Image Classification from TensorFlow

Tensorflow |

Image Classification from TensorFlow

Image Analysis

Run
About
API Example

Step 1: Upload your data

Upload Training Images

Drag your file(s) or upload

Your file can be in the following formats:zip

The training data are the images that will train your classification model, 20% of this data will be used for validation. The training data should consist of a zipped folder named 'data' that contains a sub folder named after each of your class labels. Each sub folder should contain images of the type corresponding to the subfolder's name. Images should any of '.bmp', '.gif', '.jpeg', '.jpg', '.png' files. data.zip/ ├─ data/ │ ├─ class1/ │ │ ├─ image1.jpg │ │ ├─ image2.jpg │ │ ├─ image3.jpg │ │ ├─ ... │ ├─ class2/ │ ├─ class3/ │ ├─ .../

Don’t have a file?

Use our demo data to run

Use Demo Data

Step 2: Set Parameters

Augment Training Data

Include fine-tuning

Epochs

100

500

Pretrained model

mobilenet_v2_100_224

Step 3: Complete run profile

Job name - Optional

Image classification models have millions of parameters. Training them from scratch requires a lot of labelled training data and a lot of computing power. Transfer learning is a technique that shortcuts much of this by taking a piece of a model that has already been trained on a related task and reusing it in a new model. Model saving and GPU access available soon.

Example use case: Lesion, tumour, bacteria, animal etc. classification

Technology: Pretrained models from TensorFlow Hub.

Metrics: All models trained on the ImageNet dataset containing 14,197,122 images labelled under 1000 classes.

Citation:

von Chamier, L., Laine, R.F., Jukkala, J. et al. Democratising deep learning for microscopy with ZeroCostDL4Mic. Nat Commun 12, 2276 (2021). https://doi.org/10.1038/s41467-021-22518-0

Released:
Nov-18-2022

Previous Job Parameters

Your previous job parameters will show up here
so you can keep track of your jobs

Results

Parameters