ValueError: Invalid value for argument filters. Expected a strictly positive value. Received filters=0.

[stnridy]

Check if applicable

• I used Google/Bing/other search engines to thoroughly research my question and DID NOT find any suitable answers
• Additionally I went through the issues in this repository/MaixPy/Tensorflow repositories and DID NOT find any suitable answers

Describe the bug

1. I try to use theegacy-yolov2 branch as mentioned in Can't upload script via MaixPy IDE TinkerGen/Mark-micropython#1

%load_ext tensorboard
#we need imgaug 0.4 for image augmentations to work properly, see https://stackoverflow.com/questions/62580797/in-colab-doing-image-data-augmentation-with-imgaug-is-not-working-as-intended
!pip uninstall -y imgaug && pip uninstall -y albumentations && pip install imgaug==0.4
!pip install --upgrade --no-cache-dir gdown
!git clone -b legacy-yolov2 https://github.com/AIWintermuteAI/aXeleRate.git
import sys
sys.path.append('/content/aXeleRate')
from axelerate import setup_training, setup_inference

3. below is my config

config = {
        "model":{
            "type":                 "Detector",
            "architecture":         "MobileNet7_5",
            "input_size":           224,
            "anchors":              [[[0.76120044, 0.57155991], [0.6923348, 0.88535553], [0.47163042, 0.34163313]]],
            "labels":               ["licence"],
            "obj_thresh" : 		    0.7,
            "iou_thresh" : 		    0.5,
            "coord_scale" : 		  1.0,
            "class_scale" : 		1.0,
            "object_scale" : 		  5.0,
            "no_object_scale" : 	1.0
        },
        "weights" : {
            "full":   				  "",
            "backend":   		    "imagenet"
        },
        "train" : {
            "actual_epoch":        100,
            "train_image_folder":   "/content/MyDrive/MyDrive/ALPR/im",
            "train_annot_folder":   "/content/MyDrive/MyDrive/ALPR/images",
            "train_times":          1,
            "valid_image_folder":   "/content/MyDrive/MyDrive/ALPR/validation",
            "valid_annot_folder":   "/content/MyDrive/MyDrive/ALPR/validation_annot",
            "valid_times":          1,
            "valid_metric":         "recall",
            "batch_size":           4,
            "learning_rate":        1e-4,
            "saved_folder":   		F"/content/MyDrive/MyDrive/ALPR/ww44p3_result",
            "first_trainable_layer": "",
            "augmentation":				  True,
            "is_only_detect" : 		  False
        },
        "converter" : {
            "type":   				["k210"]
        }
}

Expected behavior

Expected to be able to train the model

Platform

• Version/commit number of aXeleRate --> legacy-yolov2

Relevant log output

ValueError                                Traceback (most recent call last)
<ipython-input-14-bbd5d1611139> in <cell line: 3>()
      1 from keras import backend as K
      2 K.clear_session()
----> 3 model_path = setup_training(config_dict=config)

7 frames
/content/aXeleRate/axelerate/train.py in setup_training(config_file, config_dict)
    163         os.makedirs(dirname)
    164 
--> 165     return(train_from_config(config, dirname))
    166 
    167 

/content/aXeleRate/axelerate/train.py in train_from_config(config, project_folder)
    114 
    115         # 1. Construct the model
--> 116         yolo = create_yolo(config['model']['architecture'],
    117                            labels,
    118                            input_size,

/content/aXeleRate/axelerate/networks/yolo/frontend.py in create_yolo(architecture, labels, input_size, anchors, coord_scale, class_scale, object_scale, no_object_scale, weights)
     34     n_classes = len(labels)
     35     n_boxes = int(len(anchors)/2)
---> 36     yolo_network = create_yolo_network(architecture, input_size, n_classes, n_boxes, weights)
     37     yolo_loss = YoloLoss(yolo_network.get_grid_size(),
     38                          n_classes,

/content/aXeleRate/axelerate/networks/yolo/backend/network.py in create_yolo_network(architecture, input_size, nb_classes, nb_box, weights)
     14                         weights):
     15     feature_extractor = create_feature_extractor(architecture, input_size, weights)
---> 16     yolo_net = YoloNetwork(feature_extractor,
     17                            input_size,
     18                            nb_classes,

/content/aXeleRate/axelerate/networks/yolo/backend/network.py in __init__(self, feature_extractor, input_size, nb_classes, nb_box)
     33 
     34         # make the object detection layer
---> 35         output_tensor = Conv2D(nb_box * (4 + 1 + nb_classes), (1,1), strides=(1,1),
     36                                padding='same',
     37                                name='detection_layer_{}'.format(nb_box * (4 + 1 + nb_classes)),

/usr/local/lib/python3.10/dist-packages/keras/src/dtensor/utils.py in _wrap_function(layer_instance, *args, **kwargs)
     94                     layout_args[variable_name + "_layout"] = layout
     95 
---> 96         init_method(layer_instance, *args, **kwargs)
     97 
     98         # Inject the layout parameter after the invocation of __init__()

/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/conv2d.py in __init__(self, filters, kernel_size, strides, padding, data_format, dilation_rate, groups, activation, use_bias, kernel_initializer, bias_initializer, kernel_regularizer, bias_regularizer, activity_regularizer, kernel_constraint, bias_constraint, **kwargs)
    177         **kwargs
    178     ):
--> 179         super().__init__(
    180             rank=2,
    181             filters=filters,

/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py in __init__(self, rank, filters, kernel_size, strides, padding, data_format, dilation_rate, groups, activation, use_bias, kernel_initializer, bias_initializer, kernel_regularizer, bias_regularizer, activity_regularizer, kernel_constraint, bias_constraint, trainable, name, conv_op, **kwargs)
    127             filters = int(filters)
    128         if filters is not None and filters <= 0:
--> 129             raise ValueError(
    130                 "Invalid value for argument `filters`. "
    131                 "Expected a strictly positive value. "

ValueError: Invalid value for argument `filters`. Expected a strictly positive value. Received filters=0.



https://colab.research.google.com/drive/1ZVO7KDgd_X1aEVd7Jh6gAFDNlQLxhCiJ#scrollTo=AjQngERURAWI

[muaz919]

Hi, @AIWintermuteAI, I see your issues closed about implementing YOLOv3 on the Maix board. -> #63

Since there is an option to use yolov3 in your Readme, can you provide the pre-compiled firmware that has been deleted before?

Pre-compiled firmare

[AIWintermuteAI]

Hi @muaz919 !
Please create a separate issue as this is unrelated.