recon = tf.squeeze(recon)
#########################################################################
# Start TF session (respecting OMP_NUM_THREADS)
nthr = os.getenv('OMP_NUM_THREADS')
if nthr is None:
sess = tf.Session()
else:
sess = tf.Session(config=tf.ConfigProto(
intra_op_parallelism_threads=int(nthr)))
sess.run(tf.global_variables_initializer())
#########################################################################
# Load latest model
print("Restoring model from " + mfile)
ut.loadNet(mfile, model.weights, sess)
print("Done!")
mses, psnrs = [], []
for nm in open(VLIST, 'r'):
nm = nm.strip()
if 'foreman' in nm or 'Parrots' in nm:
image = np.float32(imread(nm)[:, :, 0]) / 65535.
h, w = image.shape[:2]
else:
image = np.float32(imread(nm)) / 255.
h, w = image.shape
h_pad, w_pad = (PSZ - h % PSZ) % PSZ, (PSZ - w % PSZ) % PSZ
image = np.pad(image, ((0, h_pad), (0, w_pad)), 'constant')
nthr = os.getenv('OMP_NUM_THREADS')
if nthr is None:
sess = tf.Session()
else:
sess = tf.Session(config=tf.ConfigProto(
intra_op_parallelism_threads=int(nthr)))
sess.run(tf.global_variables_initializer())
#########################################################################
# Load saved weights if any
if niter > 0:
mfn = wts+"/iter_%06d.model.npz" % niter
sfn = wts+"/iter_%06d.state.npz" % niter
ut.mprint("Restoring model from " + mfn )
ut.loadNet(mfn,model.weights,sess)
ut.mprint("Restoring state from " + sfn )
ut.loadAdam(sfn,opt,model.weights,sess)
ut.mprint("Done!")
#########################################################################
# Main Training loop
stop=False
ut.mprint("Starting from Iteration %d" % niter)
sess.run(tset.fetchOp,feed_dict=tset.fdict())
while niter < MAXITER and not ut.stop:
## Validate model every so often
if niter % VALFREQ == 0: