Not able to run CLIP Model using from_present

[carrycooldude]

Current Behavior:

Expected Behavior:

not able to load CLIP model even though I installed keras-nlp too

Steps To Reproduce:

Version:

Anything else:

This is my colab link

[sachinprasadhs]

You need to install the dependencies and load the clip model as below.

!pip install -U keras-cv
!pip install -U keras-nlp
!pip install -U keras

import tensorflow as tf
from tensorflow.keras.layers import Input, Dense, Concatenate
from tensorflow.keras.models import Model
from keras_cv.models import CLIP
import numpy as np

# Load the pre-trained CLIP model from KerasCV
clip_model = CLIP.from_preset("clip-vit-base-patch16")

for Image and Text encoder, you can use as below.

# Define inputs
image_input = Input(shape=(224, 224, 3), name='image_input')
text_input = Input(shape=(77,), name='text_input', dtype=tf.int32)

# Process image through CLIP
image_embeds = clip_model.image_encoder(image_input)

# Process text through CLIP
text_embeds = clip_model.text_encoder(text_input)

[github-actions]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[carrycooldude]

thanks @sachinprasadhs , it's working but I guess it's not in docs
Can I contribute to it?

[sachinprasadhs]

Sure

[github-actions]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.