StatsGary commited on
Commit
42983d3
1 Parent(s): 4561b68

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -114
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -21,7 +20,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.903
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,118 +28,14 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # VIT-food101-image-classifier
31
 
32
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.6312
35
- - Accuracy: 0.903
36
 
37
  ## Model description
38
 
39
- Model trained on the food classification dataset trained on labels:
40
-
41
- 0 apple_pie
42
- 1 baby_back_ribs
43
- 2 baklava
44
- 3 beef_carpaccio
45
- 4 beef_tartare
46
- 5 beet_salad
47
- 6 beignets
48
- 7 bibimbap
49
- 8 bread_pudding
50
- 9 breakfast_burrito
51
- 10 bruschetta
52
- 11 caesar_salad
53
- 12 cannoli
54
- 13 caprese_salad
55
- 14 carrot_cake
56
- 15 ceviche
57
- 16 cheesecake
58
- 17 cheese_plate
59
- 18 chicken_curry
60
- 19 chicken_quesadilla
61
- 20 chicken_wings
62
- 21 chocolate_cake
63
- 22 chocolate_mousse
64
- 23 churros
65
- 24 clam_chowder
66
- 25 club_sandwich
67
- 26 crab_cakes
68
- 27 creme_brulee
69
- 28 croque_madame
70
- 29 cup_cakes
71
- 30 deviled_eggs
72
- 31 donuts
73
- 32 dumplings
74
- 33 edamame
75
- 34 eggs_benedict
76
- 35 escargots
77
- 36 falafel
78
- 37 filet_mignon
79
- 38 fish_and_chips
80
- 39 foie_gras
81
- 40 french_fries
82
- 41 french_onion_soup
83
- 42 french_toast
84
- 43 fried_calamari
85
- 44 fried_rice
86
- 45 frozen_yogurt
87
- 46 garlic_bread
88
- 47 gnocchi
89
- 48 greek_salad
90
- 49 grilled_cheese_sandwich
91
- 50 grilled_salmon
92
- 51 guacamole
93
- 52 gyoza
94
- 53 hamburger
95
- 54 hot_and_sour_soup
96
- 55 hot_dog
97
- 56 huevos_rancheros
98
- 57 hummus
99
- 58 ice_cream
100
- 59 lasagna
101
- 60 lobster_bisque
102
- 61 lobster_roll_sandwich
103
- 62 macaroni_and_cheese
104
- 63 macarons
105
- 64 miso_soup
106
- 65 mussels
107
- 66 nachos
108
- 67 omelette
109
- 68 onion_rings
110
- 69 oysters
111
- 70 pad_thai
112
- 71 paella
113
- 72 pancakes
114
- 73 panna_cotta
115
- 74 peking_duck
116
- 75 pho
117
- 76 pizza
118
- 77 pork_chop
119
- 78 poutine
120
- 79 prime_rib
121
- 80 pulled_pork_sandwich
122
- 81 ramen
123
- 82 ravioli
124
- 83 red_velvet_cake
125
- 84 risotto
126
- 85 samosa
127
- 86 sashimi
128
- 87 scallops
129
- 88 seaweed_salad
130
- 89 shrimp_and_grits
131
- 90 spaghetti_bolognese
132
- 91 spaghetti_carbonara
133
- 92 spring_rolls
134
- 93 steak
135
- 94 strawberry_shortcake
136
- 95 sushi
137
- 96 tacos
138
- 97 takoyaki
139
- 98 tiramisu
140
- 99 tuna_tartare
141
- 100 waffles
142
-
143
- The model is then used to detect new images and produce a classification based on what it thinks is in the model.
144
 
145
  ## Intended uses & limitations
146
 
@@ -164,15 +59,17 @@ The following hyperparameters were used during training:
164
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
165
  - lr_scheduler_type: linear
166
  - lr_scheduler_warmup_ratio: 0.1
167
- - num_epochs: 3
168
 
169
  ### Training results
170
 
171
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
172
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
173
- | 2.6787 | 0.99 | 62 | 2.5274 | 0.847 |
174
- | 1.8204 | 1.99 | 124 | 1.8050 | 0.883 |
175
- | 1.5946 | 2.99 | 186 | 1.6312 | 0.903 |
 
 
176
 
177
 
178
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
 
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
+ value: 0.933
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
 
29
  # VIT-food101-image-classifier
30
 
31
+ This model was trained from scratch on the food101 dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 0.5661
34
+ - Accuracy: 0.933
35
 
36
  ## Model description
37
 
38
+ More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
 
40
  ## Intended uses & limitations
41
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 5
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.1716 | 0.99 | 62 | 1.2149 | 0.896 |
69
+ | 0.7758 | 1.99 | 124 | 0.8727 | 0.906 |
70
+ | 0.6269 | 2.99 | 186 | 0.6833 | 0.928 |
71
+ | 0.5495 | 3.99 | 248 | 0.6041 | 0.931 |
72
+ | 0.4973 | 4.99 | 310 | 0.5661 | 0.933 |
73
 
74
 
75
  ### Framework versions