metadata
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: queue_detection
results: []
queue_detection
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4686
- Map: 0.2556
- Map 50: 0.4262
- Map 75: 0.2687
- Map Small: -1.0
- Map Medium: 0.0006
- Map Large: 0.2572
- Mar 1: 0.2033
- Mar 10: 0.561
- Mar 100: 0.715
- Mar Small: -1.0
- Mar Medium: 0.0036
- Mar Large: 0.7212
- Map Cashier: 0.3957
- Mar 100 Cashier: 0.812
- Map Cx: 0.1154
- Mar 100 Cx: 0.618
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Cashier | Mar 100 Cashier | Map Cx | Mar 100 Cx |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 218 | 1.6672 | 0.1422 | 0.2781 | 0.1441 | -1.0 | 0.0 | 0.1427 | 0.166 | 0.421 | 0.6116 | -1.0 | 0.0 | 0.6154 | 0.2345 | 0.7322 | 0.05 | 0.4911 |
| No log | 2.0 | 436 | 1.4686 | 0.2556 | 0.4262 | 0.2687 | -1.0 | 0.0006 | 0.2572 | 0.2033 | 0.561 | 0.715 | -1.0 | 0.0036 | 0.7212 | 0.3957 | 0.812 | 0.1154 | 0.618 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1