
337
+ | 0.9942 | 53.14 | 28800 | 0.0073 | 0.9864 |
338
+ | 0.9902 | 53.32 | 28900 | 0.0073 | 0.9864 |
339
+ | 0.9992 | 53.51 | 29000 | 0.0073 | 0.9864 |
340
+ | 0.9954 | 53.69 | 29100 | 0.0073 | 0.9864 |
341
+ | 0.991 | 53.87 | 29200 | 0.0073 | 0.9864 |
342
+ | 0.9955 | 54.06 | 29300 | 0.0073 | 0.9864 |
343
+ | 0.9978 | 54.24 | 29400 | 0.0073 | 0.9864 |
344
+ | 0.9998 | 54.43 | 29500 | 0.0073 | 0.9864 |
345
+ | 0.9716 | 54.61 | 29600 | 0.0073 | 0.9864 |
346
+ | 0.9891 | 54.8 | 29700 | 0.0073 | 0.9864 |
347
+ | 0.9984 | 54.98 | 29800 | 0.0073 | 0.9864 |
348
+ | 0.9756 | 55.17 | 29900 | 0.0073 | 0.9864 |
349
+ | 0.9901 | 55.35 | 30000 | 0.0073 | 0.9864 |
350
+ | 0.9866 | 55.54 | 30100 | 0.0073 | 0.9864 |
351
+ | 0.9908 | 55.72 | 30200 | 0.0073 | 0.9864 |
352
+ | 0.977 | 55.9 | 30300 | 0.0073 | 0.9864 |
353
+ | 0.9882 | 56.09 | 30400 | 0.0073 | 0.9864 |
354
+ | 0.9903 | 56.27 | 30500 | 0.0073 | 0.9864 |
355
+ | 0.9819 | 56.46 | 30600 | 0.0073 | 0.9864 |
356
+ | 0.9883 | 56.64 | 30700 | 0.0073 | 0.9864 |
357
+ | 0.9922 | 56.83 | 30800 | 0.0073 | 0.9864 |
358
+ | 0.9788 | 57.01 | 30900 | 0.0073 | 0.9864 |
359
+ | 0.9756 | 57.2 | 31000 | 0.0073 | 0.9864 |
360
+ | 0.9955 | 57.38 | 31100 | 0.0073 | 0.9864 |
361
+ | 0.9925 | 57.56 | 31200 | 0.0073 | 0.9864 |
362
+ | 0.9976 | 57.75 | 31300 | 0.0073 | 0.9864 |
363
+ | 0.9938 | 57.93 | 31400 | 0.0073 | 0.9864 |
364
+ | 0.9905 | 58.12 | 31500 | 0.0073 | 0.9864 |
365
+ | 0.9819 | 58.3 | 31600 | 0.0073 | 0.9864 |
366
+ | 0.9827 | 58.49 | 31700 | 0.0073 | 0.9864 |
367
+ | 0.9927 | 58.67 | 31800 | 0.0073 | 0.9864 |
368
+ | 0.9953 | 58.86 | 31900 | 0.0073 | 0.9864 |
369
+ | 0.9937 | 59.04 | 32000 | 0.0073 | 0.9864 |
370
+ | 0.9961 | 59.23 | 32100 | 0.0073 | 0.9864 |
371
+ | 0.9886 | 59.41 | 32200 | 0.0073 | 0.9864 |
372
+ | 0.9906 | 59.59 | 32300 | 0.0073 | 0.9864 |
373
+ | 0.9811 | 59.78 | 32400 | 0.0073 | 0.9864 |
374
+ | 0.9977 | 59.96 | 32500 | 0.0073 | 0.9864 |
375
+
376
+
377
+ ### Framework versions
378
+
379
+ - Transformers 4.37.2
380
+ - Pytorch 2.2.0
381
+ - Datasets 2.17.0
382
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SegformerForKelpSemanticSegmentation"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "classifier_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 768,
8
+ "depths": [
9
+ 3,
10
+ 4,
11
+ 18,
12
+ 3
13
+ ],
14
+ "downsampling_rates": [
15
+ 1,
16
+ 4,
17
+ 8,
18
+ 16
19
+ ],
20
+ "drop_path_rate": 0.1,
21
+ "hidden_act": "gelu",
22
+ "hidden_dropout_prob": 0.0,
23
+ "hidden_sizes": [
24
+ 64,
25
+ 128,
26
+ 320,
27
+ 512
28
+ ],
29
+ "image_size": 350,
30
+ "initializer_range": 0.02,
31
+ "layer_norm_eps": 1e-06,
32
+ "mlp_ratios": [
33
+ 4,
34
+ 4,
35
+ 4,
36
+ 4
37
+ ],
38
+ "model_type": "segformer",
39
+ "num_attention_heads": [
40
+ 1,
41
+ 2,
42
+ 5,
43
+ 8
44
+ ],
45
+ "num_channels": 3,
46
+ "num_encoder_blocks": 4,
47
+ "patch_sizes": [
48
+ 7,
49
+ 3,
50
+ 3,
51
+ 3
52
+ ],
53
+ "reshape_last_stage": true,
54
+ "semantic_loss_ignore_index": 255,
55
+ "sr_ratios": [
56
+ 8,
57
+ 4,
58
+ 2,
59
+ 1
60
+ ],
61
+ "strides": [
62
+ 4,
63
+ 2,
64
+ 2,
65
+ 2
66
+ ],
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.37.2"
69
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f4566f0da415ff0cf94ba17f9706141f55a93439ffd69c0fcd6931016c9dd2
3
+ size 188979776
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a917c0cc2ae291ee13fa0079b0ffd10f59e9b2505f4a6d9b0c7363c6c99e89
3
+ size 4792