update readme

[ehofesmann]

This PR adds a couple small tweaks to the FiftyOne integration, primarily to the documentation:

• Documenting the various environments in which the visualize() method can be used (shell, script, Jupyter notebook, Colab, remote, etc)
• Adding a section to the README on visualizing outputs of vision tasks
• Updating the embeddings example and image to resnet101 to match other embeddings examples. Please replace the previous embeddings image you uploaded with this one if possible: https://user-images.githubusercontent.com/21222883/122239476-f79ef600-ce8e-11eb-814c-910fbc6d07ed.png

Here's the content of the new README section (all Flash code)

Visualization

Predictions from image and video tasks can be visualized through an integration with FiftyOne, allowing you to better understand and analyze how your model is performing.

from flash.core.data.utils import download_data
from flash.core.integrations.fiftyone import visualize
from flash.image import ObjectDetector
from flash.image.detection.serialization import FiftyOneDetectionLabels

# 1. Download the data
# Dataset Credit: https://www.kaggle.com/ultralytics/coco128
download_data(
    "https://github.com/zhiqwang/yolov5-rt-stack/releases/download/v0.3.0/coco128.zip",
    "data/",
)

# 2. Load the model from a checkpoint and use the FiftyOne serializer
model = ObjectDetector.load_from_checkpoint(
    "https://flash-weights.s3.amazonaws.com/object_detection_model.pt"
)
model.serializer = FiftyOneDetectionLabels()

# 3. Detect the object on the images
filepaths = [
    "data/coco128/images/train2017/000000000025.jpg",
    "data/coco128/images/train2017/000000000520.jpg",
    "data/coco128/images/train2017/000000000532.jpg",
]
predictions = model.predict(filepaths)

# 4. Visualize predictions in FiftyOne App
session = visualize(predictions, filepaths=filepaths)

[ehofesmann]

New docs image: