minus31 / blazeface Goto Github PK

Hi sir nice work you have here .. I have two questions :

• I have a dataset with annotations xmin , ymin , xmax , ymax how can I set the labels for this data ?
• Did you train this model using this approach on a full dataset ? Are the results promising ?

Many thanks :)

Hello, thank you for sharing good code.
Could you give me some idea for dataset?
We really need this model for our project.
Is there any open dataset which can be used for this code?
or Could you share your dataset for our project?
I will promise to add you contributer for our project thank you.
contact : howtowhy(at)gmail.com

Inside dataloader.py:

img_files = glob.glob(dataset_dir)
img_files = [f for f in img_files if f[-3:] in IM_EXTENSIONS]

with open(label_path, "rb") as f:
    labels = pickle.load(f)

numofData = len(img_files)# endwiths(png,jpg ...)
data_idx = np.arange(numofData)

labels = pickle.load(f)
what'a the output of this array "labels"?

The output layer for conf prediction is of shape (None, 896, 1) but my input label shape is (BATCH_SIZE, 1).
I am getting a shape mismatch error here.

Traceback (most recent call last): File "main.py", line 156, in <module> blazeface.train() File "main.py", line 123, in train use_multiprocessing=True) File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 1303, in fit_generator steps_name='steps_per_epoch') File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_generator.py", line 265, in model_iteration batch_outs = batch_function(*batch_data) File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 979, in train_on_batch class_weight=class_weight, reset_metrics=reset_metrics) File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 253, in train_on_batch extract_tensors_from_dataset=True) File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 2503, in _standardize_user_data y, self._feed_loss_fns, feed_output_shapes) File "/Users/aniketmaurya/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 742, in check_loss_and_target_compatibility ' while using as loss ' + loss_name + '`. '

ValueError: A target array with shape (1, 13, 1) was passed for an output of shape (None, 896, 1) while using as loss binary_crossentropy.
This loss expects targets to have the same shape as the output.`