pytorch-ssd icon indicating copy to clipboard operation
pytorch-ssd copied to clipboard

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like C...

Results 112 pytorch-ssd issues
Sort by recently updated
recently updated
newest added

Hi, I am trying to train the mobilenet based model on my custom dataset. ![Capture](https://user-images.githubusercontent.com/110823484/184096011-55bc7fec-4c71-401d-8b52-3d05f02f4fe6.PNG) Above image shows the data format. I modeified the open images dataloader to create my...

Some data doesn't have the `is_difficult` parameter. Created a check to look for `is_difficult` in file, when it's not there default the value to 0.

Hello, thank you for this amazing repo, Do you have the mobilenet-ssd but v2 ? with the imagenet classes ? I am searching online for mobilnet-ssd-v2 pretrained model with pytorch...

basenet model of mobilenetv3 ssd not found so how we train for mobilenetv3 model.Please guide

Hi! Im trying to use this repo to re-train an ssd model. As the readme said, i tried to run : `python3 run_ssd_live_demo.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt` But i got this...

![image](https://user-images.githubusercontent.com/57226206/175507173-0eeb4800-3c96-4815-ad66-25b2a7866213.png)

Hello I am trying to run it on my Windows machine. My dataset seems to be correct. When I start the training I get an error. **Here is the call...

Hi, I have trained SSD with backbone VGG16 for the Gun dataset. The error I got for different pre-trained models: vgg16_reducedfc: `python train_ssd.py --dataset_type open_images --datasets /home/aass/Hoang-Cuong/ekobot/data --net "vgg16-ssd" --base_net...

Hi, I am using transfer learning with Re-training SSD-Mobilenet like [here](https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-collect-detection.md). My dataset contains 8000+ images (annotated sport players) (I have grayscale camera so all images are in grayscale (edit:...