#!/usr/bin/env python
# coding: utf-8

# [![image](https://raw.githubusercontent.com/visual-layer/visuallayer/main/imgs/vl_horizontal_logo.png)](https://www.visual-layer.com)

# # Tutorial for working directly with feature vectors
# 
# [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/visual-layer/fastdup/blob/main/examples/feature_vectors.ipynb)
# [![Open in Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://kaggle.com/kernels/welcome?src=https://github.com/visual-layer/fastdup/blob/main/examples/feature_vectors.ipynb)

# ## Use case 1: compute feature vectors with fastdup and load them with numpy for further processing

# In[4]:


get_ipython().run_line_magic('pip', 'install -U fastdup')


# In[1]:


import fastdup
import numpy as np

#chnage to your image folder
input_dir = '/Users/dannybickson/visual_database/cxx/unittests/two_images/'

# Run fastup on an input image folder to create embeddings
fd = fastdup.create(input_dir=input_dir, work_dir='out')
fd.run(overwrite=True, print_summary=False)

# Read the embeddings to use them in python
# There are two images in the input_dir, so the embedding matrix is 2x 576. 
# Each row in the embedding matrix is an image.
flist, embedding_matrix = fastdup.load_binary_feature(filename='./out/atrain_features.dat')
print('Read embedding matrix of shape', embedding_matrix.shape)
print('Image filenames are')
print(flist)


# # Use case 2: Save your own binary features to work with fastdup

# ## Version 0.2

# In[2]:


import fastdup
import numpy as np
import os
input_dir = '/Users/dannybickson/visual_database/cxx/unittests/two_images/'
flist = os.listdir(input_dir)
flist = [os.path.join(input_dir, f) for f in flist]

# replace the below code with computation of your own features
matrix = np.random.rand(2, 576).astype('float32')

# save the embedding along the filenames into a working folder
get_ipython().system('mkdir -p embedding_input')
fastdup.save_binary_feature('embedding_input', flist, matrix)
fastdup.run('~/visual_database/cxx/unittests/two_images/', run_mode=2, work_dir='embedding_input')


# ## Version 1.0

# In[7]:


# Note: files should contain absolute path and not relative path
import fastdup
import numpy as np
import os
input_dir = '/Users/dannybickson/visual_database/cxx/unittests/two_images/'
flist = os.listdir(input_dir)
flist = [os.path.join(input_dir, f) for f in flist]

# replace the below code with computation of your own features
matrix = np.random.rand(2, 576).astype('float32')

fd2 = fastdup.create(input_dir=input_dir, work_dir='output2')
fd2.run(annotations=flist, embeddings=matrix, print_summary=False, overwrite=True)


# ## Wrap Up
# 
# Next, feel free to check out other tutorials -
# 
# + ⚡ [**Quickstart**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/quick-dataset-analysis.ipynb): Learn how to install fastdup, load a dataset and analyze it for potential issues such as duplicates/near-duplicates, broken images, outliers, dark/bright/blurry images, and view visually similar image clusters. If you're new, start here!
# + 🧹 [**Clean Image Folder**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/cleaning-image-dataset.ipynb): Learn how to analyze and clean a folder of images from potential issues and export a list of problematic files for further action. If you have an unorganized folder of images, this is a good place to start.
# + 🖼 [**Analyze Image Classification Dataset**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/analyzing-image-classification-dataset.ipynb): Learn how to load a labeled image classification dataset and analyze for potential issues. If you have labeled ImageNet-style folder structure, have a go!
# + 🎁 [**Analyze Object Detection Dataset**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/analyzing-object-detection-dataset.ipynb): Learn how to load bounding box annotations for object detection and analyze for potential issues. If you have a COCO-style labeled object detection dataset, give this example a try.

# 
# ## VL Profiler
# If you prefer a no-code platform to inspect and visualize your dataset, [**try our free cloud product VL Profiler**](https://app.visual-layer.com) - VL Profiler is our first no-code commercial product that lets you visualize and inspect your dataset in your browser. 
# 
# [Sign up](https://app.visual-layer.com) now, it's free.
# 
# [![image](https://raw.githubusercontent.com/visual-layer/fastdup/main/gallery/vl_profiler_promo.svg)](https://app.visual-layer.com)
# 
# As usual, feedback is welcome! 
# 
# Questions? Drop by our [Slack channel](https://visualdatabase.slack.com/join/shared_invite/zt-19jaydbjn-lNDEDkgvSI1QwbTXSY6dlA#/shared-invite/email) or open an issue on [GitHub](https://github.com/visual-layer/fastdup/issues).

#