Skip to content

Webapp using imagenet weights for prediction instead of the new trained weights #14

@pdsing

Description

@pdsing

The main.py is using the imagenet weights instead if the new trained model weights. In the function, upload file is not importing the model with the updated weights.

Look at the model being used -
model= ResNet50(weights='imagenet')

@app.route('/uploaded', methods = ['GET', 'POST']) def upload_file(): if request.method == 'POST': f = request.files['file'] path = os.path.join(app.config['UPLOAD_FOLDER'], f.filename) model= ResNet50(weights='imagenet') img = image.load_img(path, target_size=(224,224)) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) preds = model.predict(x) preds_decoded = decode_predictions(preds, top=3)[0] print(decode_predictions(preds, top=3)[0]) f.save(path) return render_template('uploaded.html', title='Success', predictions=preds_decoded, user_image=f.filename)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions