How to use the saved model without retraining?
adityakrshnn opened this issue · 3 comments
I am trying to use the model but VGGNet_Model requires the VGGNet function which are the layers itself. Can you provide me the steps to use the pretrained model?
Hi mohammed;
I need "lenet.config" file to use "Tensorflow Object Detection API"
How can I write? or where can I find it?
example
SSD with Mobilenet v1, configured for Oxford-IIIT Pets Dataset.
Users should configure the fine_tune_checkpoint field in the train config as
well as the label_map_path and input_path fields in the train_input_reader and
eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
should be configured.
model {
ssd {
num_classes: 2
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
...
Same issue.
Trying to use pre-trained graph but keep getting errors and program requires VGGNet class.
Any updates?
Sorry guys I didn't have much time to look into the issue, and unfortunately I don't think I'd be able to check it in the foreseeable future.