Source: https://daphnislabs.com/services/deep-learning

# Deep Learning Development

Neural-network development for image, sequence and text tasks, from dataset preparation and fine-tuning to inference integration.

[Discuss your project](https://daphnislabs.com/contact?service=deep-learning) [Try the example](https://daphnislabs.com/services/deep-learning#worked-example)

Input Hidden layers Output

Input features connected through hidden layers to a model output

Checkpoint Held-out scans Inference

## Tools & technologies

-   PyTorch or TensorFlow
-   GPU training
-   Experiment tracking
-   Model serving

## When patterns outgrow hand-written rules.

### Image understanding

Train or adapt networks for visual classification and feature extraction.

### Sequence modelling

Learn patterns in time-series or event histories with time-aware evaluation.

### Model adaptation

Fine-tune a suitable pretrained model for a narrowly defined task.

## Training work that can be reproduced.

-   **Dataset preparation code**
-   **Training configuration and checkpoints**

-   **Baseline comparison report**
-   **Inference packaging and resource profile**

## Classify a document image

Capability Example

Scanned forms arrive with mixed layouts and imperfect image quality.

### Prepare

### Adapt

### Reject

Illustrative data. Nothing is sent to an external system.

Example workspace 1 / 3

### Prepared scan

-   Source: scanner B
-   Layout: application form
-   Evaluation split: held out

Label document types and separate evaluation scans by source.

### Adapted network

-   Checkpoint: document-v1
-   Compared with baseline
-   Unfamiliar layout detected

Fine-tune a pretrained network and compare it with the baseline.

### Review record

-   Suggested type: unknown
-   Action: manual sorting
-   Failure example retained

Route low-confidence or unfamiliar layouts to manual sorting.

A document-type score and review status, with inference time and failure cases recorded.

Follow the record through the next step

## Size the network around the constraint.

### Compute budget

Set training and inference resource limits before selecting the network.

### Data coverage

Test rare layouts and real capture conditions, not only clean training images.

## Questions before we start.

### Must we train from scratch?

Usually the first comparison includes pretrained models and simpler baselines. Training from scratch needs a specific justification.

### Can a model run on a device?

Potentially. Model size, supported operators, latency and device memory need measurement on the target hardware.

[AI Development](https://daphnislabs.com/services/ai-development) [Computer Vision Development](https://daphnislabs.com/services/computer-vision) [TensorFlow Development](https://daphnislabs.com/services/tensorflow-development) [Machine Learning Development](https://daphnislabs.com/services/machine-learning)

## Bring your starting point.

Bring representative inputs, the target output and the hardware or latency constraints.

[Discuss your project](https://daphnislabs.com/contact?service=deep-learning) [Explore related services](https://daphnislabs.com/services/ai-development)

[TensorFlow Development](https://daphnislabs.com/services/tensorflow-development)