EfficientDet.Pytorch
EfficientDet.Pytorch copied to clipboard
toandaominh1997
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
I have seen on your ToDo you plan TorchScript compatibility? Can you indicate a timeline for this? I can not support directly, but if I could donate something let me...
``` (venv) jake@jake-ubuntu:~/Gits/EfficientDet.Pytorch$ python train.py --network efficientdet-d0 # Example train.py:302: UserWarning: You have chosen to seed training. This will turn on the CUDNN deterministic setting, which can slow down your...
ValueError: not enough values to unpack (expected 2, got 1) error come up with inputs, annotations = inputs when im doing multiprocessing-distributed
how many gpu and u guys using for batch 64? 1. which gpu u guys used? 2. how many gpu need for batch 32 or 64?
I have train the d0 on coco 2 weeks, whatever I change the learning rate, or other parameters, the val cl loss is around 1.0 but the map is 0...
File "/usr/local/lib/python3.7/site-packages/albumentations-0.4.1-py3.7.egg/albumentations/augmentations/bbox_utils.py", line 28, in ensure_data_valid if data.get(data_name) and len(data[data_name][0]) < 5: ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()...
loading annotations into memory... Done (t=10.57s) creating index... index created! loading annotations into memory... Done (t=0.33s) creating index... index created! Downloading: "http://storage.googleapis.com/public-models/efficientnet/efficientnet-b0-355c32eb.pth" to /home/itandroids/.cache/torch/checkpoints/efficientnet-b0-355c32eb.pth Traceback (most recent call last): File...
This just changes the EfficientNet URLs to make the automatic download work, fixing #148 .
Hi, I try to use your code to train my own dataset. The procedure is normal and the loss is down to 2.1 after 100 epochs training. But when I...
Metadata
Owner
Metadata
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch