Is there any version of the Inception model for ImageNet training coded without TensorFlow's Slim? I would like to make adjustments to the code but I'm not familiar with Slim...
Thank you!
Related
How do I find more info on how the ssd_mobilenet_v1 tflite model on TFHub was trained?
Was it trained in such a way that made it easy to convert it to tflite by avoiding certain ops not supported by tflite? Or was it trained normally, and then converted using the tflite converter with TF Select and the tips on this github issue?
Also, does anyone know if there's an equivalent mobilenet tflite model trained on OpenImagesV6? If not, what's the best starting point for training one?
I am not sure about about the exact origin of the model, but looks like it does have TFLite-compatible ops. From my experience, the best place to start for TFLite-compatible SSD models is with the TF2 Detection Zoo. You can convert any of the SSD models using these instructions.
To train your own model, you can follow these instructions that leverage Google Cloud.
I am using deepLab to generate semantic segmentation masked images for a video in cityscapes datasets. So, I started with the pre-trained model xception65_cityscapes_trainfine provided on the modelzoo and trained it further on the dataset.
I am curious to know How I can start training it from scratch? and not end up just using the pre-trained model? could anyone suggest a direction on How I can achieve it?
Any contribution from the community will be helpful and appreciated.
I have searched this for a while, but it seems Keras only has quantization feature after the model is trained. I wish to add Tensorflow fake quantization to my Keras sequential model. According to Tensorflow's doc, I need these two functions to do fake quantization: tf.contrib.quantize.create_training_graph() and tf.contrib.quantize.create_eval_graph().
My question is has anyone managed to add these two functions in a Keras model? If yes, where should these two function be added? For example, before model.compile or after model.fit or somewhere else? Thanks in advance.
I worked around by post-training quantization. Since my final goal is to train a mdoel for mobile device, instead of fake quantization during training, I exported keras .h5 file and converted to Tenforflow lite .tflite file directly (with post_training_quantize flag set to true). I tested this on a simple cifar-10 model. The original keras model and the quantized tflite model have very close accuracy (the quantized one a bit lower).
Post-training quantization: https://www.tensorflow.org/performance/post_training_quantization
Convert Keras model to tensorflow lite: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/lite/toco/g3doc/python_api.md
Used the tf-nightly tensorflow here: https://pypi.org/project/tf-nightly/
If you still want to do fake quantization (because for some model, post-training quantization may give poor accuracy according to Google), the original webpage is down last week. But you can find it from github: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/quantize
Update: Turns out post-quantization does not really quantize the model. During inference, it still uses float32 kernels to do calculations. Thus, I've switched to quantization-aware training. The accuracy is pretty good for my cifar10 model.
I'm seeking the trained model of ResNet or ResNetXt for tensorflow.
Can anyone offer me a link to download it?
Thanks in advance.
Here it is. article, code, link to pre-trained model and the accuracy on ImageNet test set.
https://github.com/tensorflow/models/tree/master/research/slim#pre-trained-models
I want to implements a faster-rcnn model using distributed tensorflow, But I have difficult to load a pretrained vgg model,How to do it? thanks
The TensorFlow tutorial on retraining inception is a good start to read. Then try to reproduce what it does starting from an already trained vgg model.