---
library_name: transformers
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr_finetuned_cppe5
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# detr_finetuned_cppe5

This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3956
- Map: 0.0065
- Map 50: 0.0182
- Map 75: 0.0036
- Map Small: 0.0006
- Map Medium: 0.014
- Map Large: 0.007
- Mar 1: 0.0123
- Mar 10: 0.0366
- Mar 100: 0.067
- Mar Small: 0.0072
- Mar Medium: 0.0388
- Mar Large: 0.0714
- Map Coverall: 0.0323
- Mar 100 Coverall: 0.3018
- Map Face Shield: 0.0
- Mar 100 Face Shield: 0.0
- Map Gloves: 0.0001
- Mar 100 Gloves: 0.0165
- Map Goggles: 0.0
- Mar 100 Goggles: 0.0062
- Map Mask: 0.0
- Mar 100 Mask: 0.0107

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3

### 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 Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
| No log        | 1.0   | 107  | 2.6211          | 0.0025 | 0.0088 | 0.0008 | 0.0       | 0.008      | 0.0025    | 0.0098 | 0.0172 | 0.0569  | 0.0       | 0.0309     | 0.0621    | 0.0124       | 0.2802           | 0.0             | 0.0025              | 0.0        | 0.0004         | 0.0         | 0.0015          | 0.0      | 0.0          |
| No log        | 2.0   | 214  | 2.4397          | 0.0058 | 0.0156 | 0.0032 | 0.0004    | 0.014      | 0.0062    | 0.0081 | 0.0352 | 0.0525  | 0.0098    | 0.0338     | 0.0524    | 0.0287       | 0.2297           | 0.0             | 0.0                 | 0.0001     | 0.029          | 0.0         | 0.0             | 0.0      | 0.0036       |
| No log        | 3.0   | 321  | 2.3956          | 0.0065 | 0.0182 | 0.0036 | 0.0006    | 0.014      | 0.007     | 0.0123 | 0.0366 | 0.067   | 0.0072    | 0.0388     | 0.0714    | 0.0323       | 0.3018           | 0.0             | 0.0                 | 0.0001     | 0.0165         | 0.0         | 0.0062          | 0.0      | 0.0107       |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0