-
Hello everyone.
I trained MobileNet-v1 SSD object detector using coco pretrained checkpoint as described in every tutorial - it's Ok. Then I just changed ssd_mobilenet_v1 with ssd_mobilenet_v1_keras …
-
When fine-tuning,according to the author's README,we should use command like this,
DATASET_DIR=/home/salight/data_PE/For_use/pe_records/
TRAIN_DIR=./logs/
CHECKPOINT_PATH=./checkpoints/ssd_300_vg…
-
Hi!
when I try to eval the model ,like this
> python object_detection/eval.py \
> --logtostderr \
> --pipeline_config_path=object_detection/VOC_car/ssd_mobilenet_v1_voc2012.config \
> …
-
## 🚀 Feature
Adding new models to the models section.
## Motivation
Many new models have been proposed in the recent years and do not exist in the models module.
For example, the EfficientNets…
-
Hello, did I have something setting wrong? It seems there are feature maps size mismatch.
However, it would not occur when I set `feature_extractor` type to "ssd_efficientnet"
` File "/usr/local/…
-
Is it possible to know how to fine tune a trained model with a different dataset (augmented data)?
There is no documentation about it or about the options in order to do it
-
@jmpesp was looking to figure out a maximum data transfer size and pointed out that things are set to 0 right now. I took a brief look at disks on romulus:
```
> ::prtconf -d nvme | ::devinfo -d …
-
I have error when i training (example from SSD_Train.ipynb) on my dataset
```
history = model.fit_generator(gen.generate(True), gen.train_batches,
nb_epoch, verbose=1,…
-
I followed the instructions to convert the weights from ssd_mobilenet_v2_coco_2018_03_29 to a Caffe model.
When I try to convert using:
mvNCCompile -w deploy.caffemodel -o graph -s 12 deploy.proto…
-
I just use ssd-300-vgg model to eval the voc2017 test data, but get very low map, i do not kown why?
can you help me?
zmhik updated
5 years ago