def show_recons_seq(sess, ckptfile):
e2c.saver.restore(sess, ckptfile) # restore variable values
dataset = PlaneData("data/plane1.npz", "data/env1.png")
dataset.initialize()
T = e2c.T
print(T)
(x_vals, u_vals) = dataset.sample_seq(e2c.batch_size, T)
feed_dict = {}
for t in range(T):
feed_dict[e2c.xs[t]] = x_vals[t]
for t in range(T - 1):
feed_dict[e2c.us[t]] = u_vals[t]
fetches = e2c.x_recons + e2c.x_predicts
results = sess.run(fetches, feed_dict)
xr = results[:T - 1]
xp = results[T - 1:]
A, B = e2c.A, e2c.B
def getimgs(x):
padsize = 1
padval = .5
ph = B + 2 * padsize
pw = A + 2 * padsize
img = np.ones((ph, len(x) * pw)) * padval
for t in range(len(x)):
startc = t * pw + padsize
img[padsize:padsize + B, startc:startc + A] = x[t][1, :].reshape(
(A, B))
return img
fig, arr = plt.subplots(3, 1)
arr[0].matshow(getimgs(x_vals), cmap=plt.cm.gray, vmin=0, vmax=1)
arr[0].set_title('X')
arr[1].matshow(getimgs(xr), cmap=plt.cm.gray, vmin=0, vmax=1)
arr[1].set_title('Reconstruction')
arr[2].matshow(getimgs(xp), cmap=plt.cm.gray, vmin=0, vmax=1)
arr[2].set_title('Prediction')
plt.show()
def show_recons_seq(sess, ckptfile):
e2c.saver.restore(sess, ckptfile) # restore variable values
dataset=PlaneData("data/plane1.npz","data/env1.png")
dataset.initialize()
T=e2c.T
print(T)
(x_vals,u_vals)=dataset.sample_seq(e2c.batch_size,T)
feed_dict={}
for t in range(T):
feed_dict[e2c.xs[t]] = x_vals[t]
for t in range(T-1):
feed_dict[e2c.us[t]] = u_vals[t]
fetches=e2c.x_recons + e2c.x_predicts
results=sess.run(fetches,feed_dict)
xr=results[:T-1]
xp=results[T-1:]
A,B=e2c.A,e2c.B
def getimgs(x):
padsize=1
padval=.5
ph=B+2*padsize
pw=A+2*padsize
img=np.ones((ph,len(x)*pw))*padval
for t in range(len(x)):
startc=t*pw+padsize
img[padsize:padsize+B, startc:startc+A]=x[t][1,:].reshape((A,B))
return img
fig,arr=plt.subplots(3,1)
arr[0].matshow(getimgs(x_vals),cmap=plt.cm.gray,vmin=0,vmax=1)
arr[0].set_title('X')
arr[1].matshow(getimgs(xr),cmap=plt.cm.gray,vmin=0,vmax=1)
arr[1].set_title('Reconstruction')
arr[2].matshow(getimgs(xp),cmap=plt.cm.gray,vmin=0,vmax=1)
arr[2].set_title('Prediction')
plt.show()
# resume training
saver.restore(sess, "/ltmp/e2c-plane-single1.ckpt")
# test to make sure samples are actually trajectories
def getimgs(x):
padsize=1
padval=.5
ph=B+2*padsize
pw=A+2*padsize
img=np.ones((ph,len(x)*pw))*padval
for t in range(len(x)):
startc=t*pw+padsize
img[padsize:padsize+B, startc:startc+A]=x[t][20,:].reshape((A,B))
return img
(x_vals,u_vals)=dataset.sample_seq(batch_size,T)
plt.matshow(getimgs(x_vals),cmap=plt.cm.gray,vmin=0,vmax=1)
plt.show()
train_iters=2e5 # 5K iters
for i in range(int(train_iters)):
(x_vals,u_vals)=dataset.sample_seq(batch_size,T,replace=False)
feed_dict={}
for t in range(T):
feed_dict[xs[t]] = x_vals[t]
for t in range(T-1):
feed_dict[us[t]] = u_vals[t]
results=sess.run([loss,all_summaries,train_op],feed_dict)
if i%1000==0:
print("iter=%d : Loss: %f" % (i,results[0]))
# resume training
saver.restore(sess, "/ltmp/e2c-plane-single1.ckpt")
# test to make sure samples are actually trajectories
def getimgs(x):
padsize=1
padval=.5
ph=B+2*padsize
pw=A+2*padsize
img=np.ones((ph,len(x)*pw))*padval
for t in range(len(x)):
startc=t*pw+padsize
img[padsize:padsize+B, startc:startc+A]=x[t][20,:].reshape((A,B))
return img
(x_vals,u_vals)=dataset.sample_seq(batch_size,T)
plt.matshow(getimgs(x_vals),cmap=plt.cm.gray,vmin=0,vmax=1)
plt.show()
train_iters=2e5 # 5K iters
for i in range(int(train_iters)):
(x_vals,u_vals)=dataset.sample_seq(batch_size,T,replace=False)
feed_dict={}
for t in range(T):
feed_dict[xs[t]] = x_vals[t]
for t in range(T-1):
feed_dict[us[t]] = u_vals[t]
results=sess.run([loss,all_summaries,train_op],feed_dict)
if i%1000==0:
print("iter=%d : Loss: %f" % (i,results[0]))