StanislasBertrand / RetinaFace-tf2

RetinaFace (RetinaFace: Single-stage Dense Face Localisation in the Wild, published in 2019) reimplemented in Tensorflow 2.0, with pretrained weights available !
MIT License
258 stars 21 forks source link

"Failed to interpret file './data/retinafaceweights.npy' as a pickle" => requirements.txt is not complete for reproducibility #28

Open GrigoriiTarasov opened 1 year ago

GrigoriiTarasov commented 1 year ago
faces, landmarks = detector.detect(img, 0.9)

/RetinaFace-tf2/src/retinafacetf2/networks/network_utils.py in load_weights(weight_file)
---> 16         weights_dict = np.load(weight_file, allow_pickle=True, encoding='bytes').item()
OSError: Failed to interpret file './data/retinafaceweights.npy' as a pickle
os.path.exists('./data/retinafaceweights.npy')
True

both in 1.19 numpy and 1.22 numpy

StanislasBertrand commented 1 year ago

Thanks, I havent ran this code in a while, do you have a working numpy version (compatible with tf2.4.0) that i could add to the requirements ?