I Still dont know where to define classes, I made a training where the image_index.txt files include 1 as label. I want to call 1 packages.
The training when through although the prediction response transmitts "cat": 1 back as class all the time. and the bboxes are way off, with always strating ymin: 0.0 and with a box width of 30 pixels. while my whole image is 2560 pixel. So one package is never 30pix wide.
Any idea where these problems might arrise?
I certainly used too few pictures, with 125 training images and 15 test images.
I checked the image_index.txt file and the bboxes are correct though.
I am using the SSD 300 reduced: VGG_ILSVRC_16_layers_fc_reduced.caffemodel
Are there like empty models which i can train from scratch does that bring better results?
Service Create:
"description":"generic image detection service",
"model":{
"repository":"/images/models/packages_detc",
"templates":"../templates/caffe/",
"weight": "VGG_ILSVRC_16_layers_fc_reduced.caffemodel"
},
"mllib":"caffe",
"type":"supervised",
"parameters":{
"input":{
"connector":"image",
"width":300,
"height":300,
"db": true,
"bbox": true
},
"mllib":{
"template":"ssd_300",
"nclasses":2,
"finetuning":true
}
},
}Training:
"service":"packages_detc",
"async":true,
"parameters":{
"input":{
"connector":"image",
"test_split":0.1,
"shuffle":true,
"height":300,
"width":300,
"db":true,
"rgb":true,
},
"mllib":{
"gpu":false,
"mirror":true,
"net":{
"batch_size":5,
"test_batch_size":5
},
"solver":{
"test_interval":250,
"iterations":500,
"base_lr":0.01,
"solver_type": "RMSPROP"
},
"noise":{"all_effects":true, "prob":0.001},
"distort":{"all_effects":true, "prob":0.01},
"bbox": true
},
"output":{
"measure":["map"],
}
},
"data":["/images/train/bboxes/train.txt", "/images/test/bboxes/test.txt"]
}test_split since you are passing train.txt and test.txt already
weights from this model instead of your current .caffemodel : https://www.deepdetect.com/models/detection_600/
prob of the distort object to 0.5
rgb to false
Can train now with detection_600 amma post my calls so people might find it in the future:
Create Service JSON:
{
"description":"generic image detection service",
"model":{
"repository":"/images/models/packages_detc",
"create_repository": true,
"templates":"../templates/caffe/",
"weight": "VGG_openimage_pretrain_ilsvrc_res_pred_openimage_detect_v2_SSD_openimage_pretrain_ilsvrc_res_pred_300x300_iter_1200000.caffemodel"
},
"mllib":"caffe",
"type":"supervised",
"parameters":{
"input":{
"connector":"image",
"width":300,
"height":300,
"db": true,
"bbox": true
},
"mllib":{
"template":"vgg_16",
"nclasses":602,
"finetuning":true
}
},
}Start training:
{
"service":"packages_detc",
"async":true,
"parameters":{
"input":{
"connector":"image",
"shuffle":true,
"height":300,
"width":300,
"db":true,
"rgb":false,
},
"mllib":{
"gpu":false,
"mirror":true,
"net":{
"batch_size":5,
"test_batch_size":5
},
"solver":{
"test_interval":250,
"iterations":1000,
"solver_type": "ADAM"
},
"noise":{"all_effects":true, "prob":0.001},
"distort":{"all_effects":true, "prob":0.5},
"bbox": true
},
"output":{
"measure":["map"],
}
},
"data":["/images/train/train.txt", "/images/train/train.txt"]
}
refinedet_512 and download https://www.deepdetect.com/models/pretrained/refinedet_512/VOC0712_refinedet_vgg16_512x512_iter_120000.caffemodel to use them as weights
batch_size and iter_size depending on your GPU. You can set iter_size to 4 to compensate. You'll need many more than 1000 iterations also, not sure what your data are, but 25000 is reasonable for a first run/try.
My image_32.txt files are build like:
<label> <xmin> <ymin> <xmax> <ymax>
601 22 32 673 756
601 because detection 600 had 600 classes in it and i wanted a new class
train.txt lines are :
[docker volume folder]/train/image_3.jpg- [docker volume folder]/train/image_3.txt
What do you mean wrong format?
hey @beniz - happy new year! long time since I've been looking through this stuff - tons of updates!! was just wondering if you're still building docker images with TF included. I'm trying to update our build process and I'm running into quite a number of issues with changes in DD affecting the build as well as changes in floopz/tensorflow_cc (and tensorflow itself).
Anyways, was just wondering if a (even CPU-only, for now) automated build is still happening with tensorflow that I can compare my build process too. Thanks in advance!
Also, do you have a reliable pipeline for converting models? I'd love to convert some of our models but there seems to be quite a bit of manual effort involved (not to mention validating/testing afterwards). If you have any sort of pipeline I'd be very interested :)
I believe the best pipeline for CPU would be to convert to ONNX and use onnxruntime. You could use onnxruntime directly, or we could add it to DD. It's actually on our optional todolist, but as we are driven by our customers and they never asked for CPU we didn't got it into DD. Not difficult for inference though.
Let me know your thoughts.
In practice, it sounds like you're more often training models and then deploying, rather than converting models - is that accurate? It sounds like I'll need to put together a methodology to compare and validate models before/after converting them. I'm hoping to not have to do it manually but it will probably come down to that....