def evaluate():
# Clear stats
stats.clearStats(True)
# Parse Dataset
cfg.CLASSES, TRAIN, VAL = train.parseDataset()
# Build Model
NET = birdnet.build_model()
# Train and return best net
best_net = train.train(NET, TRAIN, VAL)
# Load trained net
SNAPSHOT = io.loadModel(best_net)
# Test snapshot
MAP, TIME_PER_EPOCH = test.test(SNAPSHOT)
result = np.array([[MAP]], dtype='float32')
return result
# Early stopping?
if epoch - stats.getValue('best_epoch') >= cfg.EARLY_STOPPING_WAIT:
log.i('EARLY STOPPING!')
break
# Stop?
if cfg.DO_BREAK:
break
except KeyboardInterrupt:
log.i('KeyboardInterrupt')
cfg.DO_BREAK = True
break
# Status
log.i('TRAINING DONE!')
log.r(('BEST MLRAP:', stats.getValue('best_mlrap'), 'EPOCH:', stats.getValue('best_epoch')))
# Save best model and return
io.saveParams(stats.getValue('best_net'), cfg.CLASSES, stats.getValue('best_epoch'))
print('in training vish')
return io.saveModel(stats.getValue('best_net'), cfg.CLASSES, stats.getValue('best_epoch'))
if __name__ == '__main__':
cfg.CLASSES, TRAIN, VAL = parseDataset()
NET = birdnet.build_model()
net_name = train(NET, TRAIN, VAL)