squeezeDet icon indicating copy to clipboard operation
squeezeDet copied to clipboard

A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.

Results 85 squeezeDet issues
Sort by recently updated
recently updated
newest added

Hello, I have a GTX 1060 6G GPU, so I can fine tune the model only. I know the images and annotation should be in KITTI format. no problem about...

Hello. I wonder if you have some experience on the issue of box matching. Most CNN based object detection have box matching strategies to assign prior(anchor) box to ground truth...

@BichenWuUCB I have a few questions as I was playing around with squeezedet - 1. Is it possible using the squeezedet architecture to train the network on size of let's...

@ALL Hey, anyone who knows why the evaluation results (i.e. Car_easy =0.00....) like as follows: Evaluating detections... Running: ./src/dataset/kitti-eval/cpp/evaluate_object ./data/KITTI/training ./data/KITTI/ImageSets/val.txt ./data/model_checkpoints/squeezeDet/val/detection_files_200000 3769 /bin/sh: 1: ./src/dataset/kitti-eval/cpp/evaluate_object: not found Evaluation summary:...

I try to convert the squeezedet checkpoint to frozen graph and then conversion tflite but I cant. my command is: python3 freeze_graph.py --input_meta_graph=/home/davari/detection_on_mobile/squeezeDet/model.ckpt-95000.meta --input_checkpoint=/home/davari/detection_on_mobile/squeezeDet/model.ckpt-95000 --output_node_names="bbox/trimming/bbox,probability/class_idx,probability/score" --input_binary=True --output_graph=/home/davari/detection_on_mobile/squeezeDet/model-95000.pb is it correct...

Hi Bichen, I have training set with image resolution of **1280x720**. When I modified the image height and width in "**kitti_model_config.py**" and "**kitti_squeezeDet_config.py**", I got the following error ValueError: Cannot...

Hi @BichenWuUCB I basically tried to retrain the model as it is and managed to get good results when validating. Thanks for sharing the work. I then try to freeze...

Hi, Are there any plans to publish a frozen model (in the .pb file)? I tried myself but failed to convert one since the code is not entirely friendly to...

The code brings up this error InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./data/model_checkpoints/squeezedet/model.cpkt-87000: Not Found: ./data/model_checkpoints/squeeeDet I can see the model in the model_checkpoints directory .

Hi! with `demo.py`, it produce detections not accurate as the demo image you provided ![out_sample](https://user-images.githubusercontent.com/18298163/35802663-e42b3822-0aab-11e8-964f-71f35c4c56fd.png) I use `tf 1.4`, do you have any idea? thanks