search

BichenWuUCB / squeezeDet

A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.
BSD 2-Clause "Simplified" License
739 stars 306 forks source link

Unsuccesful TensorSliceReader #100

Open jibola1997 opened 6 years ago

jibola1997 commented 6 years ago

The code brings up this error

InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./data/model_checkpoints/squeezedet/model.cpkt-87000: Not Found: ./data/model_checkpoints/squeeeDet

I can see the model in the model_checkpoints directory .

kiad4631 commented 5 years ago

The code brings up this error

InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on ./data/model_checkpoints/squeezedet/model.cpkt-87000: Not Found: ./data/model_checkpoints/squeeeDet

I can see the model in the model_checkpoints directory .

This is because of you have two data folder.one of them is beside demo.py and another one is in parent directory.and you need that one.so change demo.py to this:

tf.app.flags.DEFINE_string( 'checkpoint', '../data/model_checkpoints/squeezeDet/model.ckpt-87000', """Path to the model parameter file.""") tf.app.flags.DEFINE_string( 'input_path', '../data/sample.png', """Input image or video to be detected. Can process glob input such as """ """./data/00000*.png.""")