paul
commited on
Commit
·
7ee9c17
1
Parent(s):
19d4f45
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: microsoft-resnet-50-cartoon-emotion-detection
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Image Classification
|
| 17 |
+
type: image-classification
|
| 18 |
+
dataset:
|
| 19 |
+
name: imagefolder
|
| 20 |
+
type: imagefolder
|
| 21 |
+
config: default
|
| 22 |
+
split: train
|
| 23 |
+
args: default
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Accuracy
|
| 26 |
+
type: accuracy
|
| 27 |
+
value: 0.6697247706422018
|
| 28 |
+
- name: Precision
|
| 29 |
+
type: precision
|
| 30 |
+
value: 0.5798801171844885
|
| 31 |
+
- name: Recall
|
| 32 |
+
type: recall
|
| 33 |
+
value: 0.6697247706422018
|
| 34 |
+
- name: F1
|
| 35 |
+
type: f1
|
| 36 |
+
value: 0.6086361803243947
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 40 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 41 |
+
|
| 42 |
+
# microsoft-resnet-50-cartoon-emotion-detection
|
| 43 |
+
|
| 44 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
|
| 45 |
+
It achieves the following results on the evaluation set:
|
| 46 |
+
- Loss: 1.0059
|
| 47 |
+
- Accuracy: 0.6697
|
| 48 |
+
- Precision: 0.5799
|
| 49 |
+
- Recall: 0.6697
|
| 50 |
+
- F1: 0.6086
|
| 51 |
+
|
| 52 |
+
## Model description
|
| 53 |
+
|
| 54 |
+
More information needed
|
| 55 |
+
|
| 56 |
+
## Intended uses & limitations
|
| 57 |
+
|
| 58 |
+
More information needed
|
| 59 |
+
|
| 60 |
+
## Training and evaluation data
|
| 61 |
+
|
| 62 |
+
More information needed
|
| 63 |
+
|
| 64 |
+
## Training procedure
|
| 65 |
+
|
| 66 |
+
### Training hyperparameters
|
| 67 |
+
|
| 68 |
+
The following hyperparameters were used during training:
|
| 69 |
+
- learning_rate: 0.00012
|
| 70 |
+
- train_batch_size: 64
|
| 71 |
+
- eval_batch_size: 64
|
| 72 |
+
- seed: 42
|
| 73 |
+
- gradient_accumulation_steps: 4
|
| 74 |
+
- total_train_batch_size: 256
|
| 75 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 76 |
+
- lr_scheduler_type: linear
|
| 77 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 78 |
+
- num_epochs: 20
|
| 79 |
+
|
| 80 |
+
### Training results
|
| 81 |
+
|
| 82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 84 |
+
| No log | 0.97 | 8 | 1.3833 | 0.2477 | 0.2054 | 0.2477 | 0.2042 |
|
| 85 |
+
| 1.4276 | 1.97 | 16 | 1.3711 | 0.3028 | 0.1982 | 0.3028 | 0.1932 |
|
| 86 |
+
| 1.4046 | 2.97 | 24 | 1.3550 | 0.3028 | 0.0917 | 0.3028 | 0.1407 |
|
| 87 |
+
| 1.3817 | 3.97 | 32 | 1.3375 | 0.3119 | 0.2852 | 0.3119 | 0.1592 |
|
| 88 |
+
| 1.3562 | 4.97 | 40 | 1.3179 | 0.3211 | 0.4337 | 0.3211 | 0.1785 |
|
| 89 |
+
| 1.3562 | 5.97 | 48 | 1.2991 | 0.3761 | 0.5442 | 0.3761 | 0.2741 |
|
| 90 |
+
| 1.3624 | 6.97 | 56 | 1.2751 | 0.4495 | 0.5593 | 0.4495 | 0.3659 |
|
| 91 |
+
| 1.2914 | 7.97 | 64 | 1.2494 | 0.4771 | 0.5442 | 0.4771 | 0.4094 |
|
| 92 |
+
| 1.2518 | 8.97 | 72 | 1.2279 | 0.5046 | 0.5525 | 0.5046 | 0.4430 |
|
| 93 |
+
| 1.2085 | 9.97 | 80 | 1.1905 | 0.5321 | 0.5134 | 0.5321 | 0.4579 |
|
| 94 |
+
| 1.2085 | 10.97 | 88 | 1.1602 | 0.5505 | 0.5151 | 0.5505 | 0.4872 |
|
| 95 |
+
| 1.1865 | 11.97 | 96 | 1.1307 | 0.5963 | 0.5969 | 0.5963 | 0.5416 |
|
| 96 |
+
| 1.122 | 12.97 | 104 | 1.1037 | 0.5872 | 0.5069 | 0.5872 | 0.5206 |
|
| 97 |
+
| 1.0812 | 13.97 | 112 | 1.0797 | 0.5688 | 0.4868 | 0.5688 | 0.5068 |
|
| 98 |
+
| 1.0449 | 14.97 | 120 | 1.0712 | 0.6239 | 0.5269 | 0.6239 | 0.5641 |
|
| 99 |
+
| 1.0449 | 15.97 | 128 | 1.0425 | 0.6239 | 0.5123 | 0.6239 | 0.5517 |
|
| 100 |
+
| 1.0458 | 16.97 | 136 | 1.0346 | 0.6239 | 0.6487 | 0.6239 | 0.5782 |
|
| 101 |
+
| 1.004 | 17.97 | 144 | 1.0264 | 0.6330 | 0.5472 | 0.6330 | 0.5721 |
|
| 102 |
+
| 0.9806 | 18.97 | 152 | 1.0041 | 0.6606 | 0.6334 | 0.6606 | 0.6069 |
|
| 103 |
+
| 0.97 | 19.97 | 160 | 1.0059 | 0.6697 | 0.5799 | 0.6697 | 0.6086 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.24.0.dev0
|
| 109 |
+
- Pytorch 1.11.0+cu102
|
| 110 |
+
- Datasets 2.6.1
|
| 111 |
+
- Tokenizers 0.13.1
|